exo: handle -c flag for multiprocessing helpers in frozen apps

When Python's multiprocessing spawns child processes on macOS (using the
"spawn" method), it also spawns helper processes like the resource tracker
by executing:

    ./frozen_app -c "from multiprocessing.resource_tracker import main; main()"

A frozen PyInstaller app doesn't understand `-c` natively - it just runs
main(). This causes the resource tracker to fail silently.

This adds a minimal `-c` handler that intercepts the flag, extracts the
inline code, and exec()s it before main() runs. This is required for the
Process() spawn in runner_supervisor.py to work correctly in the DMG.

Note that the pyinstaller docs say `freeze_support` is supposed to make
this work, but it doesn't.

Test plan:

Hardware setup: 3x Mac Studio M3 Ultra connected all-to-all with TB5

- Built a DMG[0].
- Installed on the Macs.
- Started an instance. Got an error this time in ~/.exo/exo.log. The
  last DMG from main doesn't show anything when an instance starts, this
  now shows the errors.

[0] https://github.com/exo-explore/exo/actions/runs/20464409279/job/58804485197

.circleci/config.yml

@@ -1,346 +0,0 @@
-version: 2.1
-
-orbs:
-  python: circleci/python@2
-
-commands:
-  run_chatgpt_api_test:
-    parameters:
-      inference_engine:
-        type: string
-      model_id:
-        type: string
-      expected_output:
-        type: string
-      prompt:
-        type: string
-    steps:
-      - run:
-          name: Run chatgpt api integration test (<<parameters.inference_engine>>, <<parameters.model_id>>)
-          command: |
-            source env/bin/activate
-
-            # Set CLANG=1 for tinygrad only
-            if [ "<<parameters.inference_engine>>" = "tinygrad" ]; then
-              pip install llvmlite
-              export TOKENIZERS_PARALLELISM=true SUPPORT_BF16=0 CLANG=1
-            fi
-
-            # Start first instance
-            HF_HOME="$(pwd)/.hf_cache_node1" DEBUG_DISCOVERY=7 DEBUG=7 exo --inference-engine <<parameters.inference_engine>> \
-              --node-id "node1" --listen-port 5678 --broadcast-port 5679 --chatgpt-api-port 8000 \
-              --chatgpt-api-response-timeout 900 --disable-tui > output1.log &
-            PID1=$!
-            tail -f output1.log &
-            TAIL1=$!
-
-            # Start second instance
-            HF_HOME="$(pwd)/.hf_cache_node2" DEBUG_DISCOVERY=7 DEBUG=7 exo --inference-engine <<parameters.inference_engine>> \
-              --node-id "node2" --listen-port 5679 --broadcast-port 5678 --chatgpt-api-port 8001 \
-              --chatgpt-api-response-timeout 900 --disable-tui > output2.log &
-            PID2=$!
-            tail -f output2.log &
-            TAIL2=$!
-
-            # Remember to kill the tail processes at the end
-            trap 'kill $TAIL1 $TAIL2' EXIT
-
-            # Wait for discovery
-            sleep 10
-
-            # Function to check if processes are still running
-            check_processes() {
-              if ! kill -0 $PID1 2>/dev/null; then
-                echo "First instance (PID $PID1) died unexpectedly. Log output:"
-                cat output1.log
-                exit 1
-              fi
-              if ! kill -0 $PID2 2>/dev/null; then
-                echo "Second instance (PID $PID2) died unexpectedly. Log output:"
-                cat output2.log
-                exit 1
-              fi
-            }
-
-            # Check processes before proceeding
-            check_processes
-
-            echo "Sending request to first instance..."
-            response_1=$(curl -s http://localhost:8000/v1/chat/completions \
-              -H "Content-Type: application/json" \
-              -d '{
-                "model": "<<parameters.model_id>>",
-                "messages": [{"role": "user", "content": "<<parameters.prompt>>"}],
-                "temperature": 0.7
-              }')
-            echo "Response 1: $response_1"
-
-            # Check processes after first response
-            check_processes
-
-            echo "Sending request to second instance..."
-            response_2=$(curl -s http://localhost:8001/v1/chat/completions \
-              -H "Content-Type: application/json" \
-              -d '{
-                "model": "<<parameters.model_id>>",
-                "messages": [{"role": "user", "content": "<<parameters.prompt>>"}],
-                "temperature": 0.7
-              }')
-            echo "Response 2: $response_2"
-
-            # Check processes after second response
-            check_processes
-
-            # Stop both instances
-            kill $PID1 $PID2
-
-            echo ""
-            # Extract content using jq and check if it contains expected output
-            content1=$(echo "$response_1" | jq -r '.choices[0].message.content')
-            content2=$(echo "$response_2" | jq -r '.choices[0].message.content')
-
-            if [[ "$content1" != *"<<parameters.expected_output>>"* ]] || [[ "$content2" != *"<<parameters.expected_output>>"* ]]; then
-              echo "Test failed: Response does not match '<<parameters.expected_output>>'"
-              echo "Response 1 content: $content1"
-              echo ""
-              echo "Response 2 content: $content2"
-              echo "Output of first instance:"
-              cat output1.log
-              echo "Output of second instance:"
-              cat output2.log
-              exit 1
-            else
-              echo "Test passed: Response from both nodes matches '<<parameters.expected_output>>'"
-            fi
-
-jobs:
-  unit_test:
-    macos:
-      xcode: "16.0.0"
-    resource_class: m2pro.large
-    steps:
-      - checkout
-      - run:
-          name: Set up Python
-          command: |
-            brew install python@3.12
-            python3.12 -m venv env
-            source env/bin/activate
-      - run:
-          name: Install dependencies
-          command: |
-            source env/bin/activate
-            pip install --upgrade pip
-            pip install .
-      - run:
-          name: Run tests
-          command: |
-            source env/bin/activate
-            # set TEMPERATURE to 0 for deterministic sampling
-            echo "Running inference engine tests..."
-            METAL_DEVICE_WRAPPER_TYPE=1 METAL_DEBUG_ERROR_MODE=0 METAL_XCODE=1 TEMPERATURE=0 python3 -m exo.inference.test_inference_engine
-            echo "Running tokenizer tests..."
-            python3 ./test/test_tokenizers.py
-            python3 ./test/test_model_helpers.py
-
-  discovery_integration_test:
-    macos:
-      xcode: "16.0.0"
-    steps:
-      - checkout
-      - run:
-          name: Set up Python
-          command: |
-            brew install python@3.12
-            python3.12 -m venv env
-            source env/bin/activate
-      - run:
-          name: Install dependencies
-          command: |
-            source env/bin/activate
-            pip install --upgrade pip
-            pip install .
-      - run:
-          name: Run discovery integration test
-          command: |
-            source env/bin/activate
-            DEBUG_DISCOVERY=7 DEBUG=7 exo --node-id "node1" --listen-port 5678 --broadcast-port 5679 --chatgpt-api-port 8000 --disable-tui > output1.log 2>&1 &
-            PID1=$!
-            DEBUG_DISCOVERY=7 DEBUG=7 exo --node-id "node2" --listen-port 5679 --broadcast-port 5678 --chatgpt-api-port 8001 --disable-tui > output2.log 2>&1 &
-            PID2=$!
-            sleep 10
-            kill $PID1 $PID2
-            if grep -q "Peer statuses: {\\'node2\\': \\'is_connected=True, health_check=True" output1.log && ! grep -q "Failed to connect peers:" output1.log && grep -q "Peer statuses: {\\'node1\\': \\'is_connected=True, health_check=True" output2.log && ! grep -q "Failed to connect peers:" output2.log; then
-              echo "Test passed: Both instances discovered each other"
-              exit 0
-            else
-              echo "Test failed: Devices did not discover each other"
-              echo "Output of first instance:"
-              cat output1.log
-              echo "Output of second instance:"
-              cat output2.log
-              exit 1
-            fi
-
-  chatgpt_api_integration_test_mlx:
-    macos:
-      xcode: "16.0.0"
-    resource_class: m2pro.large
-    steps:
-      - checkout
-      - run:
-          name: Set up Python
-          command: |
-            brew install python@3.12
-            python3.12 -m venv env
-            source env/bin/activate
-      - run:
-          name: Install dependencies
-          command: |
-            source env/bin/activate
-            pip install --upgrade pip
-            pip install .
-      - run_chatgpt_api_test:
-          inference_engine: mlx
-          model_id: llama-3.2-1b
-          prompt: "Keep responses concise. Who was the king of pop?"
-          expected_output: "Michael Jackson"
-
-  chatgpt_api_integration_test_dummy:
-    macos:
-      xcode: "16.0.0"
-    resource_class: m2pro.large
-    steps:
-      - checkout
-      - run:
-          name: Set up Python
-          command: |
-            brew install python@3.12
-            python3.12 -m venv env
-            source env/bin/activate
-      - run:
-          name: Install dependencies
-          command: |
-            source env/bin/activate
-            pip install --upgrade pip
-            pip install .
-      - run_chatgpt_api_test:
-          inference_engine: dummy
-          model_id: dummy
-          prompt: "Dummy prompt."
-          expected_output: "dummy"
-
-  chatgpt_api_integration_test_tinygrad:
-    macos:
-      xcode: "16.0.0"
-    resource_class: m2pro.large
-    steps:
-      - checkout
-      - run:
-          name: Set up Python
-          command: |
-            brew install python@3.12
-            python3.12 -m venv env
-            source env/bin/activate
-      - run:
-          name: Install dependencies
-          command: |
-            source env/bin/activate
-            pip install --upgrade pip
-            pip install .
-      - run_chatgpt_api_test:
-          inference_engine: tinygrad
-          model_id: llama-3.2-1b
-          prompt: "Keep responses concise. Who was the king of pop?"
-          expected_output: "Michael Jackson"
-
-  measure_pip_sizes:
-    macos:
-      xcode: "16.0.0"
-    steps:
-      - checkout
-      - run:
-          name: Set up Python
-          command: |
-            brew install python@3.12
-            python3.12 -m venv env
-            source env/bin/activate
-      - run:
-          name: Install dependencies and measure sizes
-          command: |
-            source env/bin/activate
-            pip install --upgrade pip
-            pip install .
-            python ./extra/pipsize.py --json ./pipsize.json
-      - store_artifacts:
-          path: ./pipsize.json
-          destination: pip-sizes.json
-
-  check_line_count:
-    docker:
-      - image: cimg/python:3.10
-    steps:
-      - checkout
-
-      - run:
-          name: Setup git for PR comparison
-          command: |
-            if [[ -n "$CIRCLE_PULL_REQUEST" ]]; then
-              PR_NUMBER=$(echo $CIRCLE_PULL_REQUEST | rev | cut -d'/' -f1 | rev)
-              BASE_BRANCH=$(curl -s -H "Circle-Token: $CIRCLE_TOKEN" \
-                "https://circleci.com/api/v2/project/github/$CIRCLE_PROJECT_USERNAME/$CIRCLE_PROJECT_REPONAME/pipeline/$CIRCLE_WORKFLOW_ID" \
-                | jq -r '.target_branch')
-
-              git clone -b $BASE_BRANCH --single-branch \
-                https://github.com/$CIRCLE_PROJECT_USERNAME/$CIRCLE_PROJECT_REPONAME.git \
-                base_branch
-            fi
-
-      - run:
-          name: Install dependencies
-          command: |
-            python -m pip install --upgrade pip
-            pip install tabulate
-
-      - run:
-          name: Run line count check
-          command: |
-            if [[ -n "$CIRCLE_PULL_REQUEST" ]]; then
-              python extra/line_counter.py base_branch .
-            else
-              python extra/line_counter.py .
-            fi
-
-      - store_artifacts:
-          path: line-count-snapshot.json
-          destination: line-count-snapshot.json
-
-      - store_artifacts:
-          path: line-count-diff.json
-          destination: line-count-diff.json
-
-      - run:
-          name: Create test results directory
-          command: |
-            mkdir -p test-results/line-count
-            cp line-count-*.json test-results/line-count/
-
-      - store_test_results:
-          path: test-results
-
-workflows:
-  version: 2
-  build_and_test:
-    jobs:
-      - check_line_count:
-          filters:
-            branches:
-              only: /.*/
-            tags:
-              only: /.*/
-      - unit_test
-      - discovery_integration_test
-      - chatgpt_api_integration_test_mlx
-      - chatgpt_api_integration_test_tinygrad
-      - chatgpt_api_integration_test_dummy
-      - measure_pip_sizes

.clauderules

@@ -0,0 +1,63 @@
+# Claude Code Rules - Follow Every Rule Exactly
+
+You must prioritize straightforward code semantics, well-named types, clear function signatures, and robust, carefully-chosen abstractions. Think about how your decisions might impact these aspects of code quality before proposing any changes.
+
+You have access to all modern Python features from Python 3.13, 3.12, 3.11...
+
+**When you're done making changes, remove any redundant comments; remaining comments should only apply to complex code segments, adding relevant context.**
+
+## 1. Code Discipline
+
+* Eliminate superfluous `try`/`catch` and `if` branches through strict typing and static analysis.
+* Use pure functions unless you must mutate fixed state—then wrap that state in a class.
+* Every function is **referentially transparent**: same inputs ⇒ same outputs, no hidden state, no unintended I/O.
+* Put side-effects in injectable "effect handlers"; keep core logic pure.
+
+## 2. Naming
+
+* Choose descriptive, non-abbreviated names—no 3-letter acronyms or non-standard contractions.
+* Anyone reading a function's type signature alone should grasp its purpose without extra context.
+
+## 3. Typing
+
+* Maintain **strict, exhaustive** typing; never bypass the type-checker.
+* Default to `Literal[...]` when an enum-like set is needed.
+* Prefer built-in types; when two values share structure but differ in meaning, enforce separation:
+  * Use `typing.NewType` for primitives (zero runtime cost).
+  * For serializable objects, add a `type: str` field that states the object's identity.
+
+## 4. Pydantic
+
+* Read, respect, and rely on Pydantic documentation.
+* Centralize a common `ConfigDict` with `frozen=True` and `strict=True` (or stricter) and reuse it everywhere.
+* For hierarchies of `BaseModel` variants, declare a discriminated union with `typing.Annotated[Base, Field(discriminator='variant')]`; publish a single `TypeAdapter[Base]` so all variants share one strict validator.
+
+## 5. IDs & UUIDs
+
+* Subclass Pydantic's `UUID4` for custom ID types.
+* Generate fresh IDs with `uuid.uuid4()`.
+* Create idempotency keys by hashing *persisted* state plus a **function-specific salt** to avoid collisions after crashes.
+
+## 6. Error Handling
+
+* Catch an exception **only** where you can handle or transform it meaningfully.
+* State in the docstring **where** each exception is expected to be handled and **why**.
+
+## 7. Dependencies
+
+* Introduce new external dependencies only after approval.
+* Request only libraries common in production environments.
+
+## 8. Use of `@final` & Freezing
+
+* Mark classes, methods, and variables as `@final` or otherwise immutable wherever applicable.
+
+## 9. Repository Workflow
+
+If you spot a rule violation within code that you've not been asked to work on directly, inform the user rather than patching it ad-hoc.
+
+---
+
+### One-Sentence Summary
+
+Write strictly-typed, pure, self-describing Python that uses Pydantic, well-scoped side-effects, immutable state, approved dependencies, and explicit error handling.

.cursorrules

@@ -0,0 +1,64 @@
+# follow **every** rule exactly; report any violation instead of silently fixing it.
+
+You must prioritize straightforward code semantics, well-named types, clear function signatures, and robust, carefully-chosen abstractions. Think about how your decisions might impact these aspects of code quality before proposing any changes.
+
+You can use the advanced features of `typing`. You have access to all of the new features from Python 3.13, 3.12, 3.11...
+
+**When you're done making your changes, remove any redundant comments that you may have left; the comments that remain should only apply to complex segments of code, adding relevant context.**
+
+## 1. Code Discipline
+
+* Eliminate superfluous `try` / `catch` and `if` branches through strict typing and static analysis.
+* Use pure functions unless you must mutate fixed state—then wrap that state in a class.
+* Every function is **referentially transparent**: same inputs ⇒ same outputs, no hidden state, no unintended I/O.
+* Put side-effects in injectable “effect handlers”; keep core logic pure.
+
+## 2. Naming
+
+* Choose descriptive, non-abbreviated names—no 3-letter acronyms or non-standard contractions.
+* Anyone reading a function’s type signature alone should grasp its purpose without extra context.
+
+## 3. Typing
+
+* Maintain **strict, exhaustive** typing; never bypass the type-checker.
+* Default to `Literal[...]` when an enum-like set is needed.
+* Prefer built-in types; when two values share structure but differ in meaning, enforce separation:
+  * Use `typing.NewType` for primitives (zero runtime cost).
+  * For serialisable objects, add a `type: str` field that states the object’s identity.
+
+## 4. Pydantic
+
+* Read, respect, and rely on Pydantic docs.
+* Centralise a common `ConfigDict` with `frozen=True` and `strict=True` (or stricter) and reuse it everywhere.
+* For hierarchies of `BaseModel` variants, declare a discriminated union with `typing.Annotated[Base, Field(discriminator='variant')]`; publish a single `TypeAdapter[Base]` so all variants share one strict validator.
+
+## 5. IDs & UUIDs
+
+* Subclass Pydantic’s `UUID4` for custom ID types.
+* Generate fresh IDs with `uuid.uuid4()`.
+* Create idempotency keys by hashing *persisted* state plus a **function-specific salt** to avoid collisions after crashes.
+
+## 6. Error Handling
+
+* Catch an exception **only** where you can handle or transform it meaningfully.
+* State in the docstring **where** each exception is expected to be handled and **why**.
+
+## 7. Dependencies
+
+* Introduce new external dependencies only after approval.
+* Request only libraries common in production environments.
+
+## 8. Use of `@final` & Freezing
+
+* Mark classes, methods, and variables as `@final` or otherwise immutable wherever applicable.
+
+## 9. Repository Workflow
+
+If you spot a rule violation within code that you've not been asked to work on directly, inform the user rather than patching it ad-hoc.
+
+
+---
+
+### One-Sentence Summary
+
+Write strictly-typed, pure, self-describing Python that uses Pydantic, well-scoped side-effects, immutable state, approved dependencies, and explicit error handling

.envrc

@@ -0,0 +1 @@
+use flake

.gitattributes

@@ -1,2 +0,0 @@
-*.mp3 filter=lfs diff=lfs merge=lfs -text
-*.png filter=lfs diff=lfs merge=lfs -text

.githooks/post-checkout

@@ -0,0 +1,3 @@
+#!/bin/sh
+command -v git-lfs >/dev/null 2>&1 || { printf >&2 "\n%s\n\n" "This repository is configured for Git LFS but 'git-lfs' was not found on your path. If you no longer wish to use Git LFS, remove this hook by deleting the 'post-checkout' file in the hooks directory (set by 'core.hookspath'; usually '.git/hooks')."; exit 2; }
+git lfs post-checkout "$@"

.githooks/post-commit

@@ -0,0 +1,3 @@
+#!/bin/sh
+command -v git-lfs >/dev/null 2>&1 || { printf >&2 "\n%s\n\n" "This repository is configured for Git LFS but 'git-lfs' was not found on your path. If you no longer wish to use Git LFS, remove this hook by deleting the 'post-commit' file in the hooks directory (set by 'core.hookspath'; usually '.git/hooks')."; exit 2; }
+git lfs post-commit "$@"

.githooks/post-merge

@@ -0,0 +1,3 @@
+#!/bin/sh
+command -v git-lfs >/dev/null 2>&1 || { printf >&2 "\n%s\n\n" "This repository is configured for Git LFS but 'git-lfs' was not found on your path. If you no longer wish to use Git LFS, remove this hook by deleting the 'post-merge' file in the hooks directory (set by 'core.hookspath'; usually '.git/hooks')."; exit 2; }
+git lfs post-merge "$@"

.githooks/pre-push

@@ -0,0 +1,3 @@
+#!/bin/sh
+command -v git-lfs >/dev/null 2>&1 || { printf >&2 "\n%s\n\n" "This repository is configured for Git LFS but 'git-lfs' was not found on your path. If you no longer wish to use Git LFS, remove this hook by deleting the 'pre-push' file in the hooks directory (set by 'core.hookspath'; usually '.git/hooks')."; exit 2; }
+git lfs pre-push "$@"

.github/CODEOWNERS

@@ -0,0 +1,3 @@
+*   @ToxicPine
+*   @AlexCheema
+*   @GeluVrabie

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,43 @@
+---
+name: Bug Report
+about: Create a report to help us improve
+title: '[BUG] '
+labels: bug
+assignees: ''
+---
+
+## Describe the bug
+
+A clear and concise description of what the bug is.
+
+## To Reproduce
+
+Steps to reproduce the behavior:
+1.
+2.
+3.
+
+## Expected behavior
+
+A clear and concise description of what you expected to happen.
+
+## Actual behavior
+
+A clear and concise description of what actually happened.
+
+## Environment
+
+- macOS Version:
+- EXO Version:
+- Hardware:
+  - Device 1: (e.g., MacBook Pro M1 Max, 32GB RAM)
+  - Device 2: (e.g., Mac Mini M2, 16GB RAM)
+  - Additional devices:
+- Interconnection:
+  - (e.g., Thunderbolt 4 cable between Device 1 and 2)
+  - (e.g., WiFi 6 for Device 3)
+  - (e.g., 10GbE Ethernet between all devices)
+
+## Additional context
+
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,11 @@
+---
+name: Feature Request
+about: Suggest an idea for this project
+title: ''
+labels: enhancement
+assignees: ''
+---
+
+<!-- Please use a clear, descriptive title above -->
+
+Describe what you'd like to see added to EXO.

.github/actions/conditional-commit/action.yml

@@ -0,0 +1,16 @@
+name: Commit if changed
+description: "Create a commit when the working tree is dirty"
+
+inputs:
+  message:
+    description: "Commit message"
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - name: Commit changed files
+      shell: bash
+      run: |
+        git diff --quiet && exit 0
+        git commit -am "${{ inputs.message }}"

.github/actions/format/action.yml

@@ -0,0 +1,10 @@
+name: Format Code
+
+description: "Run code formatter"
+
+runs:
+  using: "composite"
+  steps:
+    - name: Format code
+      run: nix --extra-experimental-features nix-command --extra-experimental-features flakes develop -c just fmt
+      shell: bash

.github/actions/lint-check/action.yml

@@ -0,0 +1,10 @@
+name: Lint Check
+
+description: "Check for lint errors"
+
+runs:
+  using: "composite"
+  steps:
+    - name: Lint check
+      run: nix --extra-experimental-features nix-command --extra-experimental-features flakes develop -c just lint-check
+      shell: bash

.github/actions/lint/action.yml

@@ -0,0 +1,10 @@
+name: Lint Code
+
+description: "Run code linter"
+
+runs:
+  using: "composite"
+  steps:
+    - name: Lint code
+      run: nix --extra-experimental-features nix-command --extra-experimental-features flakes develop -c just lint
+      shell: bash

.github/actions/regenerate-protobufs/action.yml

@@ -0,0 +1,10 @@
+name: Regenerate Protobufs
+
+description: "Regenerate protobuf files"
+
+runs:
+  using: "composite"
+  steps:
+    - name: Regenerate protobufs
+      run: nix --extra-experimental-features nix-command --extra-experimental-features flakes develop -c just regenerate-protobufs
+      shell: bash

.github/actions/setup-python-uv/action.yml

@@ -0,0 +1,20 @@
+name: Setup Python & uv
+
+description: "Regenerate Python environment from uv.lock"
+
+runs:
+  using: "composite"
+  steps:
+    - name: Install uv
+      uses: astral-sh/setup-uv@v6
+      with:
+        enable-cache: true
+        cache-dependency-glob: uv.lock
+
+    - name: Install Python
+      run: uv python install
+      shell: bash
+
+    - name: Sync
+      run: uv sync --locked --all-extras --dev
+      shell: bash

.github/actions/typecheck/action.yml

@@ -0,0 +1,12 @@
+name: Type Check
+
+description: "Run type checker"
+
+runs:
+  using: "composite"
+  steps:
+    - name: Run type checker
+      run: |
+        nix --extra-experimental-features nix-command --extra-experimental-features flakes develop -c just sync
+        nix --extra-experimental-features nix-command --extra-experimental-features flakes develop -c just check
+      shell: bash

.github/actions/unit-test/action.yml

@@ -0,0 +1,12 @@
+name: Unit Test
+
+description: "Run unit tests"
+
+runs:
+  using: "composite"
+  steps:
+    - name: Run unit tests
+      run: |
+        nix --extra-experimental-features nix-command --extra-experimental-features flakes develop -c just sync-clean
+        nix --extra-experimental-features nix-command --extra-experimental-features flakes develop -c just test-fast
+      shell: bash

.github/actions/verify-clean/action.yml

@@ -0,0 +1,20 @@
+name: Verify Clean Working Tree
+
+description: "Fail the job if the previous step left the working tree dirty"
+
+inputs:
+  step:
+    description: "The name of the step that just executed"
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - name: Check git diff
+      shell: bash
+      run: |
+        if ! git diff --quiet; then
+          echo "Error: ${{ inputs.step }} left working tree dirty." >&2
+          git --no-pager diff >&2
+          exit 1
+        fi 

.github/benchmark-dashboard/README.md

@@ -0,0 +1,159 @@
+# EXO Benchmark Dashboard
+
+A fully self-contained, browser-based dashboard for tracking EXO benchmark performance over time.
+
+## Features
+
+- 📊 **Success Rate Tracking**: Monitor cluster reliability across commits
+- ⚡ **Response Time Analysis**: Track average request completion times  
+- 🎯 **Throughput Metrics**: Tokens per second visualization
+- 📈 **Request Distribution**: Success/failure breakdown over time
+- 🔄 **Auto-Refresh**: Updates every 60 seconds
+- 📺 **TV-Ready**: Large, clear visualizations perfect for display
+- 🔐 **Secure**: Credentials stored in browser localStorage only
+- 🌐 **No Backend**: Directly accesses S3 from the browser
+
+## Quick Start
+
+### Option 1: Direct File Access (Simplest)
+
+Just open the HTML file directly in your browser:
+
+```bash
+open .github/benchmark-dashboard/index.html
+```
+
+Then click "Configure AWS Credentials" and enter your keys.
+
+### Option 2: URL Parameters (For Quick Setup)
+
+```bash
+# Serve with credentials in URL (they'll be moved to localStorage)
+open ".github/benchmark-dashboard/index.html?accessKey=YOUR_KEY&secretKey=YOUR_SECRET&region=us-east-1"
+```
+
+The credentials will be saved to localStorage and removed from the URL immediately.
+
+### Option 3: Simple HTTP Server
+
+```bash
+# From repo root
+python3 -m http.server 8080
+
+# Then open: http://localhost:8080/.github/benchmark-dashboard/
+```
+
+## AWS Credentials
+
+The dashboard needs read-only access to the `exo-benchmark-results` S3 bucket.
+
+### Required IAM Permissions
+
+```json
+{
+  "Version": "2012-10-17",
+  "Statement": [
+    {
+      "Effect": "Allow",
+      "Action": [
+        "s3:GetObject",
+        "s3:ListBucket"
+      ],
+      "Resource": [
+        "arn:aws:s3:::exo-benchmark-results",
+        "arn:aws:s3:::exo-benchmark-results/*"
+      ]
+    }
+  ]
+}
+```
+
+### Security Notes
+
+- ✅ Credentials stored in browser `localStorage` only
+- ✅ Never sent to any server (except AWS)
+- ✅ All S3 access happens client-side
+- ✅ Use read-only IAM credentials
+- ⚠️ Don't commit credentials to git
+- ⚠️ Use a dedicated read-only IAM user
+
+## TV/Kiosk Mode
+
+For permanent display on a TV:
+
+### macOS
+```bash
+open -a "Google Chrome" --args --kiosk ".github/benchmark-dashboard/index.html"
+```
+
+### Linux
+```bash
+chromium-browser --kiosk --app="file://$(pwd)/.github/benchmark-dashboard/index.html"
+```
+
+### Auto-start on Boot
+
+Create a simple startup script:
+
+```bash
+#!/bin/bash
+# /usr/local/bin/start-benchmark-dashboard.sh
+
+cd /path/to/exo
+python3 -m http.server 8080 &
+sleep 2
+chromium-browser --kiosk http://localhost:8080/.github/benchmark-dashboard/
+```
+
+## Data Displayed
+
+### Summary Cards
+- **Latest Success Rate**: Most recent benchmark success percentage with trend
+- **Avg Response Time**: Latest average response time in ms with trend
+- **Total Benchmarks**: Count of all benchmarks run
+- **Active Configurations**: Number of unique benchmark configs
+
+### Charts
+1. **Success Rate Over Time**: Line chart showing reliability trends
+2. **Average Response Time**: Performance over time (lower is better)
+3. **Throughput**: Tokens/second metric (higher is better)
+4. **Request Distribution**: Stacked bar chart of successes/failures
+
+## How It Works
+
+1. **Loads AWS SDK**: Uses AWS SDK for JavaScript (browser version)
+2. **Lists S3 Objects**: Fetches all files from `s3://exo-benchmark-results/bench/`
+3. **Downloads Results**: Fetches each JSON result file
+4. **Parses & Visualizes**: Uses Chart.js to create interactive charts
+5. **Auto-Refreshes**: Polls S3 every 60 seconds for new results
+
+## Customization
+
+To modify the dashboard:
+
+1. Edit `index.html` 
+2. Adjust `REFRESH_INTERVAL` for different polling frequency
+3. Modify chart colors/styles in the Chart.js configuration
+4. Add new metrics by extending the results parsing
+
+## Troubleshooting
+
+**"AWS credentials not configured"**
+- Click "Configure AWS Credentials" and enter your keys
+
+**"Error loading benchmark data"**
+- Check AWS credentials are correct
+- Verify S3 bucket name is `exo-benchmark-results`
+- Ensure IAM user has read permissions
+- Check browser console for detailed errors
+
+**"No benchmark results found"**
+- Wait for benchmark workflows to run
+- Verify results are being uploaded to S3
+- Check S3 bucket has files in `bench/` prefix
+
+**Charts not updating**
+- Check browser console for errors
+- Verify network connectivity to S3
+- Try refreshing the page manually
+

.github/configs/README.md

@@ -0,0 +1,186 @@
+# EXO Benchmark Configurations
+
+This directory contains configuration files for the EXO staged benchmark system.
+
+## Overview
+
+The staged benchmark system allows you to run complex, multi-stage load tests against EXO clusters. Each stage can have different characteristics:
+
+- **Prompt Length**: Number of tokens in the input prompt
+- **Generation Length**: Maximum tokens to generate in the response
+- **Time Between Requests**: Delay (in seconds) between firing consecutive requests
+- **Iterations**: Number of requests to send in this stage
+
+Requests are **fire-and-forget** - they don't wait for the previous request to complete. This allows you to test overlapping request handling and measure success rates under load.
+
+## Configuration Files
+
+### `bench_simple.yaml`
+A minimal configuration that replicates the behavior of the original `bench.py` script:
+- Single stage with 1 iteration
+- Short prompt (~20 tokens)
+- Generates up to 100 tokens
+
+This is useful for quick smoke tests.
+
+### `bench_config.yaml`
+A comprehensive multi-stage benchmark with:
+1. **Warmup** (10 requests): Light load with short prompts
+2. **Medium Load** (20 requests): Moderate load with medium prompts
+3. **Stress Test** (30 requests): Heavy overlapping requests with long prompts
+4. **Cooldown** (5 requests): Light load to wind down
+
+This tests the cluster's behavior under varying load patterns.
+
+## Configuration Schema
+
+```yaml
+# Hardware configuration - maps runner labels to instance counts
+hardware_plan:
+  M3ULTRA_GPU80_512GB: 4
+
+# Environment variables to set on each node (optional)
+environment:
+  OVERRIDE_MEMORY_MB: 512
+
+# Timeout for instance and runner readiness (seconds)
+timeout_seconds: 600
+
+# Model instances to run concurrently
+model_ids:
+  - "mlx-community/Llama-3.2-1B-Instruct-4bit"
+
+# Benchmark stages
+stages:
+  - name: "stage_name"              # Human-readable name for this stage
+    prompt_length: 100               # Target prompt length in tokens
+    generation_length: 200           # Max tokens to generate
+    time_between_requests: 2.0       # Seconds between firing requests
+    iterations: 10                   # Number of requests in this stage
+```
+
+## Running Benchmarks
+
+### Via GitHub Actions
+
+**Automatic (every commit):**
+- The **`bench`** workflow runs automatically on every push
+- Uses `bench_simple.yaml` as the default configuration
+- All settings (hardware plan, timeout, environment variables, models, stages) are defined in the config file
+
+**Manual (on-demand):**
+1. Go to **Actions** → **bench** workflow
+2. Click **Run workflow**
+3. Configure:
+   - **Config File**: Path to your YAML config (default: `.github/configs/bench_simple.yaml`)
+     - `.github/configs/bench_simple.yaml` for quick tests
+     - `.github/configs/bench_config.yaml` for complex multi-stage tests
+   
+All other settings (hardware plan, timeout, environment variables, models, stages) are read from the specified config file.
+
+### Via Command Line
+
+```bash
+# Start EXO on localhost:8000
+uv run exo --api-port 8000
+
+# Run simple benchmark (1 stage, 1 iteration)
+python3 .github/scripts/bench.py \
+  --api-port 8000 \
+  --config .github/configs/bench_simple.yaml \
+  --expected-nodes 1 \
+  --is-primary true \
+  --timeout-seconds 600
+
+# Run complex staged benchmark (4 stages, multiple iterations)
+python3 .github/scripts/bench.py \
+  --api-port 8000 \
+  --config .github/configs/bench_config.yaml \
+  --expected-nodes 1 \
+  --is-primary true \
+  --timeout-seconds 600
+```
+
+## Output Metrics
+
+For each stage, the benchmark reports:
+
+- **Total Requests**: Number of requests fired
+- **Successful Requests**: Requests that completed successfully
+- **Failed Requests**: Requests that encountered errors
+- **Success Rate**: Percentage of successful requests
+- **Total Tokens**: Sum of all tokens generated across successful requests
+- **Avg Tokens/Request**: Average tokens per successful request
+- **Avg Time/Request**: Average completion time per successful request
+
+A JSON summary is also printed for easy parsing and storage.
+
+## Creating Custom Benchmarks
+
+To create a custom benchmark:
+
+1. Copy an existing config file (e.g., `bench_config.yaml`)
+2. Modify the stages to match your test scenario
+3. Save it in this directory with a descriptive name
+4. Run it using the workflow or command line
+
+### Example: Sustained Load Test
+
+```yaml
+hardware_plan:
+  M3ULTRA_GPU80_512GB: 2
+
+environment:
+  OVERRIDE_MEMORY_MB: 1024
+
+timeout_seconds: 600
+
+model_ids:
+  - "mlx-community/Llama-3.2-1B-Instruct-4bit"
+
+stages:
+  - name: "sustained_load"
+    prompt_length: 200
+    generation_length: 150
+    time_between_requests: 0.5     # Very fast - 2 requests/second
+    iterations: 100                 # Run for ~50 seconds
+```
+
+### Example: Varying Prompt Sizes
+
+```yaml
+hardware_plan:
+  M4PRO_GPU16_24GB: 3
+
+timeout_seconds: 900
+
+model_ids:
+  - "mlx-community/Llama-3.2-1B-Instruct-4bit"
+
+stages:
+  - name: "tiny_prompts"
+    prompt_length: 10
+    generation_length: 100
+    time_between_requests: 1.0
+    iterations: 10
+    
+  - name: "medium_prompts"
+    prompt_length: 200
+    generation_length: 100
+    time_between_requests: 1.0
+    iterations: 10
+    
+  - name: "large_prompts"
+    prompt_length: 1000
+    generation_length: 100
+    time_between_requests: 1.0
+    iterations: 10
+```
+
+## Tips
+
+- **Overlapping Requests**: Set `time_between_requests` < expected completion time to test concurrent request handling
+- **Sequential Requests**: Set `time_between_requests` > expected completion time to ensure requests don't overlap
+- **Realistic Load**: Model real usage patterns by varying prompt/generation lengths across stages
+- **Success Rate**: A 100% success rate indicates the cluster handled the load well; lower rates suggest capacity limits
+

.github/configs/bench_config.yaml

@@ -0,0 +1,49 @@
+# EXO Staged Benchmark Configuration
+# This configuration defines a multi-stage load test for EXO clusters
+
+# Hardware configuration - maps runner labels to instance counts
+hardware_plan:
+  M3ULTRA_GPU80_512GB: 4
+
+# Environment variables to set on each node (optional)
+environment:
+  OVERRIDE_MEMORY_MB: 512
+
+# Timeout for instance and runner readiness (seconds)
+timeout_seconds: 600
+
+# Multiple instances run concurrently on the cluster
+model_ids:
+  - "mlx-community/Qwen3-0.6B-4bit"
+  - "mlx-community/Qwen3-0.6B-4bit"
+
+# Stages run sequentially, each with its own characteristics
+stages:
+  # Stage 1: Light load with short prompts
+  - name: "warmup"
+    prompt_length: 50          # Number of tokens in prompt
+    generation_length: 100     # Max tokens to generate
+    time_between_requests: 5.0 # Seconds between firing requests
+    iterations: 10             # Number of requests to send in this stage
+    
+  # Stage 2: Medium load with medium prompts
+  - name: "medium_load"
+    prompt_length: 200
+    generation_length: 150
+    time_between_requests: 3.0
+    iterations: 20
+    
+  # Stage 3: Heavy load with long prompts - requests will overlap
+  - name: "stress_test"
+    prompt_length: 500
+    generation_length: 200
+    time_between_requests: 1.0  # Fast firing - will definitely overlap
+    iterations: 30
+    
+  # Stage 4: Cool down with simple prompts
+  - name: "cooldown"
+    prompt_length: 50
+    generation_length: 50
+    time_between_requests: 10.0
+    iterations: 5
+

.github/configs/bench_simple.yaml

@@ -0,0 +1,125 @@
+# Simple single-shot benchmark
+# Tests 2 instances concurrently on 2 nodes
+
+# Hardware configuration - maps runner labels to instance counts
+hardware_plan:
+  puffin4: 1
+  puffin8: 1
+
+# Environment variables to set on each node
+environment:
+  PLACEHOLDER: "placeholder"
+  # OVERRIDE_MEMORY_MB: 50000
+  MLX_METAL_FAST_SYNCH: 1
+
+# Timeout for instance and runner readiness (seconds)
+timeout_seconds: 1800
+
+# Model instances to run concurrently
+model_ids:
+  # - "mlx-community/DeepSeek-V3.1-8bit"
+  # - "mlx-community/Kimi-K2-Instruct-4bit"
+  - "mlx-community/Kimi-K2-Thinking"
+  # - "mlx-community/Qwen3-235B-A22B-4bit"
+  # - "mlx-community/Llama-3.3-70B-Instruct-4bit"
+  # - "mlx-community/Llama-3.3-70B-Instruct-8bit"
+  # - "mlx-community/Llama-3.2-1B-Instruct-4bit"
+
+# Sharding strategy: "Pipeline" or "Tensor"
+sharding: "Tensor"
+
+# Instance type: "MlxRing" or "MlxIbv"
+instance_meta: "MlxIbv"
+
+# If true, run requests sequentially (no overlap); if false, fire-and-forget (default: false)
+no_overlap: true
+
+# Benchmark stages
+# pp: 64, 256, 1024, 2048, 4096, 8192, 16384
+# g: 64, 512
+stages:
+  # - name: "simple"
+  #   prompt_length: 512
+  #   generation_length: 10
+  #   time_between_requests: 2.0
+  #   iterations: 5
+  # - name: "pp64_g64"
+  #   prompt_length: 64
+  #   generation_length: 64
+  #   time_between_requests: 2.0
+  #   iterations: 5
+  # - name: "pp64_g64"
+  #   prompt_length: 64
+  #   generation_length: 64
+  #   time_between_requests: 2.0
+  #   iterations: 5
+  # - name: "pp64_g512"
+  #   prompt_length: 64
+  #   generation_length: 512
+  #   time_between_requests: 2.0
+  #   iterations: 10
+  # - name: "pp256_g64"
+  #   prompt_length: 256
+  #   generation_length: 64
+  #   time_between_requests: 2.0
+  #   iterations: 5
+  - name: "pp256_g64"
+    prompt_length: 256
+    generation_length: 64
+    time_between_requests: 2.0
+    iterations: 5
+  # - name: "pp256_g512"
+  #   prompt_length: 256
+  #   generation_length: 512
+  #   time_between_requests: 2.0
+  #   iterations: 10
+  # - name: "pp1024_g64"
+  #   prompt_length: 1024
+  #   generation_length: 64
+  #   time_between_requests: 2.0
+  #   iterations: 5
+  # - name: "pp1024_g512"
+  #   prompt_length: 1024
+  #   generation_length: 512
+  #   time_between_requests: 2.0
+  #   iterations: 10
+  # - name: "pp2048_g64"
+  #   prompt_length: 2048
+  #   generation_length: 64
+  #   time_between_requests: 2.0
+  #   iterations: 5
+  # - name: "pp2048_g512"
+  #   prompt_length: 2048
+  #   generation_length: 512
+  #   time_between_requests: 2.0
+  #   iterations: 10
+  # - name: "pp4096_g64"
+  #   prompt_length: 4096
+  #   generation_length: 64
+  #   time_between_requests: 2.0
+  #   iterations: 4
+  # - name: "pp4096_g512"
+  #   prompt_length: 4096
+  #   generation_length: 512
+  #   time_between_requests: 2.0
+  #   iterations: 10
+  # - name: "pp8192_g64"
+  #   prompt_length: 8192
+  #   generation_length: 64
+  #   time_between_requests: 2.0
+  #   iterations: 5
+  # - name: "pp8192_g512"
+  #   prompt_length: 8192
+  #   generation_length: 512
+  #   time_between_requests: 2.0
+  #   iterations: 5
+  # - name: "pp16384_g64"
+  #   prompt_length: 16384
+  #   generation_length: 64
+  #   time_between_requests: 2.0
+  #   iterations: 10
+  # - name: "pp16384_g512"
+  #   prompt_length: 16384
+  #   generation_length: 512
+  #   time_between_requests: 2.0
+  #   iterations: 10

.github/pull_request_template.md

@@ -0,0 +1,23 @@
+## Motivation
+
+<!-- Why is this change needed? What problem does it solve? -->
+<!-- If it fixes an open issue, please link to the issue here -->
+
+## Changes
+
+<!-- Describe what you changed in detail -->
+
+## Why It Works
+
+<!-- Explain why your approach solves the problem -->
+
+## Test Plan
+
+### Manual Testing
+<!-- Hardware: (e.g., MacBook Pro M1 Max 32GB, Mac Mini M2 16GB, connected via Thunderbolt 4) -->
+<!-- What you did: -->
+<!-- - -->
+
+### Automated Testing
+<!-- Describe changes to automated tests, or how existing tests cover this change -->
+<!-- - -->

.github/scripts/build_matrix.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+import json
+import os
+from typing import NotRequired, TypedDict, cast
+
+import yaml
+
+
+class MatrixEntry(TypedDict):
+    label: str
+    index: int
+
+
+class MatrixInclude(TypedDict):
+    label: str
+    index: int
+    is_primary: bool
+    expected_nodes: int
+
+
+class Config(TypedDict):
+    hardware_plan: dict[str, int]
+    timeout_seconds: NotRequired[int]
+    environment: NotRequired[dict[str, str]]
+
+
+# Read the config file
+config_file: str = os.environ["CONFIG_FILE"]
+with open(config_file, "r") as f:
+    config: Config = cast(Config, yaml.safe_load(f))
+
+# Extract hardware plan from config
+plan: dict[str, int] = config["hardware_plan"]
+if not plan:
+    raise ValueError(f"No hardware_plan found in {config_file}")
+
+# Build matrix entries
+entries: list[MatrixEntry] = []
+for label, count in plan.items():
+    for idx in range(count):
+        entries.append({"label": label, "index": idx})
+
+total_nodes: int = len(entries)
+matrix: dict[str, list[MatrixInclude]] = {
+    "include": [
+        {
+            "label": e["label"],
+            "index": e["index"],
+            "is_primary": (i == 0),
+            "expected_nodes": total_nodes,
+        }
+        for i, e in enumerate(entries)
+    ]
+}
+
+# Extract other config values
+timeout_seconds: int = config.get("timeout_seconds", 600)
+environment: dict[str, str] = config.get("environment", {})
+
+# Output to GitHub Actions
+with open(os.environ["GITHUB_OUTPUT"], "a") as f:
+    f.write(f"matrix={json.dumps(matrix)}\n")
+    f.write(f"config_file={config_file}\n")
+    f.write(f"timeout_seconds={timeout_seconds}\n")
+    f.write(f"environment={json.dumps(environment)}\n")
+
+print(f"Matrix: {json.dumps(matrix)}")
+print(f"Config file: {config_file}")
+print(f"Timeout: {timeout_seconds}")
+print(f"Environment: {json.dumps(environment)}")

.github/workflows/BENCH_USAGE.md

@@ -0,0 +1,156 @@
+# Benchmark Workflow Usage
+
+## Overview
+
+The `bench_matrix.yml` workflow enables distributed benchmarking of models across multiple self-hosted macOS runners with different hardware configurations.
+
+## Workflow Inputs
+
+| Input | Description | Default | Required |
+|-------|-------------|---------|----------|
+| `model_id` | Model ID to benchmark | `mlx-community/Llama-3.2-1B-Instruct-4bit` | Yes |
+| `hardware_plan` | JSON mapping of runner labels to counts | `{"M4PRO_GPU16_24GB": 1}` | Yes |
+| `prompt` | Benchmark prompt text | `What is the capital of France?` | No |
+| `timeout_seconds` | Timeout for instance/runner readiness | `600` | No |
+
+## Hardware Plan Format
+
+The `hardware_plan` input is a JSON object mapping runner labels to the number of machines:
+
+```json
+{
+  "M4PRO_GPU16_24GB": 2,
+  "M3ULTRA_GPU80_512GB": 1
+}
+```
+
+This example would:
+- Start 2 runners with the `M4PRO_GPU16_24GB` label
+- Start 1 runner with the `M3ULTRA_GPU80_512GB` label
+- Total of 3 runners coordinating on a single distributed inference instance
+
+## How It Works
+
+1. **Planning Job** (`plan`)
+   - Runs on `ubuntu-latest`
+   - Parses the `hardware_plan` JSON
+   - Generates a dynamic matrix with one entry per runner
+   - Only the first runner (index 0) is marked as `is_primary`
+
+2. **Benchmark Worker Jobs** (`bench_worker`)
+   - Each job runs on a self-hosted macOS runner with the specified label
+   - All runners start EXO in parallel
+   - The primary runner creates the model instance
+   - All runners wait for their assigned runner to be ready (Loaded/Running status)
+   - The primary runner executes the benchmark and prints results
+   - The primary runner deletes the instance
+
+## Example Usage
+
+### Single Machine Benchmark
+
+```yaml
+model_id: mlx-community/Llama-3.2-1B-Instruct-4bit
+hardware_plan: '{"M4PRO_GPU16_24GB": 1}'
+prompt: What is the capital of France?
+timeout_seconds: 600
+```
+
+### Multi-Machine Distributed Benchmark
+
+```yaml
+model_id: mlx-community/Llama-3.2-3B-Instruct-4bit
+hardware_plan: '{"M4PRO_GPU16_24GB": 2, "M3ULTRA_GPU80_512GB": 1}'
+prompt: Explain quantum computing in simple terms.
+timeout_seconds: 900
+```
+
+## Benchmark Output
+
+The primary runner outputs a JSON object with benchmark results:
+
+```json
+{
+  "model_id": "mlx-community/Llama-3.2-1B-Instruct-4bit",
+  "instance_id": "abc-123-def",
+  "tokens": 42,
+  "elapsed_s": 2.451,
+  "tps": 17.136
+}
+```
+
+Where:
+- `tokens`: Number of chunks/tokens generated
+- `elapsed_s`: Total elapsed time in seconds
+- `tps`: Tokens per second (tokens / elapsed_s)
+
+## Runner Requirements
+
+Each self-hosted runner must:
+- Be labeled with appropriate hardware tags (e.g., `M4PRO_GPU16_24GB`)
+- Have the `self-hosted` and `macOS` labels
+- Have Nix installed with flakes enabled
+- Have network connectivity to other runners in the same job
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│ GitHub Actions Workflow (bench_matrix.yml)                  │
+├─────────────────────────────────────────────────────────────┤
+│                                                              │
+│  ┌────────────────┐                                         │
+│  │  Plan Job      │                                         │
+│  │  (ubuntu)      │──┬─► Matrix: [{label, index, primary}] │
+│  └────────────────┘  │                                      │
+│                      │                                      │
+│  ┌───────────────────▼──────────────────────────────────┐  │
+│  │  Bench Worker Jobs (Matrix)                         │  │
+│  ├──────────────────────────────────────────────────────┤  │
+│  │                                                       │  │
+│  │  Runner 0 (Primary)     Runner 1         Runner 2    │  │
+│  │  ┌─────────────┐       ┌─────────────┐ ┌──────────┐ │  │
+│  │  │ Start EXO   │       │ Start EXO   │ │ Start EXO│ │  │
+│  │  │ Create Inst │       │ Wait...     │ │ Wait...  │ │  │
+│  │  │ Wait Ready  │       │ Wait Ready  │ │ Wait...  │ │  │
+│  │  │ Run Bench   │       │ (idle)      │ │ (idle)   │ │  │
+│  │  │ Print TPS   │       │             │ │          │ │  │
+│  │  │ Delete Inst │       │             │ │          │ │  │
+│  │  └─────────────┘       └─────────────┘ └──────────┘ │  │
+│  └───────────────────────────────────────────────────────┘  │
+└─────────────────────────────────────────────────────────────┘
+```
+
+## Implementation Details
+
+### `scripts/bench.py`
+
+A standalone Python script that:
+- Creates instance (primary only)
+- Polls `/state` endpoint until instance and all runners are ready
+- Executes chat completion with timing (primary only)
+- Parses SSE stream and counts tokens
+- Computes TPS metrics
+- Cleans up instance (primary only)
+
+### Key Functions
+
+- `wait_for_instance()`: Polls until instance with model_id appears
+- `wait_for_runners_ready()`: Polls until expected number of runners reach Loaded/Running status
+- `run_benchmark()`: Executes chat completion, measures time, counts tokens
+
+## Troubleshooting
+
+### Instance never becomes ready
+- Check EXO logs in the workflow output
+- Verify model_id is valid and accessible
+- Increase `timeout_seconds`
+
+### Runner mismatch
+- Ensure hardware_plan counts match available labeled runners
+- Check runner labels match exactly (case-sensitive)
+
+### Network issues
+- Verify runners can communicate on the network
+- Check firewall rules between runner hosts
+

.github/workflows/bench.yml

@@ -0,0 +1,305 @@
+name: bench
+
+on: [push]
+
+jobs:
+  plan:
+    if: contains(github.event.head_commit.message, '/bench')
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.build.outputs.matrix }}
+      config_file: ${{ steps.build.outputs.config_file }}
+      timeout_seconds: ${{ steps.build.outputs.timeout_seconds }}
+      environment: ${{ steps.build.outputs.environment }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Build matrix from config file
+        id: build
+        shell: bash
+        run: |
+          set -euo pipefail
+          CONFIG_FILE='.github/configs/bench_simple.yaml'
+          export CONFIG_FILE
+          echo "Config file: $CONFIG_FILE"
+          python3 .github/scripts/build_matrix.py
+
+  bench_worker:
+    needs: plan
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(needs.plan.outputs.matrix) }}
+    name: "bench on ${{ matrix.label }} [${{ matrix.index }}]"
+    runs-on: [self-hosted, macOS, "${{ matrix.label }}"]
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          lfs: false
+
+      - name: Configure git user
+        run: |
+          git config --local user.email "github-actions@users.noreply.github.com"
+          git config --local user.name  "github-actions bot"
+        shell: bash
+
+      # TODO: this is mega hacky and I'd like a simpler solution.
+      - name: Setup Nix Environment
+        run: |
+          echo "Checking for nix installation..."
+          
+          # Check if nix is already available
+          if command -v nix >/dev/null 2>&1; then
+            echo "Nix already in PATH"
+          # Try sourcing profile scripts to set up environment properly
+          elif [ -f /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh ]; then
+            echo "Sourcing multi-user nix-daemon profile script"
+            source /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
+          elif [ -f "$HOME/.nix-profile/etc/profile.d/nix.sh" ]; then
+            echo "Sourcing single-user nix profile script"
+            source "$HOME/.nix-profile/etc/profile.d/nix.sh"
+          elif [ -f /nix/var/nix/profiles/per-user/$USER/profile/etc/profile.d/nix.sh ]; then
+            echo "Sourcing per-user nix profile script"
+            source /nix/var/nix/profiles/per-user/$USER/profile/etc/profile.d/nix.sh
+          elif [ -f /etc/profile.d/nix.sh ]; then
+            echo "Sourcing system-wide nix profile script"
+            source /etc/profile.d/nix.sh
+          # Fallback: manually add nix to PATH if binary exists
+          elif [ -f /nix/var/nix/profiles/default/bin/nix ]; then
+            echo "Found nix binary, manually adding to PATH"
+            export PATH="/nix/var/nix/profiles/default/bin:$PATH"
+          elif [ -f "$HOME/.nix-profile/bin/nix" ]; then
+            echo "Found nix binary in user profile, manually adding to PATH"
+            export PATH="$HOME/.nix-profile/bin:$PATH"
+          else
+            echo "Nix not found. Debugging info:"
+            echo "USER: $USER"
+            echo "HOME: $HOME"
+            echo "Current PATH: $PATH"
+            echo ""
+            echo "Checking common Nix locations:"
+            echo "  /nix/var/nix/profiles/default/bin/nix:"
+            ls -la /nix/var/nix/profiles/default/bin/nix 2>/dev/null || echo "    Not found"
+            echo "  /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh:"
+            ls -la /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh 2>/dev/null || echo "    Not found"
+            echo "  ~/.nix-profile/etc/profile.d/nix.sh:"
+            ls -la "$HOME/.nix-profile/etc/profile.d/nix.sh" 2>/dev/null || echo "    Not found"
+            echo "  /nix/var/nix/profiles/per-user/$USER/profile/etc/profile.d/nix.sh:"
+            ls -la "/nix/var/nix/profiles/per-user/$USER/profile/etc/profile.d/nix.sh" 2>/dev/null || echo "    Not found"
+            echo ""
+            echo "/nix directory structure:"
+            ls -la /nix 2>/dev/null || echo "    /nix directory not found"
+            echo ""
+            echo "/nix/var:"
+            ls -la /nix/var 2>/dev/null || echo "    /nix/var not found"
+            echo ""
+            echo "/nix/store:"
+            ls -la /nix/store 2>/dev/null | head -20 || echo "    /nix/store not found"
+            echo ""
+            echo "GitHub Actions runner is running as user '$USER'."
+            echo "If Nix is installed for a different user, either:"
+            echo "  1. Install Nix for user '$USER' (multi-user install recommended)"
+            echo "  2. Configure the runner service to run as the user with Nix installed"
+            echo "  3. Ensure Nix is installed system-wide with proper daemon setup"
+            exit 1
+          fi
+          
+          # Verify nix is available and persist to GITHUB_ENV
+          if command -v nix >/dev/null 2>&1; then
+            echo "✓ Nix is available"
+            nix --version
+            echo "PATH=$PATH" >> $GITHUB_ENV
+            if [ -n "$NIX_PATH" ]; then
+              echo "NIX_PATH=$NIX_PATH" >> $GITHUB_ENV
+            fi
+          else
+            echo "ERROR: Failed to set up Nix"
+            echo "PATH after setup attempt: $PATH"
+            exit 1
+          fi
+        shell: bash
+
+      - name: Setup EXO_HOME and API_PORT
+        run: |
+          EXO_HOME=$(mktemp -d -t exo-e2e-XXXXXXXX)
+          API_PORT=$((49152 + RANDOM % (65535 - 49152 + 1)))
+          EXO_MODELS_DIR="$HOME/.exo/models"
+          EXO_LIBP2P_NAMESPACE="bench-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}"
+          echo "EXO_HOME=$EXO_HOME" >> "$GITHUB_ENV"
+          echo "API_PORT=$API_PORT" >> "$GITHUB_ENV"
+          echo "EXO_MODELS_DIR=$EXO_MODELS_DIR" >> "$GITHUB_ENV"
+          echo "EXO_LIBP2P_NAMESPACE=$EXO_LIBP2P_NAMESPACE" >> "$GITHUB_ENV"
+          echo "Created EXO_HOME: $EXO_HOME"
+          echo "Generated API_PORT: $API_PORT"
+          echo "Using models from: $EXO_MODELS_DIR"
+          echo "Using libp2p namespace: $EXO_LIBP2P_NAMESPACE"
+        shell: bash
+
+      - name: Configure local MLX if available
+        run: |
+          echo "=== DEBUG: Checking for local MLX configuration ==="
+          MODIFIED=false
+          
+          echo "Checking for /Users/Shared/mlx directory..."
+          if [ -d "/Users/Shared/mlx" ]; then
+            echo "✓ Found /Users/Shared/mlx"
+            ls -la /Users/Shared/mlx | head -5
+            echo "Enabling local mlx path in pyproject.toml"
+            sed -i.bak 's|^# mlx = { path = "/Users/Shared/mlx", editable=true }$|mlx = { path = "/Users/Shared/mlx", editable=true }|' pyproject.toml
+            MODIFIED=true
+          else
+            echo "✗ /Users/Shared/mlx not found, will use PyPI version"
+          fi
+          
+          echo "Checking for /Users/Shared/mlx-lm directory..."
+          if [ -d "/Users/Shared/mlx-lm" ]; then
+            echo "✓ Found /Users/Shared/mlx-lm"
+            ls -la /Users/Shared/mlx-lm | head -5
+            echo "Enabling local mlx-lm path in pyproject.toml"
+            sed -i.bak 's|^# mlx-lm = { path = "/Users/Shared/mlx-lm", editable=true }$|mlx-lm = { path = "/Users/Shared/mlx-lm", editable=true }|' pyproject.toml
+            MODIFIED=true
+          else
+            echo "✗ /Users/Shared/mlx-lm not found, will use PyPI version"
+          fi
+          
+          if [ "$MODIFIED" = true ]; then
+            echo "=== Modified pyproject.toml [tool.uv.sources] section: ==="
+            sed -n '/\[tool\.uv\.sources\]/,/^\[/{/^\[tool\.uv\.sources\]/p; /^\[/!p;}' pyproject.toml
+            echo "=== Regenerating uv.lock with local MLX paths... ==="
+            nix --extra-experimental-features nix-command --extra-experimental-features flakes develop --command uv lock --upgrade-package mlx --upgrade-package mlx-lm
+            echo "✓ Lock file regenerated"
+          else
+            echo "⚠ No local MLX directories found, using PyPI packages"
+          fi
+          echo "=== DEBUG: Local MLX configuration complete ==="
+        shell: bash
+
+      - name: Sync dependencies
+        run: |
+          if [ -d "/Users/Shared/test" ]; then
+            pushd /Users/Shared/test
+            uv sync --reinstall
+            popd
+          fi
+          echo "Running just sync to ensure clean dependencies..."
+          nix --extra-experimental-features nix-command --extra-experimental-features flakes develop --command just sync
+        shell: bash
+
+      - name: Start EXO and run bench script
+        shell: bash
+        env:
+          IS_PRIMARY: ${{ matrix.is_primary }}
+          EXPECTED_NODES: ${{ matrix.expected_nodes }}
+          HARDWARE_LABEL: ${{ matrix.label }}
+          CONFIG_FILE: ${{ needs.plan.outputs.config_file }}
+          TIMEOUT_SECONDS: ${{ needs.plan.outputs.timeout_seconds }}
+          ENVIRONMENT_JSON: ${{ needs.plan.outputs.environment }}
+        run: |
+          set -euo pipefail
+
+          # Parse environment variables from config
+          ENV_VARS=""
+          if [ -n "$ENVIRONMENT_JSON" ] && [ "$ENVIRONMENT_JSON" != "{}" ]; then
+            ENV_VARS=$(echo "$ENVIRONMENT_JSON" | python3 -c "import sys, json; env = json.load(sys.stdin); print(' '.join([f'{k}={v}' for k, v in env.items()]))")
+          fi
+
+          echo "Starting EXO with API_PORT=${API_PORT} EXO_HOME=${EXO_HOME} EXO_LIBP2P_NAMESPACE=${EXO_LIBP2P_NAMESPACE}"
+          echo "Environment variables from config: $ENV_VARS"
+          LOG_FILE=/tmp/exo.log
+          : > "$LOG_FILE"
+
+          MASTER_FLAG=""
+          if [ "$IS_PRIMARY" = "true" ]; then
+            MASTER_FLAG="-m"
+          fi
+
+          nix --extra-experimental-features nix-command --extra-experimental-features flakes develop --command bash -c \
+            "EXO_HOME=$EXO_HOME EXO_MODELS_DIR=$EXO_MODELS_DIR EXO_LIBP2P_NAMESPACE=$EXO_LIBP2P_NAMESPACE $ENV_VARS PYTHONUNBUFFERED=1 PYTHONDEBUG=1 PYTHONPATH=. uv run exo $MASTER_FLAG --api-port $API_PORT" \
+            >> "$LOG_FILE" 2>&1 &
+
+          EXO_PID=$!
+          echo "Started EXO in background with PID: $EXO_PID"
+          echo "Log file: $LOG_FILE"
+
+          cleanup() {
+            echo '=== EXO log (tail) ==='
+            tail -n 300 "$LOG_FILE" || true
+            if ps -p "$EXO_PID" >/dev/null 2>&1; then
+              echo "Killing EXO (PID $EXO_PID)"
+              kill "$EXO_PID" || true
+            fi
+          }
+          trap cleanup EXIT
+
+          for i in $(seq 1 60); do
+            if curl -s "http://localhost:${API_PORT}/state" >/dev/null 2>&1; then
+              echo "EXO API ready"
+              break
+            fi
+            if ! ps -p "$EXO_PID" >/dev/null 2>&1; then
+              echo "EXO terminated early"; sed -n '1,200p' "$LOG_FILE" || true; exit 1
+            fi
+            sleep 1
+          done
+
+          RESULTS_FILE="/tmp/bench_results_${GITHUB_RUN_ID}_${GITHUB_RUN_ATTEMPT}_$(date +%s).json"
+          echo "Results will be saved to: $RESULTS_FILE"
+          echo "RESULTS_FILE=$RESULTS_FILE" >> "$GITHUB_ENV"
+
+          echo "Running bench script with config: $CONFIG_FILE, timeout: $TIMEOUT_SECONDS"
+          nix --extra-experimental-features nix-command --extra-experimental-features flakes develop --command bash -c \
+            "PYTHONUNBUFFERED=1 uv run --no-project --with pyyaml --with pydantic python .github/scripts/bench.py \
+              --api-port $API_PORT \
+              --config $CONFIG_FILE \
+              --expected-nodes ${EXPECTED_NODES} \
+              --is-primary ${IS_PRIMARY} \
+              --timeout-seconds ${TIMEOUT_SECONDS} \
+              --output $RESULTS_FILE \
+              --git-commit ${GITHUB_SHA} \
+              --hardware-labels ${HARDWARE_LABEL}"
+
+      - name: Install AWS CLI
+        if: always() && env.RESULTS_FILE && matrix.is_primary
+        run: |
+          if ! command -v aws &> /dev/null; then
+            echo "AWS CLI not found, installing..."
+            brew install awscli
+          else
+            echo "AWS CLI already installed"
+          fi
+        shell: bash
+
+      - name: Upload results to S3
+        if: always() && env.RESULTS_FILE && matrix.is_primary
+        env:
+          AWS_ACCESS_KEY_ID: ${{ secrets.S3_BENCHMARKS_AWS_ACCESS_KEY_ID }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.S3_BENCHMARKS_AWS_SECRET_ACCESS_KEY }}
+          AWS_DEFAULT_REGION: us-east-1
+        run: |
+          echo "Checking for results file: $RESULTS_FILE"
+          echo "Is primary: ${{ matrix.is_primary }}"
+
+          if [ -f "$RESULTS_FILE" ]; then
+            TIMESTAMP=$(date -u +%Y/%m/%d/%H%M%S)
+            S3_KEY="bench/${TIMESTAMP}_${GITHUB_SHA:0:8}_${GITHUB_RUN_ID}.json"
+            echo "Uploading results to s3://exo-benchmark-results/$S3_KEY"
+
+            aws s3 cp "$RESULTS_FILE" "s3://exo-benchmark-results/$S3_KEY" \
+              --content-type application/json \
+              --metadata "commit=${GITHUB_SHA},run_id=${GITHUB_RUN_ID},branch=${GITHUB_REF_NAME}"
+
+            echo "Results uploaded successfully"
+            echo "View at: https://exo-benchmark-results.s3.amazonaws.com/$S3_KEY"
+          else
+            echo "Results file not found at: $RESULTS_FILE"
+            echo "Skipping upload"
+          fi
+        shell: bash
+
+      - name: Cleanup EXO_HOME
+        run: |
+          echo "Cleaning up EXO_HOME: $EXO_HOME"
+          rm -rf "$EXO_HOME"
+        shell: bash
+        if: always()

.github/workflows/build-app.yml

@@ -0,0 +1,298 @@
+name: Build EXO macOS DMG
+
+on:
+  push:
+    tags:
+      - "v*"
+    branches:
+      - "test-app"
+
+jobs:
+  build-macos-app:
+    runs-on: "macos-26"
+    env:
+      SPARKLE_VERSION: 2.8.1
+      SPARKLE_DOWNLOAD_PREFIX: ${{ secrets.SPARKLE_DOWNLOAD_PREFIX }}
+      SPARKLE_FEED_URL: ${{ secrets.SPARKLE_FEED_URL }}
+      SPARKLE_ED25519_PUBLIC: ${{ secrets.SPARKLE_ED25519_PUBLIC }}
+      SPARKLE_ED25519_PRIVATE: ${{ secrets.SPARKLE_ED25519_PRIVATE }}
+      SPARKLE_S3_BUCKET: ${{ secrets.SPARKLE_S3_BUCKET }}
+      SPARKLE_S3_PREFIX: ${{ secrets.SPARKLE_S3_PREFIX }}
+      AWS_REGION: ${{ secrets.AWS_REGION }}
+      EXO_BUILD_NUMBER: ${{ github.run_number }}
+      EXO_LIBP2P_NAMESPACE: ${{ github.ref_name }}
+
+    steps:
+      # ============================================================
+      # Checkout and tag validation
+      # ============================================================
+
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Derive release version from tag
+        run: |
+          if [[ "$GITHUB_REF_NAME" == "test-app" ]]; then
+            VERSION="0.0.0-alpha.0"
+            echo "IS_ALPHA=true" >> $GITHUB_ENV
+          else
+            VERSION="${GITHUB_REF_NAME#v}"
+            if [[ "$VERSION" == *-alpha* ]]; then
+              echo "IS_ALPHA=true" >> $GITHUB_ENV
+            else
+              echo "IS_ALPHA=false" >> $GITHUB_ENV
+            fi
+          fi
+          echo "RELEASE_VERSION=$VERSION" >> $GITHUB_ENV
+
+      - name: Ensure tag commit is on main
+        if: github.ref_type == 'tag'
+        run: |
+          git fetch origin main
+          # Alpha tags can be on any branch, production tags must be on main
+          if [[ "$IS_ALPHA" == "true" ]]; then
+            echo "Alpha tag detected, skipping main branch check"
+          elif ! git merge-base --is-ancestor origin/main HEAD; then
+            echo "Production tag must point to a commit on main"
+            exit 1
+          fi
+
+      # ============================================================
+      # Install dependencies
+      # ============================================================
+
+      - name: Select Xcode 26.2
+        run: |
+          sudo xcode-select -s /Applications/Xcode_26.2.app
+          if ! xcrun -f metal >/dev/null 2>&1; then
+            echo "Metal toolchain is not installed."
+            exit 1
+          fi
+
+      - name: Install Homebrew packages
+        run: brew install just awscli macmon
+
+      - name: Install UV
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+          cache-dependency-glob: uv.lock
+
+      - name: Setup Python
+        run: |
+          uv python install
+          uv sync --locked
+
+      - name: Build dashboard
+        run: |
+          cd dashboard
+          npm ci
+          npm run build
+
+      - name: Install Sparkle CLI
+        run: |
+          CLI_URL="${SPARKLE_CLI_URL:-https://github.com/sparkle-project/Sparkle/releases/download/${SPARKLE_VERSION}/Sparkle-${SPARKLE_VERSION}.tar.xz}"
+          echo "Downloading Sparkle CLI from: $CLI_URL"
+          mkdir -p /tmp/sparkle
+          curl --fail --location --output /tmp/sparkle.tar.xz "$CLI_URL"
+          tar -xJf /tmp/sparkle.tar.xz -C /tmp/sparkle --strip-components=1
+          echo "SPARKLE_BIN=/tmp/sparkle/bin" >> $GITHUB_ENV
+
+      - name: Prepare code-signing keychain
+        env:
+          MACOS_CERTIFICATE: ${{ secrets.MACOS_CERTIFICATE }}
+          MACOS_CERTIFICATE_PASSWORD: ${{ secrets.MACOS_CERTIFICATE_PASSWORD }}
+          PROVISIONING_PROFILE: ${{ secrets.PROVISIONING_PROFILE }}
+        run: |
+          KEYCHAIN_PATH="$HOME/Library/Keychains/build.keychain-db"
+
+          # Create fresh keychain
+          security create-keychain -p "$MACOS_CERTIFICATE_PASSWORD" "$KEYCHAIN_PATH"
+
+          # Disable auto-lock (no timeout, no lock-on-sleep)
+          security set-keychain-settings "$KEYCHAIN_PATH"
+
+          # Add to search list while preserving existing keychains
+          security list-keychains -d user -s "$KEYCHAIN_PATH" $(security list-keychains -d user | tr -d '"')
+
+          # Set as default and unlock
+          security default-keychain -s "$KEYCHAIN_PATH"
+          security unlock-keychain -p "$MACOS_CERTIFICATE_PASSWORD" "$KEYCHAIN_PATH"
+
+          # Import certificate with full access for codesign
+          echo "$MACOS_CERTIFICATE" | base64 --decode > /tmp/cert.p12
+          security import /tmp/cert.p12 -k "$KEYCHAIN_PATH" -P "$MACOS_CERTIFICATE_PASSWORD" \
+            -T /usr/bin/codesign -T /usr/bin/security -T /usr/bin/productbuild
+          rm /tmp/cert.p12
+
+          # Allow codesign to access the key without prompting
+          security set-key-partition-list -S apple-tool:,apple:,codesign: -s -k "$MACOS_CERTIFICATE_PASSWORD" "$KEYCHAIN_PATH"
+
+          # Verify keychain is unlocked and identity is available
+          echo "Verifying signing identity..."
+          security find-identity -v -p codesigning "$KEYCHAIN_PATH"
+
+          # Setup provisioning profile
+          mkdir -p "$HOME/Library/Developer/Xcode/UserData/Provisioning Profiles"
+          echo "$PROVISIONING_PROFILE" | base64 --decode > "$HOME/Library/Developer/Xcode/UserData/Provisioning Profiles/EXO.provisionprofile"
+
+          # Export keychain path for other steps
+          echo "BUILD_KEYCHAIN_PATH=$KEYCHAIN_PATH" >> $GITHUB_ENV
+
+      # ============================================================
+      # Build the bundle
+      # ============================================================
+
+      - name: Build PyInstaller bundle
+        run: uv run pyinstaller packaging/pyinstaller/exo.spec
+
+      - name: Build Swift app
+        env:
+          MACOS_CERTIFICATE_PASSWORD: ${{ secrets.MACOS_CERTIFICATE_PASSWORD }}
+          SPARKLE_FEED_URL: ${{ secrets.SPARKLE_FEED_URL }}
+          SPARKLE_ED25519_PUBLIC: ${{ secrets.SPARKLE_ED25519_PUBLIC }}
+        run: |
+          cd app/EXO
+          security unlock-keychain -p "$MACOS_CERTIFICATE_PASSWORD" "$BUILD_KEYCHAIN_PATH"
+          SIGNING_IDENTITY=$(security find-identity -v -p codesigning "$BUILD_KEYCHAIN_PATH" | awk -F '"' '{print $2}')
+          xcodebuild clean build \
+            -scheme EXO \
+            -configuration Release \
+            -derivedDataPath build \
+            MARKETING_VERSION="$RELEASE_VERSION" \
+            CURRENT_PROJECT_VERSION="$EXO_BUILD_NUMBER" \
+            EXO_BUILD_TAG="$RELEASE_VERSION" \
+            EXO_BUILD_COMMIT="$GITHUB_SHA" \
+            SPARKLE_FEED_URL="$SPARKLE_FEED_URL" \
+            SPARKLE_ED25519_PUBLIC="$SPARKLE_ED25519_PUBLIC" \
+            CODE_SIGNING_IDENTITY="$SIGNING_IDENTITY" \
+            CODE_SIGN_INJECT_BASE_ENTITLEMENTS=YES
+          mkdir -p ../../output
+          cp -R build/Build/Products/Release/EXO.app ../../output/EXO.app
+
+      - name: Inject PyInstaller runtime
+        run: |
+          rm -rf output/EXO.app/Contents/Resources/exo
+          mkdir -p output/EXO.app/Contents/Resources
+          cp -R dist/exo output/EXO.app/Contents/Resources/exo
+
+      - name: Codesign PyInstaller runtime
+        env:
+          MACOS_CERTIFICATE_PASSWORD: ${{ secrets.MACOS_CERTIFICATE_PASSWORD }}
+        run: |
+          cd output
+          security unlock-keychain -p "$MACOS_CERTIFICATE_PASSWORD" "$BUILD_KEYCHAIN_PATH"
+          SIGNING_IDENTITY=$(security find-identity -v -p codesigning "$BUILD_KEYCHAIN_PATH" | awk -F '"' '{print $2}')
+          RUNTIME_DIR="EXO.app/Contents/Resources/exo"
+          find "$RUNTIME_DIR" -type f \( -perm -111 -o -name "*.dylib" -o -name "*.so" \) -print0 |
+            while IFS= read -r -d '' file; do
+              /usr/bin/codesign --force --timestamp --options runtime \
+                --sign "$SIGNING_IDENTITY" "$file"
+            done
+
+      - name: Sign, notarize, and create DMG
+        env:
+          MACOS_CERTIFICATE_PASSWORD: ${{ secrets.MACOS_CERTIFICATE_PASSWORD }}
+          APPLE_NOTARIZATION_USERNAME: ${{ secrets.APPLE_NOTARIZATION_USERNAME }}
+          APPLE_NOTARIZATION_PASSWORD: ${{ secrets.APPLE_NOTARIZATION_PASSWORD }}
+          APPLE_NOTARIZATION_TEAM: ${{ secrets.APPLE_NOTARIZATION_TEAM }}
+        run: |
+          cd output
+          security unlock-keychain -p "$MACOS_CERTIFICATE_PASSWORD" "$BUILD_KEYCHAIN_PATH"
+          SIGNING_IDENTITY=$(security find-identity -v -p codesigning "$BUILD_KEYCHAIN_PATH" | awk -F '"' '{print $2}')
+          /usr/bin/codesign --deep --force --timestamp --options runtime \
+            --sign "$SIGNING_IDENTITY" EXO.app
+          mkdir -p dmg-root
+          cp -R EXO.app dmg-root/
+          ln -s /Applications dmg-root/Applications
+          DMG_NAME="EXO-${RELEASE_VERSION}.dmg"
+          hdiutil create -volname "EXO" -srcfolder dmg-root -ov -format UDZO "$DMG_NAME"
+          /usr/bin/codesign --force --timestamp --options runtime \
+            --sign "$SIGNING_IDENTITY" "$DMG_NAME"
+          if [[ -n "$APPLE_NOTARIZATION_USERNAME" ]]; then
+            SUBMISSION_OUTPUT=$(xcrun notarytool submit "$DMG_NAME" \
+              --apple-id "$APPLE_NOTARIZATION_USERNAME" \
+              --password "$APPLE_NOTARIZATION_PASSWORD" \
+              --team-id "$APPLE_NOTARIZATION_TEAM" \
+              --wait --timeout 15m 2>&1)
+            echo "$SUBMISSION_OUTPUT"
+
+            SUBMISSION_ID=$(echo "$SUBMISSION_OUTPUT" | awk 'tolower($1)=="id:" && $2 ~ /^[0-9a-fA-F-]+$/ {print $2; exit}')
+            STATUS=$(echo "$SUBMISSION_OUTPUT" | awk 'tolower($1)=="status:" {print $2; exit}')
+
+            if [[ -n "$SUBMISSION_ID" ]]; then
+              xcrun notarytool log "$SUBMISSION_ID" \
+                --apple-id "$APPLE_NOTARIZATION_USERNAME" \
+                --password "$APPLE_NOTARIZATION_PASSWORD" \
+                --team-id "$APPLE_NOTARIZATION_TEAM" > notarization-log.txt || true
+              echo "===== Notarization Log ====="
+              cat notarization-log.txt
+              echo "============================"
+            fi
+
+            if [[ "$STATUS" != "Accepted" ]]; then
+              echo "Notarization failed with status: ${STATUS:-Unknown}"
+              exit 1
+            fi
+
+            xcrun stapler staple "$DMG_NAME"
+          fi
+
+      - name: Generate Sparkle appcast
+        env:
+          SPARKLE_DOWNLOAD_PREFIX: ${{ env.SPARKLE_DOWNLOAD_PREFIX }}
+          SPARKLE_ED25519_PRIVATE: ${{ secrets.SPARKLE_ED25519_PRIVATE }}
+          IS_ALPHA: ${{ env.IS_ALPHA }}
+        run: |
+          set -euo pipefail
+          cd output
+          DOWNLOAD_PREFIX="${SPARKLE_DOWNLOAD_PREFIX:-https://assets.exolabs.net}"
+          echo "$SPARKLE_ED25519_PRIVATE" > sparkle_ed25519.key
+          chmod 600 sparkle_ed25519.key
+
+          CHANNEL_FLAG=""
+          if [[ "$IS_ALPHA" == "true" ]]; then
+            CHANNEL_FLAG="--channel alpha"
+            echo "Generating appcast for alpha channel"
+          fi
+
+          $SPARKLE_BIN/generate_appcast \
+            --ed-key-file sparkle_ed25519.key \
+            --download-url-prefix "$DOWNLOAD_PREFIX" \
+            $CHANNEL_FLAG \
+            .
+
+      # ============================================================
+      # Upload artifacts
+      # ============================================================
+
+      - name: Upload DMG
+        uses: actions/upload-artifact@v4
+        with:
+          name: EXO-dmg-${{ env.RELEASE_VERSION }}
+          path: output/EXO-${{ env.RELEASE_VERSION }}.dmg
+
+      - name: Upload to S3
+        if: env.SPARKLE_S3_BUCKET != '' && github.ref_type == 'tag'
+        env:
+          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          AWS_REGION: ${{ env.AWS_REGION }}
+          SPARKLE_S3_BUCKET: ${{ env.SPARKLE_S3_BUCKET }}
+          SPARKLE_S3_PREFIX: ${{ env.SPARKLE_S3_PREFIX }}
+          IS_ALPHA: ${{ env.IS_ALPHA }}
+        run: |
+          set -euo pipefail
+          cd output
+          PREFIX="${SPARKLE_S3_PREFIX:-}"
+          if [[ -n "$PREFIX" && "${PREFIX: -1}" != "/" ]]; then
+            PREFIX="${PREFIX}/"
+          fi
+          DMG_NAME="EXO-${RELEASE_VERSION}.dmg"
+          aws s3 cp "$DMG_NAME" "s3://${SPARKLE_S3_BUCKET}/${PREFIX}${DMG_NAME}"
+          if [[ "$IS_ALPHA" != "true" ]]; then
+            aws s3 cp "$DMG_NAME" "s3://${SPARKLE_S3_BUCKET}/${PREFIX}EXO-latest.dmg"
+          fi
+          aws s3 cp appcast.xml "s3://${SPARKLE_S3_BUCKET}/${PREFIX}appcast.xml" --content-type application/xml --cache-control no-cache

.github/workflows/pipeline.yml

@@ -0,0 +1,183 @@
+name: ci-pipeline
+
+on:
+  push:
+  pull_request:
+    branches:
+      - staging
+      - main
+
+jobs:
+  typecheck:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          lfs: false
+
+      - uses: cachix/install-nix-action@v31
+        with:
+          nix_path: nixpkgs=channel:nixos-unstable
+
+      - name: Configure git user
+        run: |
+          git config --local user.email "github-actions@users.noreply.github.com"
+          git config --local user.name  "github-actions bot"
+        shell: bash
+
+      - name: Pull LFS files
+        run: |
+          echo "Pulling Git LFS files..."
+          git lfs pull
+        shell: bash
+
+      - name: Setup Nix Environment
+        run: |
+          echo "Checking for nix installation..."
+          
+          # Check if nix binary exists directly
+          if [ -f /nix/var/nix/profiles/default/bin/nix ]; then
+            echo "Found nix binary at /nix/var/nix/profiles/default/bin/nix"
+            export PATH="/nix/var/nix/profiles/default/bin:$PATH"
+            echo "PATH=$PATH" >> $GITHUB_ENV
+            nix --version
+          elif [ -f /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh ]; then
+            echo "Found nix profile script, sourcing..."
+            source /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
+            nix --version
+          elif command -v nix >/dev/null 2>&1; then
+            echo "Nix already in PATH"
+            nix --version
+          else
+            echo "Nix not found. Debugging info:"
+            echo "Contents of /nix/var/nix/profiles/default/:"
+            ls -la /nix/var/nix/profiles/default/ 2>/dev/null || echo "Directory not found"
+            echo "Contents of /nix/var/nix/profiles/default/bin/:"
+            ls -la /nix/var/nix/profiles/default/bin/ 2>/dev/null || echo "Directory not found"
+            exit 1
+          fi
+        shell: bash
+
+      - name: Configure basedpyright include for local MLX
+        run: |
+          RUNNER_LABELS='${{ toJSON(runner.labels) }}'
+          if echo "$RUNNER_LABELS" | grep -q "local_mlx"; then
+            if [ -d "/Users/Shared/mlx" ]; then
+              echo "Updating [tool.basedpyright].include to use /Users/Shared/mlx"
+              awk '
+                BEGIN { in=0 }
+                /^\[tool\.basedpyright\]/ { in=1; print; next }
+                in && /^\[/ { in=0 }  # next section
+                in && /^[ \t]*include[ \t]*=/ {
+                  print "include = [\"/Users/Shared/mlx\"]"
+                  next
+                }
+                { print }
+              ' pyproject.toml > pyproject.toml.tmp && mv pyproject.toml.tmp pyproject.toml
+
+              echo "New [tool.basedpyright] section:"
+              sed -n '/^\[tool\.basedpyright\]/,/^\[/p' pyproject.toml | sed '$d' || true
+            else
+              echo "local_mlx tag present but /Users/Shared/mlx not found; leaving pyproject unchanged."
+            fi
+          else
+            echo "Runner does not have 'local_mlx' tag; leaving pyproject unchanged."
+          fi
+        shell: bash
+
+      - uses: ./.github/actions/typecheck
+
+  nix-flake-check:
+    name: Check Nix flake
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          lfs: false
+
+      - uses: cachix/install-nix-action@v31
+        with:
+          nix_path: nixpkgs=channel:nixos-unstable
+
+      - name: Run nix flake check
+        run: |
+          nix flake check
+        shell: bash
+
+#  ci:
+#    needs: typecheck
+#    runs-on: ubuntu-latest
+#    permissions:
+#      contents: read
+#    env:
+#      GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+#    steps:
+#      - name: Checkout repository
+#        uses: actions/checkout@v4
+#        with:
+#          fetch-depth: 0
+#          token: ${{ secrets.GITHUB_TOKEN }}
+#          lfs: true
+#
+#      - name: Configure git user
+#        run: |
+#          git config --local user.email "github-actions@users.noreply.github.com"
+#          git config --local user.name  "github-actions bot"
+#        shell: bash
+#
+#      - name: Pull LFS files
+#        run: |
+#          echo "Pulling Git LFS files..."
+#          git lfs pull
+#        shell: bash
+#
+#      - name: Setup EXO_HOME and API_PORT
+#        run: |
+#          EXO_HOME=$(mktemp -d -t exo-ci-XXXXXXXX)
+#          # Generate random port (macOS compatible method)
+#          API_PORT=$((49152 + RANDOM % (65535 - 49152 + 1)))
+#          echo "EXO_HOME=$EXO_HOME" >> $GITHUB_ENV
+#          echo "API_PORT=$API_PORT" >> $GITHUB_ENV
+#          echo "Created EXO_HOME: $EXO_HOME"
+#          echo "Generated API_PORT: $API_PORT"
+#        shell: bash
+#
+#      - name: Setup Nix Environment
+#        run: |
+#          echo "Checking for nix installation..."
+#          
+#          # Check if nix binary exists directly
+#          if [ -f /nix/var/nix/profiles/default/bin/nix ]; then
+#            echo "Found nix binary at /nix/var/nix/profiles/default/bin/nix"
+#            export PATH="/nix/var/nix/profiles/default/bin:$PATH"
+#            echo "PATH=$PATH" >> $GITHUB_ENV
+#            nix --version
+#          elif [ -f /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh ]; then
+#            echo "Found nix profile script, sourcing..."
+#            source /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
+#            nix --version
+#          elif command -v nix >/dev/null 2>&1; then
+#            echo "Nix already in PATH"
+#            nix --version
+#          else
+#            echo "Nix not found. Debugging info:"
+#            echo "Contents of /nix/var/nix/profiles/default/:"
+#            ls -la /nix/var/nix/profiles/default/ 2>/dev/null || echo "Directory not found"
+#            echo "Contents of /nix/var/nix/profiles/default/bin/:"
+#            ls -la /nix/var/nix/profiles/default/bin/ 2>/dev/null || echo "Directory not found"
+#            exit 1
+#          fi
+#        shell: bash
+#
+#      - uses: ./.github/actions/lint-check
+#
+#      - uses: ./.github/actions/unit-test
+#
+#      - name: Cleanup EXO_HOME
+#        run: |
+#          echo "Cleaning up EXO_HOME: $EXO_HOME"
+#          rm -rf "$EXO_HOME"
+#        shell: bash
+#        if: always()

.gitignore

@@ -1,175 +1,27 @@
-__pycache__/
-.venv*
-test_weights.npz
-.exo_used_ports
-.exo_node_id
-.idea
-.DS_Store
+# gitingest
+digest.txt
 
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
+# python
+**/__pycache__
 
-# C extensions
-*.so
+# nix
+.direnv/
 
-# Distribution / packaging
-/.Python
-/develop-eggs/
-/dist/
-/downloads/
-/eggs/
-/.eggs/
-/lib/
-/lib64/
-/parts/
-/sdist/
-/var/
-/wheels/
-/share/python-wheels/
-/*.egg-info/
-/.installed.cfg
-/*.egg
-/MANIFEST
 
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
+# xcode / macos
+*.xcuserstate
+*.xcuserdata
+*.xcuserdatad/
+**/.DS_Store
+app/EXO/build/
 
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
 
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
+# rust
 target/
+**/*.rs.bk
+*.pdb
 
-# Jupyter Notebook
-.ipynb_checkpoints
-Untitled.ipynb
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
-.pdm.toml
-.pdm-python
-.pdm-build/
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-
-**/*.xcodeproj/*
-.aider*
-
-exo/tinychat/images/*.png
+# svelte
+dashboard/build/
+dashboard/node_modules/
+dashboard/.svelte-kit/

.idea/.gitignore

@@ -0,0 +1,9 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml
+workspace.xml

.idea/LanguageServersSettings.xml

@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="LanguageServerSettingsState">
+    <state>
+      <map>
+        <entry key="com.insyncwithfoo.pyright">
+          <value>
+            <LanguageServerDefinitionSettings>
+              <option name="errorReportingKind" value="in_log" />
+            </LanguageServerDefinitionSettings>
+          </value>
+        </entry>
+      </map>
+    </state>
+  </component>
+</project>

.idea/exo-v2.iml

@@ -0,0 +1,31 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="EMPTY_MODULE" version="4">
+  <component name="FacetManager">
+    <facet type="Python" name="Python facet">
+      <configuration sdkName="Python 3.13 virtualenv at ~/Desktop/exo/.venv" />
+    </facet>
+  </component>
+  <component name="Go" enabled="true" />
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <sourceFolder url="file://$MODULE_DIR$/scripts/src" isTestSource="false" />
+      <sourceFolder url="file://$MODULE_DIR$/src" isTestSource="false" />
+      <sourceFolder url="file://$MODULE_DIR$/rust/exo_pyo3_bindings/src" isTestSource="false" />
+      <sourceFolder url="file://$MODULE_DIR$/rust/exo_pyo3_bindings/tests" isTestSource="true" />
+      <sourceFolder url="file://$MODULE_DIR$/rust/util/src" isTestSource="false" />
+      <sourceFolder url="file://$MODULE_DIR$/rust/networking/examples" isTestSource="false" />
+      <sourceFolder url="file://$MODULE_DIR$/rust/networking/src" isTestSource="false" />
+      <sourceFolder url="file://$MODULE_DIR$/rust/networking/tests" isTestSource="true" />
+      <sourceFolder url="file://$MODULE_DIR$/rust/system_custodian/src" isTestSource="false" />
+      <excludeFolder url="file://$MODULE_DIR$/.venv" />
+      <excludeFolder url="file://$MODULE_DIR$/.direnv" />
+      <excludeFolder url="file://$MODULE_DIR$/build" />
+      <excludeFolder url="file://$MODULE_DIR$/dist" />
+      <excludeFolder url="file://$MODULE_DIR$/.go_cache" />
+      <excludeFolder url="file://$MODULE_DIR$/rust/target" />
+    </content>
+    <orderEntry type="jdk" jdkName="Python 3.13 (exo)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+    <orderEntry type="library" name="Python 3.13 virtualenv at ~/Desktop/exo/.venv interpreter library" level="application" />
+  </component>
+</module>

.idea/externalDependencies.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ExternalDependencies">
+    <plugin id="systems.fehn.intellijdirenv" />
+  </component>
+</project>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,14 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyCompatibilityInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ourVersions">
+        <value>
+          <list size="1">
+            <item index="0" class="java.lang.String" itemvalue="3.14" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/misc.xml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.13 (exo)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.13 (exo)" project-jdk-type="Python SDK" />
+  <component name="PythonCompatibilityInspectionAdvertiser">
+    <option name="version" value="3" />
+  </component>
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/exo.iml" filepath="$PROJECT_DIR$/.idea/exo.iml" />
+    </modules>
+  </component>
+</project>

.idea/pyright-overrides.xml

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="com.insyncwithfoo.pyright.configurations.Override">
+    <option name="names">
+      <map>
+        <entry key="configurationFile" value="true" />
+        <entry key="diagnosticMode" value="true" />
+        <entry key="inlayHintsGenericTypes" value="true" />
+        <entry key="prefixTooltipMessages" value="true" />
+        <entry key="runningMode" value="true" />
+        <entry key="smartExecutableResolution" value="true" />
+        <entry key="smartLanguageServerExecutableResolution" value="true" />
+        <entry key="useEditorFontForTooltips" value="true" />
+        <entry key="useTypingExtensions" value="true" />
+      </map>
+    </option>
+  </component>
+</project>

.idea/pyright.xml

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="com.insyncwithfoo.pyright.configurations.Local">
+    <option name="diagnosticMode" value="WORKSPACE" />
+    <option name="inlayHintsGenericTypes" value="true" />
+    <option name="prefixTooltipMessages" value="true" />
+    <option name="useEditorFontForTooltips" value="true" />
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

.mlx_typings/mlx/core/cuda/__init__.pyi

@@ -0,0 +1,2 @@
+def is_available() -> bool:
+    """Check if the CUDA back-end is available."""

.mlx_typings/mlx/core/distributed/__init__.pyi

@@ -0,0 +1,216 @@
+from typing import Sequence
+
+from mlx.core import Device, Dtype, Stream, array
+
+class Group:
+    """
+    An :class:`mlx.core.distributed.Group` represents a group of independent mlx
+    processes that can communicate.
+    """
+    def rank(self) -> int:
+        """Get the rank of this process"""
+
+    def size(self) -> int:
+        """Get the size of the group"""
+
+    def split(self, color: int, key: int = ...) -> Group:
+        """
+        Split the group to subgroups based on the provided color.
+
+        Processes that use the same color go to the same group. The ``key``
+        argument defines the rank in the new group. The smaller the key the
+        smaller the rank. If the key is negative then the rank in the
+        current group is used.
+
+        Args:
+          color (int): A value to group processes into subgroups.
+          key (int, optional): A key to optionally change the rank ordering
+            of the processes.
+        """
+
+def all_gather(
+    x: array, *, group: Group | None = ..., stream: Stream | Device | None = ...
+) -> array:
+    """
+    Gather arrays from all processes.
+
+    Gather the ``x`` arrays from all processes in the group and concatenate
+    them along the first axis. The arrays should all have the same shape.
+
+    Args:
+      x (array): Input array.
+      group (Group): The group of processes that will participate in the
+        gather. If set to ``None`` the global group is used. Default:
+        ``None``.
+      stream (Stream, optional): Stream or device. Defaults to ``None``
+        in which case the default stream of the default device is used.
+
+    Returns:
+      array: The concatenation of all ``x`` arrays.
+    """
+
+def all_max(
+    x: array, *, group: Group | None = ..., stream: Stream | Device | None = ...
+) -> array:
+    """
+    All reduce max.
+
+    Find the maximum of the ``x`` arrays from all processes in the group.
+
+    Args:
+      x (array): Input array.
+      group (Group): The group of processes that will participate in the
+        reduction. If set to ``None`` the global group is used. Default:
+        ``None``.
+      stream (Stream, optional): Stream or device. Defaults to ``None``
+        in which case the default stream of the default device is used.
+
+    Returns:
+      array: The maximum of all ``x`` arrays.
+    """
+
+def all_min(
+    x: array, *, group: Group | None = ..., stream: Stream | Device | None = ...
+) -> array:
+    """
+    All reduce min.
+
+    Find the minimum of the ``x`` arrays from all processes in the group.
+
+    Args:
+      x (array): Input array.
+      group (Group): The group of processes that will participate in the
+        reduction. If set to ``None`` the global group is used. Default:
+        ``None``.
+      stream (Stream, optional): Stream or device. Defaults to ``None``
+        in which case the default stream of the default device is used.
+
+    Returns:
+      array: The minimum of all ``x`` arrays.
+    """
+
+def all_sum(
+    x: array, *, group: Group | None = ..., stream: Stream | Device | None = ...
+) -> array:
+    """
+    All reduce sum.
+
+    Sum the ``x`` arrays from all processes in the group.
+
+    Args:
+      x (array): Input array.
+      group (Group): The group of processes that will participate in the
+        reduction. If set to ``None`` the global group is used. Default:
+        ``None``.
+      stream (Stream, optional): Stream or device. Defaults to ``None``
+        in which case the default stream of the default device is used.
+
+    Returns:
+      array: The sum of all ``x`` arrays.
+    """
+
+def init(strict: bool = ..., backend: str = ...) -> Group:
+    """
+    Initialize the communication backend and create the global communication group.
+
+    Example:
+
+      .. code:: python
+
+        import mlx.core as mx
+
+        group = mx.distributed.init(backend="ring")
+
+    Args:
+      strict (bool, optional): If set to False it returns a singleton group
+        in case ``mx.distributed.is_available()`` returns False otherwise
+        it throws a runtime error. Default: ``False``
+      backend (str, optional): Which distributed backend to initialize.
+        Possible values ``mpi``, ``ring``, ``nccl``, ``any``. If set to ``any`` all
+        available backends are tried and the first one that succeeds
+        becomes the global group which will be returned in subsequent
+        calls. Default: ``any``
+
+    Returns:
+      Group: The group representing all the launched processes.
+    """
+
+def is_available() -> bool:
+    """Check if a communication backend is available."""
+
+def recv(
+    shape: Sequence[int],
+    dtype: Dtype,
+    src: int,
+    *,
+    group: Group | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    """
+    Recv an array with shape ``shape`` and dtype ``dtype`` from process
+    with rank ``src``.
+
+    Args:
+      shape (tuple[int]): The shape of the array we are receiving.
+      dtype (Dtype): The data type of the array we are receiving.
+      src (int): Rank of the source process in the group.
+      group (Group): The group of processes that will participate in the
+        recv. If set to ``None`` the global group is used. Default:
+        ``None``.
+      stream (Stream, optional): Stream or device. Defaults to ``None``
+        in which case the default stream of the default device is used.
+
+    Returns:
+      array: The array that was received from ``src``.
+    """
+
+def recv_like(
+    x: array,
+    src: int,
+    *,
+    group: Group | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    """
+    Recv an array with shape and type like ``x`` from process with rank
+    ``src``.
+
+    It is equivalent to calling ``mx.distributed.recv(x.shape, x.dtype, src)``.
+
+    Args:
+      x (array): An array defining the shape and dtype of the array we are
+        receiving.
+      src (int): Rank of the source process in the group.
+      group (Group): The group of processes that will participate in the
+        recv. If set to ``None`` the global group is used. Default:
+        ``None``.
+      stream (Stream, optional): Stream or device. Defaults to ``None``
+        in which case the default stream of the default device is used.
+
+    Returns:
+      array: The array that was received from ``src``.
+    """
+
+def send(
+    x: array,
+    dst: int,
+    *,
+    group: Group | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    """
+    Send an array from the current process to the process that has rank
+    ``dst`` in the group.
+
+    Args:
+      x (array): Input array.
+      dst (int): Rank of the destination process in the group.
+      group (Group): The group of processes that will participate in the
+        sned. If set to ``None`` the global group is used. Default:
+        ``None``.
+      stream (Stream, optional): Stream or device. Defaults to ``None``
+        in which case the default stream of the default device is used.
+
+    Returns:
+      array: An array identical to ``x`` which when evaluated the send is performed.
+    """

.mlx_typings/mlx/core/metal/__init__.pyi

@@ -0,0 +1,38 @@
+def clear_cache() -> None: ...
+def device_info() -> dict[str, str | int]:
+    """
+    Get information about the GPU device and system settings.
+
+    Currently returns:
+
+    * ``architecture``
+    * ``max_buffer_size``
+    * ``max_recommended_working_set_size``
+    * ``memory_size``
+    * ``resource_limit``
+
+    Returns:
+        dict: A dictionary with string keys and string or integer values.
+    """
+
+def get_active_memory() -> int: ...
+def get_cache_memory() -> int: ...
+def get_peak_memory() -> int: ...
+def is_available() -> bool:
+    """Check if the Metal back-end is available."""
+
+def reset_peak_memory() -> None: ...
+def set_cache_limit(limit: int) -> int: ...
+def set_memory_limit(limit: int) -> int: ...
+def set_wired_limit(limit: int) -> int: ...
+def start_capture(path: str) -> None:
+    """
+    Start a Metal capture.
+
+    Args:
+      path (str): The path to save the capture which should have
+        the extension ``.gputrace``.
+    """
+
+def stop_capture() -> None:
+    """Stop a Metal capture."""

.mlx_typings/mlx/core/random/__init__.pyi

@@ -0,0 +1,301 @@
+from typing import Sequence
+
+from mlx.core import Device, Dtype, Stream, array, scalar
+from mlx.core.distributed import state as state
+
+def bernoulli(
+    p: scalar | array = ...,
+    shape: Sequence[int] | None = ...,
+    key: array | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    """
+    Generate Bernoulli random values.
+
+    The values are sampled from the bernoulli distribution with parameter
+    ``p``. The parameter ``p`` can be a :obj:`float` or :obj:`array` and
+    must be broadcastable to ``shape``.
+
+    Args:
+        p (float or array, optional): Parameter of the Bernoulli
+          distribution. Default: ``0.5``.
+        shape (list(int), optional): Shape of the output.
+          Default: ``p.shape``.
+        key (array, optional): A PRNG key. Default: ``None``.
+
+    Returns:
+        array: The array of random integers.
+    """
+
+def categorical(
+    logits: array,
+    axis: int = ...,
+    shape: Sequence[int] | None = ...,
+    num_samples: int | None = ...,
+    key: array | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    """
+    Sample from a categorical distribution.
+
+    The values are sampled from the categorical distribution specified by
+    the unnormalized values in ``logits``. Note, at most one of ``shape``
+    or ``num_samples`` can be specified. If both are ``None``, the output
+    has the same shape as ``logits`` with the ``axis`` dimension removed.
+
+    Args:
+        logits (array): The *unnormalized* categorical distribution(s).
+        axis (int, optional): The axis which specifies the distribution.
+           Default: ``-1``.
+        shape (list(int), optional): The shape of the output. This must
+           be broadcast compatible with ``logits.shape`` with the ``axis``
+           dimension removed. Default: ``None``
+        num_samples (int, optional): The number of samples to draw from each
+          of the categorical distributions in ``logits``. The output will have
+          ``num_samples`` in the last dimension. Default: ``None``.
+        key (array, optional): A PRNG key. Default: ``None``.
+
+    Returns:
+        array: The ``shape``-sized output array with type ``uint32``.
+    """
+
+def gumbel(
+    shape: Sequence[int] = ...,
+    dtype: Dtype | None = ...,
+    key: Stream | Device | None = ...,
+    stream: array | None = ...,
+) -> array:
+    """
+    Sample from the standard Gumbel distribution.
+
+    The values are sampled from a standard Gumbel distribution
+    which CDF ``exp(-exp(-x))``.
+
+    Args:
+        shape (list(int)): The shape of the output.
+        dtype (Dtype, optional): The data type of the output.
+          Default: ``float32``.
+        key (array, optional): A PRNG key. Default: ``None``.
+
+    Returns:
+        array:
+          The :class:`array` with shape ``shape`` and distributed according
+          to the Gumbel distribution.
+    """
+
+def key(seed: int) -> array:
+    """
+    Get a PRNG key from a seed.
+
+    Args:
+        seed (int): Seed for the PRNG.
+
+    Returns:
+        array: The PRNG key array.
+    """
+
+def laplace(
+    shape: Sequence[int] = ...,
+    dtype: Dtype | None = ...,
+    loc: float = ...,
+    scale: float = ...,
+    key: array | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    """
+    Sample numbers from a Laplace distribution.
+
+    Args:
+        shape (list(int), optional): Shape of the output. Default: ``()``.
+        dtype (Dtype, optional): Type of the output. Default: ``float32``.
+        loc (float, optional): Mean of the distribution. Default: ``0.0``.
+        scale (float, optional): The scale "b" of the Laplace distribution.
+          Default:``1.0``.
+        key (array, optional): A PRNG key. Default: ``None``.
+
+    Returns:
+        array: The output array of random values.
+    """
+
+def multivariate_normal(
+    mean: array,
+    cov: array,
+    shape: Sequence[int] = ...,
+    dtype: Dtype | None = ...,
+    key: array | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    """
+    Generate jointly-normal random samples given a mean and covariance.
+
+    The matrix ``cov`` must be positive semi-definite. The behavior is
+    undefined if it is not.  The only supported ``dtype`` is ``float32``.
+
+    Args:
+        mean (array): array of shape ``(..., n)``, the mean of the
+          distribution.
+        cov (array): array  of shape ``(..., n, n)``, the covariance
+          matrix of the distribution. The batch shape ``...`` must be
+          broadcast-compatible with that of ``mean``.
+        shape (list(int), optional): The output shape must be
+          broadcast-compatible with ``mean.shape[:-1]`` and ``cov.shape[:-2]``.
+          If empty, the result shape is determined by broadcasting the batch
+          shapes of ``mean`` and ``cov``. Default: ``[]``.
+        dtype (Dtype, optional): The output type. Default: ``float32``.
+        key (array, optional): A PRNG key. Default: ``None``.
+
+    Returns:
+        array: The output array of random values.
+    """
+
+def normal(
+    shape: Sequence[int] = ...,
+    dtype: Dtype | None = ...,
+    loc: scalar | array | None = ...,
+    scale: scalar | array | None = ...,
+    key: array | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    r"""
+    Generate normally distributed random numbers.
+
+    If ``loc`` and ``scale`` are not provided the "standard" normal
+    distribution is used. That means $x \sim \mathcal{N}(0, 1)$ for
+    real numbers and $\text{Re}(x),\text{Im}(x) \sim \mathcal{N}(0,
+    \frac{1}{2})$ for complex numbers.
+
+    Args:
+        shape (list(int), optional): Shape of the output. Default: ``()``.
+        dtype (Dtype, optional): Type of the output. Default: ``float32``.
+        loc (scalar or array, optional): Mean of the distribution.
+          Default: ``None``.
+        scale (scalar or array, optional): Standard deviation of the
+          distribution. Default: ``None``.
+        key (array, optional): A PRNG key. Default: ``None``.
+
+    Returns:
+        array: The output array of random values.
+    """
+
+def permutation(
+    x: int | array,
+    axis: int = ...,
+    key: array | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    """
+    Generate a random permutation or permute the entries of an array.
+
+    Args:
+        x (int or array, optional): If an integer is provided a random
+          permtuation of ``mx.arange(x)`` is returned. Otherwise the entries
+          of ``x`` along the given axis are randomly permuted.
+        axis (int, optional): The axis to permute along. Default: ``0``.
+        key (array, optional): A PRNG key. Default: ``None``.
+
+    Returns:
+        array:
+          The generated random permutation or randomly permuted input array.
+    """
+
+def randint(
+    low: scalar | array,
+    high: scalar | array,
+    shape: Sequence[int] = ...,
+    dtype: Dtype | None = ...,
+    key: array | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    """
+    Generate random integers from the given interval.
+
+    The values are sampled with equal probability from the integers in
+    half-open interval ``[low, high)``. The lower and upper bound can be
+    scalars or arrays and must be broadcastable to ``shape``.
+
+    Args:
+        low (scalar or array): Lower bound of the interval.
+        high (scalar or array): Upper bound of the interval.
+        shape (list(int), optional): Shape of the output. Default: ``()``.
+        dtype (Dtype, optional): Type of the output. Default: ``int32``.
+        key (array, optional): A PRNG key. Default: ``None``.
+
+    Returns:
+        array: The array of random integers.
+    """
+
+def seed(seed: int) -> None:
+    """
+    Seed the global PRNG.
+
+    Args:
+        seed (int): Seed for the global PRNG.
+    """
+
+def split(key: array, num: int = ..., stream: Stream | Device | None = ...) -> array:
+    """
+    Split a PRNG key into sub keys.
+
+    Args:
+        key (array): Input key to split.
+        num (int, optional): Number of sub keys. Default: ``2``.
+
+    Returns:
+        array: The array of sub keys with ``num`` as its first dimension.
+    """
+
+def truncated_normal(
+    lower: scalar | array,
+    upper: scalar | array,
+    shape: Sequence[int] | None = ...,
+    dtype: Dtype | None = ...,
+    key: array | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    """
+    Generate values from a truncated normal distribution.
+
+    The values are sampled from the truncated normal distribution
+    on the domain ``(lower, upper)``. The bounds ``lower`` and ``upper``
+    can be scalars or arrays and must be broadcastable to ``shape``.
+
+    Args:
+        lower (scalar or array): Lower bound of the domain.
+        upper (scalar or array): Upper bound of the domain.
+        shape (list(int), optional): The shape of the output.
+          Default:``()``.
+        dtype (Dtype, optional): The data type of the output.
+          Default: ``float32``.
+        key (array, optional): A PRNG key. Default: ``None``.
+
+    Returns:
+        array: The output array of random values.
+    """
+
+def uniform(
+    low: scalar | array = ...,
+    high: scalar | array = ...,
+    shape: Sequence[int] = ...,
+    dtype: Dtype | None = ...,
+    key: array | None = ...,
+    stream: Stream | Device | None = ...,
+) -> array:
+    """
+    Generate uniformly distributed random numbers.
+
+    The values are sampled uniformly in the half-open interval ``[low, high)``.
+    The lower and upper bound can be scalars or arrays and must be
+    broadcastable to ``shape``.
+
+    Args:
+        low (scalar or array, optional): Lower bound of the distribution.
+          Default: ``0``.
+        high (scalar or array, optional): Upper bound of the distribution.
+          Default: ``1``.
+        shape (list(int), optional): Shape of the output. Default:``()``.
+        dtype (Dtype, optional): Type of the output. Default: ``float32``.
+        key (array, optional): A PRNG key. Default: ``None``.
+
+    Returns:
+        array: The output array random values.
+    """

.mlx_typings/mlx/nn/__init__.pyi

@@ -0,0 +1,9 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from layers import *
+from utils import *
+
+from . import init as init
+from . import losses as losses

.mlx_typings/mlx/nn/init.pyi

@@ -0,0 +1,284 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Callable, Literal
+
+import mlx.core as mx
+
+def constant(value: float, dtype: mx.Dtype = ...) -> Callable[[mx.array], mx.array]:
+    r"""An initializer that returns an array filled with ``value``.
+
+    Args:
+        value (float): The value to fill the array with.
+        dtype (Dtype, optional): The data type of the array. Default:
+          ``float32``.
+
+    Returns:
+        Callable[[array], array]: An initializer that returns an array with the
+        same shape as the input, filled with ``value``.
+
+    Example:
+
+        >>> init_fn = nn.init.constant(0.5)
+        >>> init_fn(mx.zeros((2, 2)))
+        array([[0.5, 0.5],
+               [0.5, 0.5]], dtype=float32)
+    """
+
+def normal(
+    mean: float = ..., std: float = ..., dtype: mx.Dtype = ...
+) -> Callable[[mx.array], mx.array]:
+    r"""An initializer that returns samples from a normal distribution.
+
+    Args:
+        mean (float, optional): Mean of the normal distribution. Default:
+          ``0.0``.
+        std (float, optional): Standard deviation of the normal distribution.
+          Default: ``1.0``.
+        dtype (Dtype, optional): The data type of the array. Default:
+          ``float32``.
+
+    Returns:
+        Callable[[array], array]: An initializer that returns an array with the
+        same shape as the input, filled with samples from a normal distribution.
+
+    Example:
+
+        >>> init_fn = nn.init.normal()
+        >>> init_fn(mx.zeros((2, 2)))
+        array([[-0.982273, -0.534422],
+               [0.380709, 0.0645099]], dtype=float32)
+    """
+
+def uniform(
+    low: float = ..., high: float = ..., dtype: mx.Dtype = ...
+) -> Callable[[mx.array], mx.array]:
+    r"""An initializer that returns samples from a uniform distribution.
+
+    Args:
+        low (float, optional): The lower bound of the uniform distribution.
+          Default: ``0.0``.
+        high (float, optional): The upper bound of the uniform distribution.
+          Default: ``1.0``
+        dtype (Dtype, optional): The data type of the array. Default: ``float32``.
+
+    Returns:
+        Callable[[array], array]: An initializer that returns an array
+        with the same shape as the input, filled with samples from a uniform
+        distribution
+
+    Example:
+
+        >>> init_fn = nn.init.uniform(low=0, high=1)
+        >>> init_fn(mx.zeros((2, 2)))
+        array([[0.883935, 0.863726],
+               [0.617261, 0.417497]], dtype=float32)
+    """
+
+def identity(dtype: mx.Dtype = ...) -> Callable[[mx.array], mx.array]:
+    r"""An initializer that returns an identity matrix.
+
+    Args:
+        dtype (Dtype, optional): The data type of the array. Defaults:
+          ``float32``.
+
+    Returns:
+        Callable[[array], array]: An initializer that returns an identity
+        matrix with the same shape as the input.
+
+    Example:
+
+        >>> init_fn = nn.init.identity()
+        >>> init_fn(mx.zeros((2, 2)))
+        array([[1, 0],
+               [0, 1]], dtype=float32)
+    """
+
+def glorot_normal(dtype: mx.Dtype = ...) -> Callable[[mx.array, float], mx.array]:
+    r"""A Glorot normal initializer.
+
+    This initializer samples from a normal distribution with a standard
+    deviation computed from the number of input (``fan_in``) and output
+    (``fan_out``) units according to:
+
+    .. math::
+        \sigma = \gamma \sqrt{\frac{2.0}{\text{fan\_in} + \text{fan\_out}}}
+
+    For more details see the original reference: `Understanding the difficulty
+    of training deep feedforward neural networks
+    <https://proceedings.mlr.press/v9/glorot10a.html>`_
+
+    Args:
+        dtype (Dtype, optional): The data type of the array. Default: ``float32``.
+
+    Returns:
+        Callable[[array, float], array]: An initializer that returns an array
+        with the same shape as the input, filled with samples from the Glorot
+        normal distribution.
+
+    Example:
+
+        >>> init_fn = nn.init.glorot_normal()
+        >>> init_fn(mx.zeros((2, 2)))
+        array([[0.191107, 1.61278],
+               [-0.150594, -0.363207]], dtype=float32)
+        >>> init_fn(mx.zeros((2, 2)), gain=4.0)
+        array([[1.89613, -4.53947],
+               [4.48095, 0.995016]], dtype=float32)
+    """
+
+def glorot_uniform(dtype: mx.Dtype = ...) -> Callable[[mx.array, float], mx.array]:
+    r"""A Glorot uniform initializer.
+
+    This initializer samples from a uniform distribution with a range
+    computed from the number of input (``fan_in``) and output (``fan_out``)
+    units according to:
+
+    .. math::
+        \sigma = \gamma \sqrt{\frac{6.0}{\text{fan\_in} + \text{fan\_out}}}
+
+    For more details see the original reference: `Understanding the difficulty
+    of training deep feedforward neural networks
+    <https://proceedings.mlr.press/v9/glorot10a.html>`_
+
+    Args:
+        dtype (Dtype, optional): The data type of the array. Default: ``float32``.
+
+    Returns:
+        Callable[[array, float], array]: An initializer that returns an array
+        with the same shape as the input, filled with samples from the Glorot
+        uniform distribution.
+
+    Example:
+
+        >>> init_fn = nn.init.glorot_uniform()
+        >>> init_fn(mx.zeros((2, 2)))
+        array([[0.223404, -0.890597],
+               [-0.379159, -0.776856]], dtype=float32)
+        >>> init_fn(mx.zeros((2, 2)), gain=4.0)
+        array([[-1.90041, 3.02264],
+               [-0.912766, 4.12451]], dtype=float32)
+    """
+
+def he_normal(
+    dtype: mx.Dtype = ...,
+) -> Callable[[mx.array, Literal["fan_in", "fan_out"], float], mx.array]:
+    r"""Build a He normal initializer.
+
+    This initializer samples from a normal distribution with a standard
+    deviation computed from the number of input (``fan_in``) or output
+    (``fan_out``) units according to:
+
+    .. math::
+        \sigma = \gamma \frac{1}{\sqrt{\text{fan}}}
+
+    where :math:`\text{fan}` is either the number of input units when the
+    ``mode`` is ``"fan_in"`` or output units when the ``mode`` is
+    ``"fan_out"``.
+
+    For more details see the original reference: `Delving Deep into Rectifiers:
+    Surpassing Human-Level Performance on ImageNet Classification
+    <https://arxiv.org/abs/1502.01852>`_
+
+    Args:
+        dtype (Dtype, optional): The data type of the array. Defaults to mx.float32.
+
+    Returns:
+        Callable[[array, str, float], array]: An initializer that returns an
+        array with the same shape as the input, filled with samples from the He
+        normal distribution.
+
+    Example:
+
+        >>> init_fn = nn.init.he_normal()
+        >>> init_fn(mx.zeros((2, 2)))  # uses fan_in
+        array([[-1.25211, 0.458835],
+               [-0.177208, -0.0137595]], dtype=float32)
+        >>> init_fn(mx.zeros((2, 2)), mode="fan_out", gain=5)
+        array([[5.6967, 4.02765],
+               [-4.15268, -2.75787]], dtype=float32)
+    """
+
+def he_uniform(
+    dtype: mx.Dtype = ...,
+) -> Callable[[mx.array, Literal["fan_in", "fan_out"], float], mx.array]:
+    r"""A He uniform (Kaiming uniform) initializer.
+
+    This initializer samples from a uniform distribution with a range
+    computed from the number of input (``fan_in``) or output (``fan_out``)
+    units according to:
+
+    .. math::
+
+        \sigma = \gamma \sqrt{\frac{3.0}{\text{fan}}}
+
+    where :math:`\text{fan}` is either the number of input units when the
+    ``mode`` is ``"fan_in"`` or output units when the ``mode`` is
+    ``"fan_out"``.
+
+    For more details see the original reference: `Delving Deep into Rectifiers:
+    Surpassing Human-Level Performance on ImageNet Classification
+    <https://arxiv.org/abs/1502.01852>`_
+
+
+    Args:
+        dtype (Dtype, optional): The data type of the array. Default: ``float32``.
+
+    Returns:
+        Callable[[array, str, float], array]: An initializer that returns an
+        array with the same shape as the input, filled with samples from  the
+        He uniform distribution.
+
+    Example:
+
+        >>> init_fn = nn.init.he_uniform()
+        >>> init_fn(mx.zeros((2, 2)))  # uses fan_in
+        array([[0.0300242, -0.0184009],
+               [0.793615, 0.666329]], dtype=float32)
+        >>> init_fn(mx.zeros((2, 2)), mode="fan_out", gain=5)
+        array([[-1.64331, -2.16506],
+               [1.08619, 5.79854]], dtype=float32)
+    """
+
+def sparse(
+    sparsity: float, mean: float = ..., std: float = ..., dtype: mx.Dtype = ...
+) -> Callable[[mx.array], mx.array]:
+    r"""An initializer that returns a sparse matrix.
+
+    Args:
+        sparsity (float): The fraction of elements in each column to be set to
+        zero.
+        mean (float, optional): Mean of the normal distribution. Default:
+          ``0.0``.
+        std (float, optional): Standard deviation of the normal distribution.
+          Default: ``1.0``.
+        dtype (Dtype, optional): The data type of the array. Default:
+          ``float32``.
+
+    Returns:
+        Callable[[array], array]: An initializer that returns an array with the
+        same shape as the input, filled with samples from a normal distribution.
+
+    Example:
+
+        >>> init_fn = nn.init.sparse(sparsity=0.5)
+        >>> init_fn(mx.zeros((2, 2)))
+        array([[-1.91187, -0.117483],
+       [0, 0]], dtype=float32)
+    """
+
+def orthogonal(
+    gain: float = ..., dtype: mx.Dtype = ...
+) -> Callable[[mx.array], mx.array]:
+    r"""An initializer that returns an orthogonal matrix.
+
+    Args:
+        gain (float, optional): Scaling factor for the orthogonal matrix.
+            Default: ``1.0``.
+        dtype (Dtype, optional): Data type of the array. Default: ``float32``.
+
+    Returns:
+        Callable[[array], array]: An initializer that returns
+        an orthogonal matrix with the same shape as the input.
+    """

.mlx_typings/mlx/nn/layers/__init__.pyi

@@ -0,0 +1,20 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from activations import *
+from base import *
+from containers import *
+from convolution import *
+from convolution_transpose import *
+from distributed import *
+from dropout import *
+from embedding import *
+from linear import *
+from normalization import *
+from pooling import *
+from positional_encoding import *
+from quantized import *
+from recurrent import *
+from transformer import *
+from upsample import *

.mlx_typings/mlx/nn/layers/activations.pyi

@@ -0,0 +1,523 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from functools import partial
+from typing import Any
+
+import mlx.core as mx
+from base import Module
+
+@partial(mx.compile, shapeless=True)
+def sigmoid(x: mx.array) -> mx.array:
+    r"""Applies the sigmoid function.
+
+    .. math::
+        \text{Sigmoid}(x) = \sigma(x) = \frac{1}{1 + \exp(-x)}
+    """
+
+@partial(mx.compile, shapeless=True)
+def relu(x: mx.array) -> mx.array:
+    r"""Applies the Rectified Linear Unit.
+
+    Simply ``mx.maximum(x, 0)``.
+    """
+
+@partial(mx.compile, shapeless=True)
+def relu2(x: mx.array) -> mx.array:
+    r"""Applies the ReLU² activation function.
+
+    Applies :math:`\max(0, x)^2` element wise.
+    """
+
+@partial(mx.compile, shapeless=True)
+def relu6(x: mx.array) -> mx.array:
+    r"""Applies the Rectified Linear Unit 6.
+
+    Applies :math:`\min(\max(x, 0), 6)` element wise.
+    """
+
+@partial(mx.compile, shapeless=True)
+def leaky_relu(x: mx.array, negative_slope=...) -> mx.array:
+    r"""Applies the Leaky Rectified Linear Unit.
+
+    Simply ``mx.maximum(negative_slope * x, x)``.
+    """
+
+@partial(mx.compile, shapeless=True)
+def log_softmax(x: mx.array, axis=...):
+    r"""Applies the Log Softmax function.
+
+    Applies :math:`x + \log \sum_i e^{x_i}` element wise.
+    """
+
+@partial(mx.compile, shapeless=True)
+def elu(x: mx.array, alpha=...) -> mx.array:
+    r"""Applies the Exponential Linear Unit.
+
+    Simply ``mx.where(x > 0, x, alpha * (mx.exp(x) - 1))``.
+    """
+
+@partial(mx.compile, shapeless=True)
+def softmax(x: mx.array, axis=...) -> mx.array:
+    r"""Applies the Softmax function.
+
+    Applies :math:`\frac{e^{x_i}}{\sum_j e^{x_j}}` element wise.
+    """
+
+@partial(mx.compile, shapeless=True)
+def softplus(x: mx.array) -> mx.array:
+    r"""Applies the Softplus function.
+
+    Applies :math:`\log(1 + \exp(x))` element wise.
+    """
+
+@partial(mx.compile, shapeless=True)
+def softsign(x: mx.array) -> mx.array:
+    r"""Applies the Softsign function.
+
+    Applies :math:`\frac{x}{1 + |x|}` element wise.
+    """
+
+@partial(mx.compile, shapeless=True)
+def softshrink(x: mx.array, lambd: float = ...) -> mx.array:
+    r"""Applies the Softshrink activation function.
+
+    .. math::
+        \text{softshrink}(x) = \begin{cases}
+        x - \lambda & \text{if } x > \lambda \\
+        x + \lambda & \text{if } x < -\lambda \\
+        0 & \text{otherwise}
+        \end{cases}
+    """
+
+@partial(mx.compile, shapeless=True)
+def celu(x: mx.array, alpha=...) -> mx.array:
+    r"""Applies the Continuously Differentiable Exponential Linear Unit.
+
+    Applies :math:`\max(0, x) + \min(0, \alpha * (\exp(x / \alpha) - 1))`
+    element wise.
+    """
+
+@partial(mx.compile, shapeless=True)
+def silu(x: mx.array) -> mx.array:
+    r"""Applies the Sigmoid Linear Unit. Also known as Swish.
+
+    Applies :math:`x \sigma(x)` element wise, where :math:`\sigma(\cdot)` is
+    the logistic sigmoid.
+    """
+
+@partial(mx.compile, shapeless=True)
+def log_sigmoid(x: mx.array) -> mx.array:
+    r"""Applies the Log Sigmoid function.
+
+    Applies :math:`\log(\sigma(x)) = -\log(1 + e^{-x})` element wise.
+    """
+
+@partial(mx.compile, shapeless=True)
+def gelu(x: mx.array) -> mx.array:
+    r"""Applies the Gaussian Error Linear Units function.
+
+    .. math::
+        \textrm{GELU}(x) = x * \Phi(x)
+
+    where :math:`\Phi(x)` is the Gaussian CDF.
+
+    See also :func:`gelu_approx` and :func:`gelu_fast_approx` for faster
+    approximations.
+    """
+
+@partial(mx.compile, shapeless=True)
+def gelu_approx(x: mx.array) -> mx.array:
+    r"""An approximation to Gaussian Error Linear Unit.
+
+    See :func:`gelu` for the exact computation.
+
+    This function approximates ``gelu`` with a maximum absolute error :math:`<
+    0.0005` in the range :math:`[-6, 6]` using the following
+
+    .. math::
+
+        x = 0.5 * x * \left(1 + \text{Tanh}\left((\sqrt{2 / \pi} * \left(x + 0.044715 * x^3\right)\right)\right)
+
+    """
+
+@partial(mx.compile, shapeless=True)
+def gelu_fast_approx(x: mx.array) -> mx.array:
+    r"""A fast approximation to Gaussian Error Linear Unit.
+
+    See :func:`gelu` for the exact computation.
+
+    This function approximates ``gelu`` with a maximum absolute error :math:`<
+    0.015` in the range :math:`[-6, 6]` using the following
+
+    .. math::
+
+        x = x \sigma\left(1.702 x\right)
+
+    where :math:`\sigma(\cdot)` is the logistic sigmoid.
+
+    References:
+    - https://github.com/hendrycks/GELUs
+    - https://arxiv.org/abs/1606.08415
+    """
+
+def glu(x: mx.array, axis: int = ...) -> mx.array:
+    r"""Applies the gated linear unit function.
+
+    This function splits the ``axis`` dimension of the input into two halves
+    (:math:`a` and :math:`b`) and applies :math:`a * \sigma(b)`.
+
+    .. math::
+        \textrm{GLU}(x) = a * \sigma(b)
+
+    Args:
+        axis (int): The dimension to split along. Default: ``-1``
+    """
+
+@partial(mx.compile, shapeless=True)
+def step(x: mx.array, threshold: float = ...) -> mx.array:
+    r"""Applies the Step Activation Function.
+
+    This function implements a binary step activation, where the output is set
+    to 1 if the input is greater than a specified threshold, and 0 otherwise.
+
+    .. math::
+        \text{step}(x) = \begin{cases}
+        0 & \text{if } x < \text{threshold} \\
+        1 & \text{if } x \geq \text{threshold}
+        \end{cases}
+
+    Args:
+        threshold: The value to threshold at.
+    """
+
+@partial(mx.compile, shapeless=True)
+def selu(x: mx.array) -> mx.array:
+    r"""Applies the Scaled Exponential Linear Unit.
+
+    .. math::
+        \text{selu}(x) = \begin{cases}
+        \lambda x & \text{if } x > 0 \\
+        \lambda \alpha (\exp(x) - 1) & \text{if } x \leq 0
+        \end{cases}
+
+    where :math:`\lambda = 1.0507` and :math:`\alpha = 1.67326`.
+
+    See also :func:`elu`.
+    """
+
+@partial(mx.compile, shapeless=True)
+def prelu(x: mx.array, alpha: mx.array) -> mx.array:
+    r"""Applies the element-wise parametric ReLU.
+
+    .. math::
+        \text{PReLU}(x) = \max(0,x) + a * \min(0,x)
+
+    where :math:`a` is an array.
+    """
+
+@partial(mx.compile, shapeless=True)
+def mish(x: mx.array) -> mx.array:
+    r"""Applies the Mish function, element-wise.
+
+    Mish: A Self Regularized Non-Monotonic Neural Activation Function.
+
+    Reference: https://arxiv.org/abs/1908.08681
+
+    .. math::
+        \text{Mish}(x) = x * \text{Tanh}(\text{Softplus}(x))
+
+    """
+
+@partial(mx.compile, shapeless=True)
+def hardswish(x: mx.array) -> mx.array:
+    r"""Applies the hardswish function, element-wise.
+
+    .. math::
+        \text{Hardswish}(x) = x * \min(\max(x + 3, 0), 6) / 6
+    """
+
+@partial(mx.compile, shapeless=True)
+def hard_tanh(x: mx.array, min_val=..., max_val=...) -> mx.array:
+    r"""Applies the HardTanh function.
+
+    Applies :math:`\max(\min(x, \text{max\_val}), \text{min\_val})` element-wise.
+    """
+
+@partial(mx.compile, shapeless=True)
+def hard_shrink(x: mx.array, lambd=...) -> mx.array:
+    r"""Applies the HardShrink activation function.
+
+    .. math::
+        \text{hardshrink}(x) = \begin{cases}
+        x & \text{if } x > \lambda \\
+        x & \text{if } x < -\lambda \\
+        0 & \text{otherwise}
+        \end{cases}
+    """
+
+@partial(mx.compile, shapeless=True)
+def softmin(x: mx.array, axis=...) -> mx.array:
+    r"""Applies the Softmin function.
+
+    Applies :math:`\frac{e^{-x_i}}{\sum_j e^{-x_j}}` element-wise.
+    """
+
+def tanh(x: mx.array) -> mx.array:
+    """Applies the hyperbolic tangent function.
+
+    Simply ``mx.tanh(x)``.
+    """
+
+class GLU(Module):
+    r"""Applies the gated linear unit function.
+
+    This function splits the ``axis`` dimension of the input into two halves
+    (:math:`a` and :math:`b`) and applies :math:`a * \sigma(b)`.
+
+    .. math::
+        \textrm{GLU}(x) = a * \sigma(b)
+
+    Args:
+        axis (int): The dimension to split along. Default: ``-1``
+    """
+    def __init__(self, axis: int = ...) -> None: ...
+    def __call__(self, x) -> Any: ...
+
+@_make_activation_module(sigmoid)
+class Sigmoid(Module):
+    r"""Applies the sigmoid function, element-wise.
+
+    .. math::
+        \text{Sigmoid}(x) = \sigma(x) = \frac{1}{1 + \exp(-x)}
+    """
+
+@_make_activation_module(mish)
+class Mish(Module):
+    r"""Applies the Mish function, element-wise.
+
+    Reference: https://arxiv.org/abs/1908.08681
+
+    .. math::
+        \text{Mish}(x) = x * \text{Tanh}(\text{Softplus}(x))
+
+    """
+
+@_make_activation_module(relu)
+class ReLU(Module):
+    r"""Applies the Rectified Linear Unit.
+        Simply ``mx.maximum(x, 0)``.
+
+    See :func:`relu` for the functional equivalent.
+    """
+
+@_make_activation_module(relu2)
+class ReLU2(Module):
+    r"""Applies the ReLU² activation function.
+
+    See :func:`relu2` for the functional equivalent.
+    """
+
+@_make_activation_module(relu6)
+class ReLU6(Module):
+    r"""Applies the Rectified Linear Unit 6.
+
+    See :func:`relu6` for the functional equivalent.
+    """
+
+class LeakyReLU(Module):
+    r"""Applies the Leaky Rectified Linear Unit.
+
+    Simply ``mx.maximum(negative_slope * x, x)``.
+
+    Args:
+        negative_slope: Controls the angle of the negative slope. Default: ``1e-2``
+    """
+    def __init__(self, negative_slope=...) -> None: ...
+    def __call__(self, x): ...
+
+class ELU(Module):
+    r"""Applies the Exponential Linear Unit.
+        Simply ``mx.where(x > 0, x, alpha * (mx.exp(x) - 1))``.
+
+    See :func:`elu` for the functional equivalent.
+
+    Args:
+        alpha: the :math:`\alpha` value for the ELU formulation. Default: ``1.0``
+    """
+    def __init__(self, alpha=...) -> None: ...
+    def __call__(self, x): ...
+
+@_make_activation_module(softmax)
+class Softmax(Module):
+    r"""Applies the Softmax function.
+
+    See :func:`softmax` for the functional equivalent.
+    """
+
+@_make_activation_module(softplus)
+class Softplus(Module):
+    r"""Applies the Softplus function.
+
+    See :func:`softplus` for the functional equivalent.
+    """
+
+@_make_activation_module(softsign)
+class Softsign(Module):
+    r"""Applies the Softsign function.
+
+    See :func:`softsign` for the functional equivalent.
+    """
+
+class Softshrink(Module):
+    r"""Applies the Softshrink function.
+
+    See :func:`softshrink` for the functional equivalent.
+
+    Args:
+        lambd: the :math:`\lambda` value for Softshrink. Default: ``0.5``
+    """
+    def __init__(self, lambd=...) -> None: ...
+    def __call__(self, x): ...
+
+class CELU(Module):
+    r"""Applies the Continuously Differentiable Exponential Linear Unit.
+        Applies :math:`\max(0, x) + \min(0, \alpha * (\exp(x / \alpha) - 1))`
+        element wise.
+
+    See :func:`celu` for the functional equivalent.
+
+    Args:
+        alpha: the :math:`\alpha` value for the CELU formulation. Default: ``1.0``
+    """
+    def __init__(self, alpha=...) -> None: ...
+    def __call__(self, x): ...
+
+@_make_activation_module(silu)
+class SiLU(Module):
+    r"""Applies the Sigmoid Linear Unit. Also known as Swish.
+
+    See :func:`silu` for the functional equivalent.
+    """
+
+@_make_activation_module(log_softmax)
+class LogSoftmax(Module):
+    r"""Applies the Log Softmax function.
+
+    See :func:`log_softmax` for the functional equivalent.
+    """
+
+@_make_activation_module(log_sigmoid)
+class LogSigmoid(Module):
+    r"""Applies the Log Sigmoid function.
+
+    See :func:`log_sigmoid` for the functional equivalent.
+    """
+
+class PReLU(Module):
+    r"""Applies the element-wise parametric ReLU.
+        Applies :math:`\max(0, x) + a * \min(0, x)` element wise, where :math:`a`
+        is an array.
+
+    See :func:`prelu` for the functional equivalent.
+
+    Args:
+        num_parameters: number of :math:`a` to learn. Default: ``1``
+        init: the initial value of :math:`a`. Default: ``0.25``
+    """
+    def __init__(self, num_parameters=..., init=...) -> None: ...
+    def __call__(self, x: mx.array): ...
+
+class GELU(Module):
+    r"""Applies the Gaussian Error Linear Units.
+
+    .. math::
+        \textrm{GELU}(x) = x * \Phi(x)
+
+    where :math:`\Phi(x)` is the Gaussian CDF.
+
+    However, if ``approx`` is set to 'precise' or 'fast' it applies
+
+    .. math::
+        \textrm{GELUApprox}(x) &= 0.5 * x * \left(1 + \text{Tanh}\left((\sqrt{2 / \pi} * \left(x + 0.044715 * x^3\right)\right)\right) \\
+        \textrm{GELUFast}(x) &= x * \sigma\left(1.702 * x\right)
+
+    respectively.
+
+    .. note::
+       For compatibility with the PyTorch API, 'tanh' can be used as an alias
+       for 'precise'.
+
+    See :func:`gelu`, :func:`gelu_approx` and :func:`gelu_fast_approx` for the
+    functional equivalents and information regarding error bounds.
+
+
+    Args:
+        approx ('none' | 'precise' | 'fast'): Which approximation to gelu to use if any.
+    """
+    def __init__(self, approx=...) -> None: ...
+    def __call__(self, x): ...
+
+@_make_activation_module(tanh)
+class Tanh(Module):
+    r"""Applies the hyperbolic tangent function.
+
+    See :func:`tanh` for the functional equivalent.
+    """
+
+@_make_activation_module(hardswish)
+class Hardswish(Module):
+    r"""Applies the hardswish function, element-wise.
+
+    See :func:`hardswish` for the functional equivalent.
+    """
+
+class Step(Module):
+    r"""Applies the Step Activation Function.
+
+    This function implements a binary step activation, where the output is set
+    to 1 if the input is greater than a specified threshold, and 0 otherwise.
+
+    .. math::
+        \text{step}(x) = \begin{cases}
+        0 & \text{if } x < \text{threshold} \\
+        1 & \text{if } x \geq \text{threshold}
+        \end{cases}
+
+    Args:
+        threshold: The value to threshold at.
+    """
+    def __init__(self, threshold: float = ...) -> None: ...
+    def __call__(self, x: mx.array): ...
+
+@_make_activation_module(selu)
+class SELU(Module):
+    r"""Applies the Scaled Exponential Linear Unit.
+
+    See :func:`selu` for the functional equivalent.
+    """
+
+@_make_activation_module(hard_tanh)
+class HardTanh(Module):
+    r"""Applies the HardTanh function.
+
+    See :func:`hard_tanh` for the functional equivalent.
+    """
+
+@_make_activation_module(hard_shrink)
+class HardShrink(Module):
+    r"""Applies the HardShrink function.
+
+    See :func:`hard_shrink` for the functional equivalent.
+
+    Args:
+        lambd: the :math:`\lambda` value for Hardshrink. Default: ``0.5``
+    """
+
+@_make_activation_module(softmin)
+class Softmin(Module):
+    r"""Applies the Softmin function.
+
+    See :func:`softmin` for the functional equivalent.
+    """

.mlx_typings/mlx/nn/layers/base.pyi

@@ -0,0 +1,393 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Any, Callable, List, Optional, Tuple, Union
+
+import mlx.core as mx
+
+class Module(dict):
+    """Base class for building neural networks with MLX.
+
+    All the layers provided in :mod:`layers` subclass this class and
+    your models should do the same.
+
+    A ``Module`` can contain other ``Module`` instances or :class:`mlx.core.array`
+    instances in arbitrary nesting of python lists or dicts. The ``Module``
+    then allows recursively extracting all the :class:`mlx.core.array` instances
+    using :meth:`Module.parameters`.
+
+    In addition, the ``Module`` has the concept of trainable and non trainable
+    parameters (called "frozen"). When using :func:`value_and_grad`
+    the gradients are returned only with respect to the trainable parameters.
+    All arrays in a module are trainable unless they are added in the "frozen"
+    set by calling :meth:`freeze`.
+
+    .. code-block:: python
+
+        import mlx.core as mx
+        import mlx.nn as nn
+
+        class MyMLP(nn.Module):
+            def __init__(self, in_dims: int, out_dims: int, hidden_dims: int = 16):
+                super().__init__()
+
+                self.in_proj = nn.Linear(in_dims, hidden_dims)
+                self.out_proj = nn.Linear(hidden_dims, out_dims)
+
+            def __call__(self, x):
+                x = self.in_proj(x)
+                x = mx.maximum(x, 0)
+                return self.out_proj(x)
+
+        model = MyMLP(2, 1)
+
+        # All the model parameters are created but since MLX is lazy by
+        # default, they are not evaluated yet. Calling `mx.eval` actually
+        # allocates memory and initializes the parameters.
+        mx.eval(model.parameters())
+
+        # Setting a parameter to a new value is as simply as accessing that
+        # parameter and assigning a new array to it.
+        model.in_proj.weight = model.in_proj.weight * 2
+        mx.eval(model.parameters())
+    """
+
+    __call__: Callable
+    def __init__(self) -> None:
+        """Should be called by the subclasses of ``Module``."""
+
+    @property
+    def training(self):  # -> bool:
+        """Boolean indicating if the model is in training mode."""
+
+    @property
+    def state(self):  # -> Self:
+        """The module's state dictionary
+
+        The module's state dictionary contains any attribute set on the
+        module including parameters in :meth:`Module.parameters`
+
+        Unlike :meth:`Module.parameters`, the :attr:`Module.state` property is
+        a reference to the module's state. Updates to it will be reflected in
+        the original module.
+        """
+
+    def __repr__(self):  # -> str:
+        ...
+    def __getattr__(self, key: str):  # -> None:
+        ...
+    def __setattr__(self, key: str, val: Any):  # -> None:
+        ...
+    def __delattr__(self, name):  # -> None:
+        ...
+    def load_weights(
+        self,
+        file_or_weights: Union[str, List[Tuple[str, mx.array]]],
+        strict: bool = ...,
+    ) -> Module:
+        """
+        Update the model's weights from a ``.npz``, a ``.safetensors`` file, or a list.
+
+        Args:
+            file_or_weights (str or list(tuple(str, mx.array))): The path to
+                the weights ``.npz`` file (``.npz`` or ``.safetensors``) or a list
+                of pairs of parameter names and arrays.
+            strict (bool, optional): If ``True`` then checks that the provided
+              weights exactly match the parameters of the model. Otherwise,
+              only the weights actually contained in the model are loaded and
+              shapes are not checked. Default: ``True``.
+
+        Returns:
+            The module instance after updating the weights.
+
+        Example:
+
+            .. code-block:: python
+
+                import mlx.core as mx
+                import mlx.nn as nn
+                model = nn.Linear(10, 10)
+
+                # Load from file
+                model.load_weights("weights.npz")
+
+                # Load from .safetensors file
+                model.load_weights("weights.safetensors")
+
+                # Load from list
+                weights = [
+                    ("weight", mx.random.uniform(shape=(10, 10))),
+                    ("bias",  mx.zeros((10,))),
+                ]
+                model.load_weights(weights)
+
+                # Missing weight
+                weights = [
+                    ("weight", mx.random.uniform(shape=(10, 10))),
+                ]
+
+                # Raises a ValueError exception
+                model.load_weights(weights)
+
+                # Ok, only updates the weight but not the bias
+                model.load_weights(weights, strict=False)
+        """
+
+    def save_weights(self, file: str):  # -> None:
+        """
+        Save the model's weights to a file. The saving method is determined by the file extension:
+        - ``.npz`` will use :func:`mx.savez`
+        - ``.safetensors`` will use :func:`mx.save_safetensors`
+        """
+
+    @staticmethod
+    def is_module(value):  # -> bool:
+        ...
+    @staticmethod
+    def valid_child_filter(module, key, value):  # -> bool:
+        ...
+    @staticmethod
+    def valid_parameter_filter(module, key, value):  # -> bool:
+        ...
+    @staticmethod
+    def trainable_parameter_filter(module, key, value):  # -> bool:
+        ...
+    def filter_and_map(
+        self,
+        filter_fn: Callable[[Module, str, Any], bool],
+        map_fn: Optional[Callable] = ...,
+        is_leaf_fn: Optional[Callable[[Module, str, Any], bool]] = ...,
+    ):  # -> dict[Any, Any | dict[Any, Any | dict[Any, Any] | list[Any]] | dict[Any, Any] | list[Any]]:
+        """Recursively filter the contents of the module using ``filter_fn``,
+        namely only select keys and values where ``filter_fn`` returns true.
+
+        This is used to implement :meth:`parameters` and :meth:`trainable_parameters`
+        but it can also be used to extract any subset of the module's parameters.
+
+        Args:
+            filter_fn (Callable): Given a value, the key in which it is found
+                and the containing module, decide whether to keep the value or
+                drop it.
+            map_fn (Callable, optional): Optionally transform the value before
+                returning it.
+            is_leaf_fn (Callable, optional): Given a value, the key in which it
+                is found and the containing module decide if it is a leaf.
+
+        Returns:
+            A dictionary containing the contents of the module recursively filtered
+        """
+
+    def parameters(
+        self,
+    ) -> mx.MX_ARRAY_TREE:
+        """Recursively return all the :class:`mlx.core.array` members of this Module
+        as a dict of dicts and lists."""
+
+    def trainable_parameters(
+        self,
+    ) -> mx.MX_ARRAY_TREE:  # -> dict[Any, Any | dict[Any, Any | dict[Any, Any] | list[Any]] | dict[Any, Any] | list[Any]]:
+        """Recursively return all the non frozen :class:`mlx.core.array` members of
+        this Module as a dict of dicts and lists."""
+
+    def children(
+        self,
+    ) -> mx.MX_ARRAY_TREE:  # -> dict[Any, Any | dict[Any, Any | dict[Any, Any] | list[Any]] | dict[Any, Any] | list[Any]]:
+        """Return the direct descendants of this Module instance."""
+
+    def leaf_modules(
+        self,
+    ) -> mx.MX_ARRAY_TREE:  # -> dict[Any, Any | dict[Any, Any | dict[Any, Any] | list[Any]] | dict[Any, Any] | list[Any]]:
+        """Return the submodules that do not contain other modules."""
+
+    def update(self, parameters: dict, strict: bool = ...) -> Module:
+        """Replace the parameters of this Module with the provided ones in the
+        dict of dicts and lists.
+
+        Commonly used by the optimizer to change the model to the updated
+        (optimized) parameters. Also used by the :meth:`value_and_grad` to set the
+        tracers in the model in order to compute gradients.
+
+        The passed in parameters dictionary need not be a full dictionary
+        similar to :meth:`parameters`. Only the provided locations will be
+        updated.
+
+        Args:
+            parameters (dict): A complete or partial dictionary of the modules
+                parameters.
+            strict (bool): If ``True`` checks that ``parameters`` is a
+                subset of the module's parameters. Default: ``True``.
+        Returns:
+            The module instance after updating the parameters.
+        """
+
+    def apply(
+        self,
+        map_fn: Callable[[mx.array], mx.array],
+        filter_fn: Optional[Callable[[Module, str, Any], bool]] = ...,
+    ) -> Module:
+        """Map all the parameters using the provided ``map_fn`` and immediately
+        update the module with the mapped parameters.
+
+        For instance running ``model.apply(lambda x: x.astype(mx.float16))``
+        casts all parameters to 16 bit floats.
+
+        Args:
+            map_fn (Callable): Maps an array to another array
+            filter_fn (Callable, optional): Filter to select which arrays to
+                map (default: :meth:`Module.valid_parameter_filter`).
+
+        Returns:
+            The module instance after updating the parameters.
+        """
+
+    def update_modules(self, modules: dict, strict: bool = ...) -> Module:
+        """Replace the child modules of this :class:`Module` instance with the
+        provided ones in the dict of dicts and lists.
+
+        It is the equivalent of :meth:`Module.update` but for modules instead
+        of parameters and allows us to flexibly edit complex architectures by
+        programmatically swapping layers.
+
+        The passed in parameters dictionary need not be a full dictionary
+        similar to :meth:`modules`. Only the provided locations will be
+        updated.
+
+        Args:
+            modules (dict): A complete or partial dictionary of the module's
+                submodules.
+            strict (bool): If ``True`` checks that ``modules`` is a
+                subset of the child modules of this instance. Default: ``True``.
+        Returns:
+            The module instance after updating the submodules.
+        """
+
+    def apply_to_modules(self, apply_fn: Callable[[str, Module], Any]) -> Module:
+        """Apply a function to all the modules in this instance (including this
+        instance).
+
+        Args:
+            apply_fn (Callable): The function to apply to the modules.
+
+        Returns:
+            The module instance after updating submodules.
+        """
+
+    def modules(self):  # -> list[Any]:
+        """Return a list with all the modules in this instance.
+
+        Returns:
+            A list of :class:`Module` instances.
+        """
+
+    def named_modules(self):  # -> list[Any]:
+        """Return a list with all the modules in this instance and their name
+        with dot notation.
+
+        Returns:
+            A list of tuples (str, :class:`Module`).
+        """
+
+    def freeze(
+        self,
+        *,
+        recurse: bool = ...,
+        keys: Optional[Union[str, List[str]]] = ...,
+        strict: bool = ...,
+    ) -> Module:
+        """Freeze the Module's parameters or some of them. Freezing a parameter means not
+        computing gradients for it.
+
+        This function is idempotent i.e. freezing a frozen model is a no-op.
+
+        Example:
+            For instance to only train the attention parameters from a Transformer:
+
+            .. code-block:: python
+
+                model = nn.Transformer()
+                model.freeze()
+                model.apply_to_modules(lambda k, v: v.unfreeze() if k.endswith("attention") else None)
+
+        Args:
+            recurse (bool, optional): If True then freeze the parameters of the
+                submodules as well. Default: ``True``.
+            keys (str or list[str], optional): If provided then only these
+                parameters will be frozen otherwise all the parameters of a
+                module. For instance freeze all biases by calling
+                ``module.freeze(keys="bias")``.
+            strict (bool, optional): If set to ``True`` validate that the passed keys exist.
+                Default: ``False``.
+
+        Returns:
+            The module instance after freezing the parameters.
+        """
+
+    def unfreeze(
+        self,
+        *,
+        recurse: bool = ...,
+        keys: Optional[Union[str, List[str]]] = ...,
+        strict: bool = ...,
+    ) -> Module:
+        """Unfreeze the Module's parameters or some of them.
+
+        This function is idempotent ie unfreezing a model that is not frozen is
+        a noop.
+
+        Example:
+
+            For instance to only train the biases of a Transformer one can do:
+
+            .. code-block:: python
+
+                model = nn.Transformer()
+                model.freeze()
+                model.unfreeze(keys="bias")
+
+        Args:
+            recurse (bool, optional): If True then unfreeze the parameters of the
+                submodules as well. Default: ``True``.
+            keys (str or list[str], optional): If provided then only these
+                parameters will be unfrozen otherwise all the parameters of a
+                module. For instance unfreeze all biases by calling
+                ``module.unfreeze(keys="bias")``.
+            strict (bool, optional): If set to ``True`` validate that the passed keys exist.
+                Default: ``False``.
+
+        Returns:
+            The module instance after unfreezing the parameters.
+        """
+
+    def train(self, mode: bool = ...) -> Module:
+        """Set the model in or out of training mode.
+
+        Training mode only applies to certain layers. For example
+        :obj:`Dropout` applies a random mask in training mode, but is the
+        identity in evaluation mode.
+
+        Args:
+            mode (bool): Indicate if the model should be in training or
+                evaluation mode. Default: ``True``.
+        Returns:
+            The module instance after updating the training mode.
+        """
+
+    def eval(self) -> Module:
+        """Set the model to evaluation mode.
+
+        See :func:`train`.
+        """
+
+    def set_dtype(
+        self, dtype: mx.Dtype, predicate: Optional[Callable[[mx.Dtype], bool]] = ...
+    ):  # -> None:
+        """Set the dtype of the module's parameters.
+
+        Args:
+            dtype (Dtype): The new dtype.
+            predicate (typing.Callable, optional): A predicate to select
+              parameters to cast. By default, only parameters of type
+              :attr:`floating` will be updated to avoid casting integer
+              parameters to the new dtype.
+        """

.mlx_typings/mlx/nn/layers/containers.pyi

@@ -0,0 +1,21 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Callable
+
+import mlx.core as mx
+from base import Module
+
+class Sequential(Module):
+    """A layer that calls the passed callables in order.
+
+    We can pass either modules or plain callables to the Sequential module. If
+    our functions have learnable parameters they should be implemented as
+    ``nn.Module`` instances.
+
+    Args:
+        modules (tuple of Callables): The modules to call in order
+    """
+    def __init__(self, *modules: Module | Callable[[mx.array], mx.array]) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...

.mlx_typings/mlx/nn/layers/convolution.pyi

@@ -0,0 +1,116 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Union
+
+import mlx.core as mx
+from base import Module
+
+class Conv1d(Module):
+    """Applies a 1-dimensional convolution over the multi-channel input sequence.
+
+    The channels are expected to be last i.e. the input shape should be ``NLC`` where:
+
+    * ``N`` is the batch dimension
+    * ``L`` is the sequence length
+    * ``C`` is the number of input channels
+
+    Args:
+        in_channels (int): The number of input channels
+        out_channels (int): The number of output channels
+        kernel_size (int): The size of the convolution filters
+        stride (int, optional): The stride when applying the filter.
+            Default: ``1``.
+        padding (int, optional): How many positions to 0-pad the input with.
+            Default: ``0``.
+        dilation (int, optional): The dilation of the convolution.
+        groups (int, optional): The number of groups for the convolution.
+            Default: ``1``.
+        bias (bool, optional): If ``True`` add a learnable bias to the output.
+            Default: ``True``
+    """
+    def __init__(
+        self,
+        in_channels: int,
+        out_channels: int,
+        kernel_size: int,
+        stride: int = ...,
+        padding: int = ...,
+        dilation: int = ...,
+        groups: int = ...,
+        bias: bool = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class Conv2d(Module):
+    """Applies a 2-dimensional convolution over the multi-channel input image.
+
+    The channels are expected to be last i.e. the input shape should be ``NHWC`` where:
+
+    * ``N`` is the batch dimension
+    * ``H`` is the input image height
+    * ``W`` is the input image width
+    * ``C`` is the number of input channels
+
+    Args:
+        in_channels (int): The number of input channels.
+        out_channels (int): The number of output channels.
+        kernel_size (int or tuple): The size of the convolution filters.
+        stride (int or tuple, optional): The size of the stride when
+            applying the filter. Default: ``1``.
+        padding (int or tuple, optional): How many positions to 0-pad
+            the input with. Default: ``0``.
+        dilation (int or tuple, optional): The dilation of the convolution.
+        groups (int, optional): The number of groups for the convolution.
+            Default: ``1``.
+        bias (bool, optional): If ``True`` add a learnable bias to the
+            output. Default: ``True``
+    """
+    def __init__(
+        self,
+        in_channels: int,
+        out_channels: int,
+        kernel_size: Union[int, tuple],
+        stride: Union[int, tuple] = ...,
+        padding: Union[int, tuple] = ...,
+        dilation: Union[int, tuple] = ...,
+        groups: int = ...,
+        bias: bool = ...,
+    ) -> None: ...
+    def __call__(self, x) -> mx.array: ...
+
+class Conv3d(Module):
+    """Applies a 3-dimensional convolution over the multi-channel input image.
+
+    The channels are expected to be last i.e. the input shape should be ``NDHWC`` where:
+
+    * ``N`` is the batch dimension
+    * ``D`` is the input image depth
+    * ``H`` is the input image height
+    * ``W`` is the input image width
+    * ``C`` is the number of input channels
+
+    Args:
+        in_channels (int): The number of input channels.
+        out_channels (int): The number of output channels.
+        kernel_size (int or tuple): The size of the convolution filters.
+        stride (int or tuple, optional): The size of the stride when
+            applying the filter. Default: ``1``.
+        dilation (int or tuple, optional): The dilation of the convolution.
+        padding (int or tuple, optional): How many positions to 0-pad
+            the input with. Default: ``0``.
+        bias (bool, optional): If ``True`` add a learnable bias to the
+            output. Default: ``True``
+    """
+    def __init__(
+        self,
+        in_channels: int,
+        out_channels: int,
+        kernel_size: Union[int, tuple],
+        stride: Union[int, tuple] = ...,
+        padding: Union[int, tuple] = ...,
+        dilation: Union[int, tuple] = ...,
+        bias: bool = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...

.mlx_typings/mlx/nn/layers/convolution_transpose.pyi

@@ -0,0 +1,119 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Union
+
+import mlx.core as mx
+from base import Module
+
+class ConvTranspose1d(Module):
+    """Applies a 1-dimensional transposed convolution over the multi-channel input sequence.
+
+    The channels are expected to be last i.e. the input shape should be ``NLC`` where:
+
+    * ``N`` is the batch dimension
+    * ``L`` is the sequence length
+    * ``C`` is the number of input channels
+
+    Args:
+        in_channels (int): The number of input channels
+        out_channels (int): The number of output channels
+        kernel_size (int): The size of the convolution filters
+        stride (int, optional): The stride when applying the filter.
+            Default: ``1``.
+        padding (int, optional): How many positions to 0-pad the input with.
+            Default: ``0``.
+        dilation (int, optional): The dilation of the convolution.
+        output_padding(int, optional): Additional size added to one side of the
+            output shape. Default: ``0``.
+        bias (bool, optional): If ``True`` add a learnable bias to the output.
+            Default: ``True``
+    """
+    def __init__(
+        self,
+        in_channels: int,
+        out_channels: int,
+        kernel_size: int,
+        stride: int = ...,
+        padding: int = ...,
+        dilation: int = ...,
+        output_padding: int = ...,
+        bias: bool = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class ConvTranspose2d(Module):
+    """Applies a 2-dimensional transposed convolution over the multi-channel input image.
+
+    The channels are expected to be last i.e. the input shape should be ``NHWC`` where:
+
+    * ``N`` is the batch dimension
+    * ``H`` is the input image height
+    * ``W`` is the input image width
+    * ``C`` is the number of input channels
+
+    Args:
+        in_channels (int): The number of input channels.
+        out_channels (int): The number of output channels.
+        kernel_size (int or tuple): The size of the convolution filters.
+        stride (int or tuple, optional): The size of the stride when
+            applying the filter. Default: ``1``.
+        padding (int or tuple, optional): How many positions to 0-pad
+            the input with. Default: ``0``.
+        dilation (int or tuple, optional): The dilation of the convolution.
+        output_padding(int or tuple, optional): Additional size added to one
+            side of the output shape. Default: ``0``.
+        bias (bool, optional): If ``True`` add a learnable bias to the
+            output. Default: ``True``
+    """
+    def __init__(
+        self,
+        in_channels: int,
+        out_channels: int,
+        kernel_size: Union[int, tuple],
+        stride: Union[int, tuple] = ...,
+        padding: Union[int, tuple] = ...,
+        dilation: Union[int, tuple] = ...,
+        output_padding: Union[int, tuple] = ...,
+        bias: bool = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class ConvTranspose3d(Module):
+    """Applies a 3-dimensional transposed convolution over the multi-channel input image.
+
+    The channels are expected to be last i.e. the input shape should be ``NDHWC`` where:
+
+    * ``N`` is the batch dimension
+    * ``D`` is the input image depth
+    * ``H`` is the input image height
+    * ``W`` is the input image width
+    * ``C`` is the number of input channels
+
+    Args:
+        in_channels (int): The number of input channels.
+        out_channels (int): The number of output channels.
+        kernel_size (int or tuple): The size of the convolution filters.
+        stride (int or tuple, optional): The size of the stride when
+            applying the filter. Default: ``1``.
+        padding (int or tuple, optional): How many positions to 0-pad
+            the input with. Default: ``0``.
+        dilation (int or tuple, optional): The dilation of the convolution.
+        output_padding(int or tuple, optional): Additional size added to one
+            side of the output shape. Default: ``0``.
+        bias (bool, optional): If ``True`` add a learnable bias to the
+            output. Default: ``True``
+    """
+    def __init__(
+        self,
+        in_channels: int,
+        out_channels: int,
+        kernel_size: Union[int, tuple],
+        stride: Union[int, tuple] = ...,
+        padding: Union[int, tuple] = ...,
+        dilation: Union[int, tuple] = ...,
+        output_padding: Union[int, tuple] = ...,
+        bias: bool = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...

.mlx_typings/mlx/nn/layers/distributed.pyi

@@ -0,0 +1,227 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from functools import lru_cache
+from typing import Callable, Optional, Union
+
+import mlx.core as mx
+from base import Module
+from mlx.nn.layers.linear import Linear
+
+@lru_cache
+def sum_gradients(
+    group: mx.distributed.Group,
+) -> Callable[..., mx.array]:  # -> Callable[..., Any] | Callable[..., array]:
+    ...
+def shard_inplace(
+    module: Module,
+    sharding: str,
+    *,
+    segments: Union[int, list[int]] = ...,
+    group: Optional[mx.distributed.Group] = ...,
+) -> None:
+    """Shard a module in-place by updating its parameter dictionary with the
+    sharded parameter dictionary.
+
+    The ``sharding`` argument can be any callable that given the path and the
+    weight returns the sharding axis and optionally also the segments that
+    comprise the unsharded weight. For instance if the weight is a fused QKV
+    matrix the segments should be 3.
+
+    .. note::
+        The module doesn't change so in order for distributed communication to
+        happen the module needs to natively support it and for it to be enabled.
+
+    Args:
+        module (Module): The parameters of this module will be sharded
+            in-place.
+        sharding (str or callable): One of "all-to-sharded" and
+            "sharded-to-all" or a callable that returns the sharding axis and
+            segments.
+        segments (int or list): The segments to use if ``sharding`` is a
+            string. Default: ``1``.
+        group (mlx.core.distributed.Group): The distributed group to shard
+            across. If not set, the global group will be used. Default: ``None``.
+    """
+
+def shard_linear(
+    module: Module,
+    sharding: str,
+    *,
+    segments: Union[int, list[int]] = ...,
+    group: Optional[mx.distributed.Group] = ...,
+) -> Linear:
+    """Create a new linear layer that has its parameters sharded and also
+    performs distributed communication either in the forward or backward
+    pass.
+
+    .. note::
+        Contrary to ``shard_inplace``, the original layer is not changed but a
+        new layer is returned.
+
+    Args:
+        module (Module): The linear layer to be sharded.
+        sharding (str): One of "all-to-sharded" and
+            "sharded-to-all" that defines the type of sharding to perform.
+        segments (int or list): The segments to use. Default: ``1``.
+        group (mlx.core.distributed.Group): The distributed group to shard
+            across. If not set, the global group will be used. Default: ``None``.
+    """
+
+class AllToShardedLinear(Module):
+    """Each member of the group applies part of the affine transformation such
+    that the result is sharded across the group.
+
+    The gradients are automatically aggregated from each member of the group.
+
+    Args:
+        input_dims (int): The dimensionality of the input features
+        output_dims (int): The dimensionality of the output features
+        bias (bool, optional): If set to ``False`` the the layer will not use a
+            bias. Default is ``True``.
+        group (mx.distributed.Group, optional): The sharding will happen across
+            this group. If not set then the global group is used. Default is
+            ``None``.
+    """
+    def __init__(
+        self,
+        input_dims: int,
+        output_dims: int,
+        bias: bool = ...,
+        group: Optional[mx.distributed.Group] = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+    @classmethod
+    def from_linear(
+        cls,
+        linear_layer: Module,
+        *,
+        segments: Union[int, list[int]] = ...,
+        group: Optional[mx.distributed.Group] = ...,
+    ) -> AllToShardedLinear: ...
+
+class ShardedToAllLinear(Module):
+    """Each member of the group applies part of the affine transformation and
+    then aggregates the results.
+
+    All nodes will have the same exact result after this layer.
+
+    :class:`ShardedToAllLinear` provides a classmethod :meth:`from_linear` to
+    convert linear layers to sharded :obj:`ShardedToAllLinear` layers.
+
+    Args:
+        input_dims (int): The dimensionality of the input features
+        output_dims (int): The dimensionality of the output features
+        bias (bool, optional): If set to ``False`` the the layer will not use a
+            bias. Default is ``True``.
+        group (mx.distributed.Group, optional): The sharding will happen across
+            this group. If not set then the global group is used. Default is
+            ``None``.
+    """
+    def __init__(
+        self,
+        input_dims: int,
+        output_dims: int,
+        bias: bool = ...,
+        group: Optional[mx.distributed.Group] = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+    @classmethod
+    def from_linear(
+        cls,
+        linear_layer: Module,
+        *,
+        segments: Union[int, list[int]] = ...,
+        group: Optional[mx.distributed.Group] = ...,
+    ) -> ShardedToAllLinear: ...
+
+class QuantizedAllToShardedLinear(Module):
+    """Each member of the group applies part of the affine transformation with
+    a quantized matrix such that the result is sharded across the group.
+
+    It is the quantized equivalent of :class:`AllToShardedLinear`.
+    Similar to :class:`QuantizedLinear` its parameters are frozen and
+    will not be included in any gradient computation.
+
+    Args:
+        input_dims (int): The dimensionality of the input features.
+        output_dims (int): The dimensionality of the output features.
+        bias (bool, optional): If set to ``False`` then the layer will not use
+            a bias. Default: ``True``.
+        group_size (int, optional): The group size to use for the quantized
+            weight. See :func:`~mlx.core.quantize`. Default: ``64``.
+        bits (int, optional): The bit width to use for the quantized weight.
+            See :func:`~mlx.core.quantize`. Default: ``4``.
+        group (mx.distributed.Group, optional): The sharding will happen across
+            this group. If not set then the global group is used. Default is
+            ``None``.
+    """
+    def __init__(
+        self,
+        input_dims: int,
+        output_dims: int,
+        bias: bool = ...,
+        group_size: int = ...,
+        bits: int = ...,
+        group: Optional[mx.distributed.Group] = ...,
+    ) -> None: ...
+    def unfreeze(self, *args, **kwargs) -> None:
+        """Wrap unfreeze so that we unfreeze any layers we might contain but
+        our parameters will remain frozen."""
+
+    def __call__(self, x: mx.array) -> mx.array: ...
+    @classmethod
+    def from_quantized_linear(
+        cls,
+        quantized_linear_layer: Module,
+        *,
+        segments: Union[int, list[int]] = ...,
+        group: Optional[mx.distributed.Group] = ...,
+    ) -> QuantizedAllToShardedLinear: ...
+
+class QuantizedShardedToAllLinear(Module):
+    """Each member of the group applies part of the affine transformation using
+    the quantized matrix and then aggregates the results.
+
+    All nodes will have the same exact result after this layer.
+
+    It is the quantized equivalent of :class:`ShardedToAllLinear`.
+    Similar to :class:`QuantizedLinear` its parameters are frozen and
+    will not be included in any gradient computation.
+
+    Args:
+        input_dims (int): The dimensionality of the input features.
+        output_dims (int): The dimensionality of the output features.
+        bias (bool, optional): If set to ``False`` then the layer will not use
+            a bias. Default: ``True``.
+        group_size (int, optional): The group size to use for the quantized
+            weight. See :func:`~mlx.core.quantize`. Default: ``64``.
+        bits (int, optional): The bit width to use for the quantized weight.
+            See :func:`~mlx.core.quantize`. Default: ``4``.
+        group (mx.distributed.Group, optional): The sharding will happen across
+            this group. If not set then the global group is used. Default is
+            ``None``.
+    """
+    def __init__(
+        self,
+        input_dims: int,
+        output_dims: int,
+        bias: bool = ...,
+        group_size: int = ...,
+        bits: int = ...,
+        group: Optional[mx.distributed.Group] = ...,
+    ) -> None: ...
+    def unfreeze(self, *args, **kwargs):  # -> None:
+        """Wrap unfreeze so that we unfreeze any layers we might contain but
+        our parameters will remain frozen."""
+
+    def __call__(self, x: mx.array) -> mx.array: ...
+    @classmethod
+    def from_quantized_linear(
+        cls,
+        quantized_linear_layer: Module,
+        *,
+        segments: Union[int, list[int]] = ...,
+        group: Optional[mx.distributed.Group] = ...,
+    ) -> QuantizedShardedToAllLinear: ...

.mlx_typings/mlx/nn/layers/dropout.pyi

@@ -0,0 +1,65 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+import mlx.core as mx
+from base import Module
+
+class Dropout(Module):
+    r"""Randomly zero a portion of the elements during training.
+
+    The remaining elements are multiplied with :math:`\frac{1}{1-p}` where
+    :math:`p` is the probability of zeroing an element. This is done so the
+    expected value of a given element will remain the same.
+
+    Args:
+        p (float): The probability to zero an element
+    """
+    def __init__(self, p: float = ...) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class Dropout2d(Module):
+    r"""Apply 2D channel-wise dropout during training.
+
+    Randomly zero out entire channels independently with probability :math:`p`.
+    This layer expects the channels to be last, i.e. the input shape should be
+    ``NWHC`` or ``WHC`` where:``N`` is the batch dimension,``H`` is the input
+    image height,``W`` is the input image width, and``C`` is the number of
+    input channels
+
+    The remaining channels are scaled by :math:`\frac{1}{1-p}` to
+    maintain the expected value of each element. Unlike traditional dropout,
+    which zeros individual entries, this layer zeros entire channels. This is
+    beneficial for early convolution layers where adjacent pixels are
+    correlated. In such case, traditional dropout may not effectively
+    regularize activations. For more details, see [1].
+
+    [1]: Thompson, J., Goroshin, R., Jain, A., LeCun, Y. and Bregler C., 2015.
+    Efficient Object Localization Using Convolutional Networks. CVPR 2015.
+
+    Args:
+        p (float): Probability of zeroing a channel during training.
+    """
+    def __init__(self, p: float = ...) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class Dropout3d(Module):
+    r"""Apply 3D channel-wise dropout during training.
+
+    Randomly zero out entire channels independently with probability :math:`p`.
+    This layer expects the channels to be last, i.e., the input shape should be
+    `NDHWC` or `DHWC` where: `N` is the batch dimension, `D` is the depth,
+    `H` is the input image height, `W` is the input image width, and `C` is
+    the number of input channels.
+
+    The remaining channels are scaled by :math:`\frac{1}{1-p}` to
+    maintain the expected value of each element. Unlike traditional dropout,
+    which zeros individual entries, this layer zeros entire channels. This is
+    often beneficial for convolutional layers processing 3D data, like in
+    medical imaging or video processing.
+
+    Args:
+        p (float): Probability of zeroing a channel during training.
+    """
+    def __init__(self, p: float = ...) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...

.mlx_typings/mlx/nn/layers/embedding.pyi

@@ -0,0 +1,34 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+import mlx.core as mx
+from base import Module
+
+from .quantized import QuantizedEmbedding
+
+class Embedding(Module):
+    """Implements a simple lookup table that maps each input integer to a
+    high-dimensional vector.
+
+    Typically used to embed discrete tokens for processing by neural networks.
+
+    Args:
+        num_embeddings (int): How many possible discrete tokens can we embed.
+           Usually called the vocabulary size.
+        dims (int): The dimensionality of the embeddings.
+    """
+    def __init__(self, num_embeddings: int, dims: int) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+    def as_linear(self, x: mx.array) -> mx.array:
+        """
+        Call the embedding layer as a linear layer.
+
+        Use this for example when input embedding and output projection
+        weights are tied.
+        """
+
+    def to_quantized(
+        self, group_size: int = ..., bits: int = ..., mode: str = ...
+    ) -> QuantizedEmbedding:
+        """Return a :obj:`QuantizedEmbedding` layer that approximates this embedding layer."""

.mlx_typings/mlx/nn/layers/linear.pyi

@@ -0,0 +1,76 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Any
+
+import mlx.core as mx
+from base import Module
+
+from .quantized import QuantizedLinear
+
+class Identity(Module):
+    r"""A placeholder identity operator that is argument-insensitive.
+
+    Args:
+        args: any argument (unused)
+        kwargs: any keyword argument (unused)
+    """
+    def __init__(self, *args: Any, **kwargs: Any) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class Linear(Module):
+    r"""Applies an affine transformation to the input.
+
+    Concretely:
+
+    .. math::
+
+        y = x W^\top + b
+
+    where:
+    where :math:`W` has shape ``[output_dims, input_dims]`` and :math:`b` has shape ``[output_dims]``.
+
+    The values are initialized from the uniform distribution :math:`\mathcal{U}(-{k}, {k})`,
+    where :math:`k = \frac{1}{\sqrt{D_i}}` and :math:`D_i` is equal to ``input_dims``.
+
+    Args:
+        input_dims (int): The dimensionality of the input features
+        output_dims (int): The dimensionality of the output features
+        bias (bool, optional): If set to ``False`` then the layer will
+          not use a bias. Default is ``True``.
+    """
+    def __init__(self, input_dims: int, output_dims: int, bias: bool = ...) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+    def to_quantized(
+        self, group_size: int = ..., bits: int = ..., mode: str = ...
+    ) -> QuantizedLinear:
+        """Return a :obj:`QuantizedLinear` layer that approximates this layer."""
+
+class Bilinear(Module):
+    r"""Applies a bilinear transformation to the inputs.
+
+    Concretely:
+
+    .. math::
+
+        y_i = x_1^\top W_i x_2 + b_i
+
+    where:
+    :math:`W` has shape ``[output_dims, input1_dims, input2_dims]``, :math:`b` has shape ``[output_dims ]``,
+    and :math:`i` indexes the output dimension.
+
+    The values are initialized from the uniform distribution :math:`\mathcal{U}(-{k}, {k})`,
+    where :math:`k = \frac{1}{\sqrt{D_1}}` and :math:`D_1` is ``input1_dims``.
+
+    Args:
+        input1_dims (int): The dimensionality of the input1 features
+        input2_dims (int): The dimensionality of the input2 features
+        output_dims (int): The dimensionality of the output features
+        bias (bool, optional): If set to ``False`` then the layer will
+          not use a bias. Default is ``True``.
+    """
+    def __init__(
+        self, input1_dims: int, input2_dims: int, output_dims: int, bias: bool = ...
+    ) -> None: ...
+    def __call__(self, x1: mx.array, x2: mx.array) -> mx.array: ...

.mlx_typings/mlx/nn/layers/normalization.pyi

@@ -0,0 +1,194 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+import mlx.core as mx
+from base import Module
+
+class InstanceNorm(Module):
+    r"""Applies instance normalization [1] on the inputs.
+
+    Computes
+
+    .. math::
+
+        y = \frac{x - \mathrm{E}[x]}{ \sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta,
+
+    where :math:`\gamma` and :math:`\beta` are learned per feature dimension
+    parameters initialized at 1 and 0 respectively. Both are of size :attr:`dims`,
+    if :attr:`affine` is ``True``.
+
+    Args:
+        dims (int): The number of features of the input.
+        eps (float): A value added to the denominator for numerical stability. Default: ``1e-5``.
+        affine (bool): Default: ``False``.
+
+    Shape:
+      - Input: :math:`(..., C)` where :math:`C` is equal to :attr:`dims`.
+      - Output: Same shape as the input.
+
+    Examples:
+        >>> import mlx.core as mx
+        >>> import mlx.nn as nn
+        >>> x = mx.random.normal((8, 4, 4, 16))
+        >>> inorm = nn.InstanceNorm(dims=16)
+        >>> output = inorm(x)
+
+    References:
+        [1]: https://arxiv.org/abs/1607.08022
+    """
+    def __init__(self, dims: int, eps: float = ..., affine: bool = ...) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class LayerNorm(Module):
+    r"""Applies layer normalization [1] on the inputs.
+
+    Computes
+
+    .. math::
+
+        y = \frac{x - E[x]}{\sqrt{Var[x]} + \epsilon} \gamma + \beta,
+
+    where :math:`\gamma` and :math:`\beta` are learned per feature dimension
+    parameters initialized at 1 and 0 respectively.
+
+    [1]: https://arxiv.org/abs/1607.06450
+
+    Args:
+        dims (int): The feature dimension of the input to normalize over
+        eps (float): A small additive constant for numerical stability
+        affine (bool): If True learn an affine transform to apply after the
+            normalization
+        bias (bool): If True include a translation to the affine
+            transformation. If set to False the transformation is not really affine
+            just scaling.
+    """
+    def __init__(
+        self, dims: int, eps: float = ..., affine: bool = ..., bias: bool = ...
+    ) -> None: ...
+    def __call__(self, x) -> mx.array: ...
+
+class RMSNorm(Module):
+    r"""Applies Root Mean Square normalization [1] to the inputs.
+
+    Computes
+
+    ..  math::
+
+        y = \frac{x}{\sqrt{E[x^2] + \epsilon}} \gamma
+
+    where :math:`\gamma` is a learned per feature dimension parameter initialized at
+    1.
+
+    Note the accumulation for the mean is done in 32-bit precision.
+
+    [1]: https://arxiv.org/abs/1910.07467
+
+    Args:
+        dims (int): The feature dimension of the input to normalize over
+        eps (float): A small additive constant for numerical stability
+    """
+    def __init__(self, dims: int, eps: float = ...) -> None: ...
+    def __call__(self, x) -> mx.array: ...
+
+class GroupNorm(Module):
+    r"""Applies Group Normalization [1] to the inputs.
+
+    Computes the same normalization as layer norm, namely
+
+    .. math::
+
+        y = \frac{x - E[x]}{\sqrt{Var[x]} + \epsilon} \gamma + \beta,
+
+    where :math:`\gamma` and :math:`\beta` are learned per feature dimension
+    parameters initialized at 1 and 0 respectively. However, the mean and
+    variance are computed over the spatial dimensions and each group of
+    features. In particular, the input is split into num_groups across the
+    feature dimension.
+
+    The feature dimension is assumed to be the last dimension and the dimensions
+    that precede it (except the first) are considered the spatial dimensions.
+
+    [1]: https://arxiv.org/abs/1803.08494
+
+    Args:
+        num_groups (int): Number of groups to separate the features into
+        dims (int): The feature dimensions of the input to normalize over
+        eps (float): A small additive constant for numerical stability
+        affine (bool): If True learn an affine transform to apply after the
+            normalization.
+        pytorch_compatible (bool): If True perform the group normalization in
+            the same order/grouping as PyTorch.
+    """
+    def __init__(
+        self,
+        num_groups: int,
+        dims: int,
+        eps: float = ...,
+        affine: bool = ...,
+        pytorch_compatible: bool = ...,
+    ) -> None: ...
+    def __call__(self, x) -> mx.array: ...
+
+class BatchNorm(Module):
+    r"""Applies Batch Normalization over a 2D or 3D input.
+
+    Computes
+
+    .. math::
+
+        y = \frac{x - E[x]}{\sqrt{Var[x]} + \epsilon} \gamma + \beta,
+
+    where :math:`\gamma` and :math:`\beta` are learned per feature dimension
+    parameters initialized at 1 and 0 respectively.
+
+    The input shape is specified as ``NC`` or ``NLC``, where ``N`` is the
+    batch, ``C`` is the number of features or channels, and ``L`` is the
+    sequence length. The output has the same shape as the input. For
+    four-dimensional arrays, the shape is ``NHWC``, where ``H`` and ``W`` are
+    the height and width respectively.
+
+    For more information on Batch Normalization, see the original paper `Batch
+    Normalization: Accelerating Deep Network Training by Reducing Internal
+    Covariate Shift <https://arxiv.org/abs/1502.03167>`_.
+
+    Args:
+        num_features (int): The feature dimension to normalize over.
+        eps (float, optional): A small additive constant for numerical
+            stability. Default: ``1e-5``.
+        momentum (float, optional): The momentum for updating the running
+            mean and variance. Default: ``0.1``.
+        affine (bool, optional): If ``True``, apply a learned affine
+            transformation after the normalization. Default: ``True``.
+        track_running_stats (bool, optional): If ``True``, track the
+            running mean and variance. Default: ``True``.
+
+    Examples:
+        >>> import mlx.core as mx
+        >>> import mlx.nn as nn
+        >>> x = mx.random.normal((5, 4))
+        >>> bn = nn.BatchNorm(num_features=4, affine=True)
+        >>> output = bn(x)
+    """
+    def __init__(
+        self,
+        num_features: int,
+        eps: float = ...,
+        momentum: float = ...,
+        affine: bool = ...,
+        track_running_stats: bool = ...,
+    ) -> None: ...
+    def unfreeze(self, *args, **kwargs):  # -> None:
+        """Wrap unfreeze to make sure that running_mean and var are always
+        frozen parameters."""
+
+    def __call__(self, x: mx.array) -> mx.array:
+        """
+        Forward pass of BatchNorm.
+
+        Args:
+            x (array): Input tensor.
+
+        Returns:
+            array: Normalized output tensor.
+        """

.mlx_typings/mlx/nn/layers/pooling.pyi

@@ -0,0 +1,242 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Optional, Tuple, Union
+
+import mlx.core as mx
+from base import Module
+
+class _Pool(Module):
+    def __init__(
+        self, pooling_function, kernel_size, stride, padding, padding_value
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class _Pool1d(_Pool):
+    def __init__(
+        self,
+        pooling_function,
+        padding_value,
+        kernel_size: Union[int, Tuple[int]],
+        stride: Optional[Union[int, Tuple[int]]] = ...,
+        padding: Union[int, Tuple[int]] = ...,
+    ) -> None: ...
+
+class _Pool2d(_Pool):
+    def __init__(
+        self,
+        pooling_function,
+        padding_value,
+        kernel_size: Union[int, Tuple[int, int]],
+        stride: Optional[Union[int, Tuple[int, int]]] = ...,
+        padding: Optional[Union[int, Tuple[int, int]]] = ...,
+    ) -> None: ...
+
+class _Pool3d(_Pool):
+    def __init__(
+        self,
+        pooling_function,
+        padding_value,
+        kernel_size: Union[int, Tuple[int, int, int]],
+        stride: Optional[Union[int, Tuple[int, int, int]]] = ...,
+        padding: Optional[Union[int, Tuple[int, int, int]]] = ...,
+    ) -> None: ...
+
+class MaxPool1d(_Pool1d):
+    r"""Applies 1-dimensional max pooling.
+
+    Spatially downsamples the input by taking the maximum of a sliding window
+    of size ``kernel_size`` and sliding stride ``stride``.
+
+    Args:
+        kernel_size (int or tuple(int)): The size of the pooling window kernel.
+        stride (int or tuple(int), optional): The stride of the pooling window.
+            Default: ``kernel_size``.
+        padding (int or tuple(int), optional): How much negative infinity
+            padding to apply to the input. The padding amount is applied to
+            both sides of the spatial axis. Default: ``0``.
+
+    Examples:
+        >>> import mlx.core as mx
+        >>> import layers as nn
+        >>> x = mx.random.normal(shape=(4, 16, 5))
+        >>> pool = nn.MaxPool1d(kernel_size=2, stride=2)
+        >>> pool(x)
+    """
+    def __init__(
+        self,
+        kernel_size: Union[int, Tuple[int]],
+        stride: Optional[Union[int, Tuple[int]]] = ...,
+        padding: Union[int, Tuple[int]] = ...,
+    ) -> None: ...
+
+class AvgPool1d(_Pool1d):
+    r"""Applies 1-dimensional average pooling.
+
+    Spatially downsamples the input by taking the average of a sliding window
+    of size ``kernel_size`` and sliding stride ``stride``.
+
+    Args:
+        kernel_size (int or tuple(int)): The size of the pooling window kernel.
+        stride (int or tuple(int), optional): The stride of the pooling window.
+            Default: ``kernel_size``.
+        padding (int or tuple(int), optional): How much zero padding to apply to
+            the input. The padding amount is applied to both sides of the spatial
+            axis. Default: ``0``.
+
+    Examples:
+        >>> import mlx.core as mx
+        >>> import layers as nn
+        >>> x = mx.random.normal(shape=(4, 16, 5))
+        >>> pool = nn.AvgPool1d(kernel_size=2, stride=2)
+        >>> pool(x)
+    """
+    def __init__(
+        self,
+        kernel_size: Union[int, Tuple[int]],
+        stride: Optional[Union[int, Tuple[int]]] = ...,
+        padding: Union[int, Tuple[int]] = ...,
+    ) -> None: ...
+
+class MaxPool2d(_Pool2d):
+    r"""Applies 2-dimensional max pooling.
+
+    Spatially downsamples the input by taking the maximum of a sliding window
+    of size ``kernel_size`` and sliding stride ``stride``.
+
+    The parameters ``kernel_size``, ``stride``, and ``padding`` can either be:
+
+    * a single ``int`` -- in which case the same value is used for both the
+      height and width axis.
+    * a ``tuple`` of two ``int`` s -- in which case, the first ``int`` is
+      used for the height axis, the second ``int`` for the width axis.
+
+    Args:
+        kernel_size (int or tuple(int, int)): The size of the pooling window.
+        stride (int or tuple(int, int), optional): The stride of the pooling
+            window. Default: ``kernel_size``.
+        padding (int or tuple(int, int), optional): How much negative infinity
+            padding to apply to the input. The padding is applied on both sides
+            of the height and width axis. Default: ``0``.
+
+    Examples:
+        >>> import mlx.core as mx
+        >>> import layers as nn
+        >>> x = mx.random.normal(shape=(8, 32, 32, 4))
+        >>> pool = nn.MaxPool2d(kernel_size=2, stride=2)
+        >>> pool(x)
+    """
+    def __init__(
+        self,
+        kernel_size: Union[int, Tuple[int, int]],
+        stride: Optional[Union[int, Tuple[int, int]]] = ...,
+        padding: Optional[Union[int, Tuple[int, int]]] = ...,
+    ) -> None: ...
+
+class AvgPool2d(_Pool2d):
+    r"""Applies 2-dimensional average pooling.
+
+    Spatially downsamples the input by taking the average of a sliding window
+    of size ``kernel_size`` and sliding stride ``stride``.
+
+    The parameters ``kernel_size``, ``stride``, and ``padding`` can either be:
+
+    * a single ``int`` -- in which case the same value is used for both the
+      height and width axis.
+    * a ``tuple`` of two ``int`` s -- in which case, the first ``int`` is
+      used for the height axis, the second ``int`` for the width axis.
+
+    Args:
+        kernel_size (int or tuple(int, int)): The size of the pooling window.
+        stride (int or tuple(int, int), optional): The stride of the pooling
+            window. Default: ``kernel_size``.
+        padding (int or tuple(int, int), optional): How much zero
+            padding to apply to the input. The padding is applied on both sides
+            of the height and width axis. Default: ``0``.
+
+    Examples:
+        >>> import mlx.core as mx
+        >>> import layers as nn
+        >>> x = mx.random.normal(shape=(8, 32, 32, 4))
+        >>> pool = nn.AvgPool2d(kernel_size=2, stride=2)
+        >>> pool(x)
+    """
+    def __init__(
+        self,
+        kernel_size: Union[int, Tuple[int, int]],
+        stride: Optional[Union[int, Tuple[int, int]]] = ...,
+        padding: Optional[Union[int, Tuple[int, int]]] = ...,
+    ) -> None: ...
+
+class MaxPool3d(_Pool3d):
+    r"""Applies 3-dimensional max pooling.
+
+    Spatially downsamples the input by taking the maximum of a sliding window
+    of size ``kernel_size`` and sliding stride ``stride``.
+
+    The parameters ``kernel_size``, ``stride``, and ``padding`` can either be:
+
+    * a single ``int`` -- in which case the same value is used for the depth,
+      height, and width axis.
+    * a ``tuple`` of three ``int`` s -- in which case, the first ``int`` is used
+      for the depth axis, the second ``int`` for the height axis, and the third
+      ``int`` for the width axis.
+
+    Args:
+        kernel_size (int or tuple(int, int, int)): The size of the pooling window.
+        stride (int or tuple(int, int, int), optional): The stride of the pooling
+            window. Default: ``kernel_size``.
+        padding (int or tuple(int, int, int), optional): How much negative infinity
+            padding to apply to the input. The padding is applied on both sides
+            of the depth, height and width axis. Default: ``0``.
+
+    Examples:
+        >>> import mlx.core as mx
+        >>> import layers as nn
+        >>> x = mx.random.normal(shape=(8, 16, 32, 32, 4))
+        >>> pool = nn.MaxPool3d(kernel_size=2, stride=2)
+        >>> pool(x)
+    """
+    def __init__(
+        self,
+        kernel_size: Union[int, Tuple[int, int, int]],
+        stride: Optional[Union[int, Tuple[int, int, int]]] = ...,
+        padding: Optional[Union[int, Tuple[int, int, int]]] = ...,
+    ) -> None: ...
+
+class AvgPool3d(_Pool3d):
+    r"""Applies 3-dimensional average pooling.
+
+    Spatially downsamples the input by taking the average of a sliding window
+    of size ``kernel_size`` and sliding stride ``stride``.
+
+    The parameters ``kernel_size``, ``stride``, and ``padding`` can either be:
+
+    * a single ``int`` -- in which case the same value is used for the depth,
+      height, and width axis.
+    * a ``tuple`` of three ``int`` s -- in which case, the first ``int`` is used
+      for the depth axis, the second ``int`` for the height axis, and the third
+      ``int`` for the width axis.
+
+    Args:
+        kernel_size (int or tuple(int, int, int)): The size of the pooling window.
+        stride (int or tuple(int, int, int), optional): The stride of the pooling
+            window. Default: ``kernel_size``.
+        padding (int or tuple(int, int, int), optional): How much zero
+            padding to apply to the input. The padding is applied on both sides
+            of the depth, height and width axis. Default: ``0``.
+
+    Examples:
+        >>> import mlx.core as mx
+        >>> import layers as nn
+        >>> x = mx.random.normal(shape=(8, 16, 32, 32, 4))
+        >>> pool = nn.AvgPool3d(kernel_size=2, stride=2)
+        >>> pool(x)
+    """
+    def __init__(
+        self,
+        kernel_size: Union[int, Tuple[int, int, int]],
+        stride: Optional[Union[int, Tuple[int, int, int]]] = ...,
+        padding: Optional[Union[int, Tuple[int, int, int]]] = ...,
+    ) -> None: ...

.mlx_typings/mlx/nn/layers/positional_encoding.pyi

@@ -0,0 +1,80 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Optional
+
+import mlx.core as mx
+from base import Module
+
+class RoPE(Module):
+    """Implements the rotary positional encoding.
+
+    The traditional implementation rotates consecutive pairs of elements in the
+    feature dimension while the default implementation rotates pairs with
+    stride half the feature dimensions for efficiency.
+
+    For more details see `RoFormer: Enhanced Transformer with Rotary Position
+    Embedding <https://arxiv.org/abs/2104.09864>`_.
+
+    Args:
+        dims (int): The feature dimensions to be rotated. If the input feature
+            is larger than dims then the rest is left unchanged.
+        traditional (bool, optional): If set to ``True`` choose the traditional
+            implementation which is slightly less efficient. Default: ``False``.
+        base (float, optional): The base used to compute angular frequency for
+            each dimension in the positional encodings. Default: ``10000``.
+        scale (float, optional): The scale used to scale the positions. Default: ``1.0``.
+    """
+    def __init__(
+        self, dims: int, traditional: bool = ..., base: float = ..., scale: float = ...
+    ) -> None: ...
+    def __call__(self, x, offset: int = ...) -> mx.array: ...
+
+class SinusoidalPositionalEncoding(Module):
+    r"""Implements sinusoidal positional encoding.
+
+    For more details see the paper `Attention Is All You Need
+    <https://arxiv.org/abs/1706.03762>`_.
+
+    Args:
+        dims (int): The dimensionality of the resulting positional embeddings.
+        min_freq (float, optional): The minimum frequency expected. Default:
+            ``0.0001``.
+        max_freq (float, optional): The maximum frequency expected. Default:
+            ``1``.
+        scale (float, optional): A multiplicative scale for the embeddings.
+            Default: ``sqrt(2/dims)``.
+        cos_first (bool, optional): If ``True`` embed using ``[cos(x); sin(x)]``
+            instead of the reverse. Default: ``False``.
+        full_turns (bool, optional): If ``True`` multiply the frequencies with
+            :math:`2\pi`. Default: ``False``.
+    """
+    def __init__(
+        self,
+        dims: int,
+        min_freq: float = ...,
+        max_freq: float = ...,
+        scale: Optional[float] = ...,
+        cos_first: bool = ...,
+        full_turns: bool = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class ALiBi(Module):
+    _alibi_mask_key = ...
+    _alibi_mask = ...
+    @classmethod
+    def create_alibi_matrix(
+        cls,
+        q_sequence_length: int,
+        k_sequence_length: int,
+        num_heads: int,
+        offset: int,
+        dtype=...,
+    ) -> mx.array | None: ...
+    @staticmethod
+    def create_alibi_slope(num_heads: int) -> mx.array: ...
+    def __call__(
+        self, attention_scores: mx.array, offset=..., mask=...
+    ) -> mx.array: ...

.mlx_typings/mlx/nn/layers/quantized.pyi

@@ -0,0 +1,125 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Callable, Optional, Union
+
+import mlx.core as mx
+from base import Module
+
+def quantize(
+    model: Module,
+    group_size: int = ...,
+    bits: int = ...,
+    *,
+    mode: str = ...,
+    class_predicate: Optional[Callable[[str, Module], Union[bool, dict]]] = ...,
+):  # -> None:
+    """Quantize the sub-modules of a module according to a predicate.
+
+    By default all layers that define a ``to_quantized(group_size, bits)``
+    method will be quantized. Both :obj:`Linear` and :obj:`Embedding` layers
+    will be quantized. Note also, the module is updated in-place.
+
+    Args:
+        model (Module): The model whose leaf modules may be quantized.
+        group_size (int): The quantization group size (see
+           :func:`mlx.core.quantize`). Default: ``64``.
+        bits (int): The number of bits per parameter (see
+           :func:`mlx.core.quantize`). Default: ``4``.
+        mode (str): The quantization method to use (see
+           :func:`mlx.core.quantize`). Default: ``"affine"``.
+        class_predicate (Optional[Callable]): A callable which receives the
+          :obj:`Module` path and :obj:`Module` itself and returns ``True`` or a
+          dict of params for `to_quantized` if it should be quantized and
+          ``False`` otherwise. If ``None``, then all layers that define a
+          ``to_quantized(group_size, bits)`` method are quantized.
+          Default: ``None``.
+    """
+
+class QuantizedEmbedding(Module):
+    """The same as :obj:`Embedding` but with a  quantized weight matrix.
+
+    :obj:`QuantizedEmbedding` also provides a :meth:`from_embedding`
+    classmethod to convert embedding layers to :obj:`QuantizedEmbedding`
+    layers.
+
+    Args:
+        num_embeddings (int): How many possible discrete tokens can we embed.
+           Usually called the vocabulary size.
+        dims (int): The dimensionality of the embeddings.
+        group_size (int, optional): The group size to use for the quantized
+            weight. See :func:`~mlx.core.quantize`. Default: ``64``.
+        bits (int, optional): The bit width to use for the quantized weight.
+            See :func:`~mlx.core.quantize`. Default: ``4``.
+        mode (str): The quantization method to use (see
+           :func:`mlx.core.quantize`). Default: ``"affine"``.
+    """
+    def __init__(
+        self,
+        num_embeddings: int,
+        dims: int,
+        group_size: int = ...,
+        bits: int = ...,
+        mode: str = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+    def as_linear(self, x: mx.array) -> mx.array:
+        """
+        Call the quantized embedding layer as a quantized linear layer.
+
+        Use this for example when input embedding and output projection
+        weights are tied.
+        """
+
+    @classmethod
+    def from_embedding(
+        cls,
+        embedding_layer: Module,
+        group_size: int = ...,
+        bits: int = ...,
+        mode: str = ...,
+    ) -> QuantizedEmbedding:
+        """Create a :obj:`QuantizedEmbedding` layer from an :obj:`Embedding` layer."""
+
+class QuantizedLinear(Module):
+    """Applies an affine transformation to the input using a quantized weight matrix.
+
+    It is the quantized equivalent of :class:`Linear`. For now its
+    parameters are frozen and will not be included in any gradient computation
+    but this will probably change in the future.
+
+    :obj:`QuantizedLinear` also provides a classmethod :meth:`from_linear` to
+    convert linear layers to :obj:`QuantizedLinear` layers.
+
+    Args:
+        input_dims (int): The dimensionality of the input features.
+        output_dims (int): The dimensionality of the output features.
+        bias (bool, optional): If set to ``False`` then the layer will not use
+            a bias. Default: ``True``.
+        group_size (int, optional): The group size to use for the quantized
+            weight. See :func:`~mlx.core.quantize`. Default: ``64``.
+        bits (int, optional): The bit width to use for the quantized weight.
+            See :func:`~mlx.core.quantize`. Default: ``4``.
+        mode (str): The quantization method to use (see
+           :func:`mlx.core.quantize`). Default: ``"affine"``.
+    """
+    def __init__(
+        self,
+        input_dims: int,
+        output_dims: int,
+        bias: bool = ...,
+        group_size: int = ...,
+        bits: int = ...,
+        mode: str = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+    @classmethod
+    def from_linear(
+        cls,
+        linear_layer: Module,
+        group_size: int = ...,
+        bits: int = ...,
+        mode: str = ...,
+    ) -> QuantizedLinear:
+        """Create a :obj:`QuantizedLinear` layer from a :obj:`Linear` layer."""

.mlx_typings/mlx/nn/layers/recurrent.pyi

@@ -0,0 +1,113 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Callable, Optional
+
+import mlx.core as mx
+from base import Module
+
+class RNN(Module):
+    r"""An Elman recurrent layer.
+
+    The input is a sequence of shape ``NLD`` or ``LD`` where:
+
+    * ``N`` is the optional batch dimension
+    * ``L`` is the sequence length
+    * ``D`` is the input's feature dimension
+
+    Concretely, for each element along the sequence length axis, this
+    layer applies the function:
+
+    .. math::
+
+        h_{t + 1} = \text{tanh} (W_{ih}x_t + W_{hh}h_t + b)
+
+    The hidden state :math:`h` has shape ``NH`` or ``H``, depending on
+    whether the input is batched or not. Returns the hidden state at each
+    time step, of shape ``NLH`` or ``LH``.
+
+    Args:
+        input_size (int): Dimension of the input, ``D``.
+        hidden_size (int): Dimension of the hidden state, ``H``.
+        bias (bool, optional): Whether to use a bias. Default: ``True``.
+        nonlinearity (callable, optional): Non-linearity to use. If ``None``,
+            then func:`tanh` is used. Default: ``None``.
+    """
+    def __init__(
+        self,
+        input_size: int,
+        hidden_size: int,
+        bias: bool = ...,
+        nonlinearity: Optional[Callable] = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array, hidden=...) -> mx.array: ...
+
+class GRU(Module):
+    r"""A gated recurrent unit (GRU) RNN layer.
+
+    The input has shape ``NLD`` or ``LD`` where:
+
+    * ``N`` is the optional batch dimension
+    * ``L`` is the sequence length
+    * ``D`` is the input's feature dimension
+
+    Concretely, for each element of the sequence, this layer computes:
+
+    .. math::
+
+        \begin{aligned}
+        r_t &= \sigma (W_{xr}x_t + W_{hr}h_t + b_{r}) \\
+        z_t &= \sigma (W_{xz}x_t + W_{hz}h_t + b_{z}) \\
+        n_t &= \text{tanh}(W_{xn}x_t + b_{n} + r_t \odot (W_{hn}h_t + b_{hn})) \\
+        h_{t + 1} &= (1 - z_t) \odot n_t + z_t \odot h_t
+        \end{aligned}
+
+    The hidden state :math:`h` has shape ``NH`` or ``H`` depending on
+    whether the input is batched or not. Returns the hidden state at each
+    time step of shape ``NLH`` or ``LH``.
+
+    Args:
+        input_size (int): Dimension of the input, ``D``.
+        hidden_size (int): Dimension of the hidden state, ``H``.
+        bias (bool): Whether to use biases or not. Default: ``True``.
+    """
+    def __init__(self, input_size: int, hidden_size: int, bias: bool = ...) -> None: ...
+    def __call__(self, x: mx.array, hidden=...) -> mx.array: ...
+
+class LSTM(Module):
+    r"""An LSTM recurrent layer.
+
+    The input has shape ``NLD`` or ``LD`` where:
+
+    * ``N`` is the optional batch dimension
+    * ``L`` is the sequence length
+    * ``D`` is the input's feature dimension
+
+    Concretely, for each element of the sequence, this layer computes:
+
+    .. math::
+        \begin{aligned}
+        i_t &= \sigma (W_{xi}x_t + W_{hi}h_t + b_{i}) \\
+        f_t &= \sigma (W_{xf}x_t + W_{hf}h_t + b_{f}) \\
+        g_t &= \text{tanh} (W_{xg}x_t + W_{hg}h_t + b_{g}) \\
+        o_t &= \sigma (W_{xo}x_t + W_{ho}h_t + b_{o}) \\
+        c_{t + 1} &= f_t \odot c_t + i_t \odot g_t \\
+        h_{t + 1} &= o_t \text{tanh}(c_{t + 1})
+        \end{aligned}
+
+    The hidden state :math:`h` and cell state :math:`c` have shape ``NH``
+    or ``H``, depending on whether the input is batched or not.
+
+    The layer returns two arrays, the hidden state and the cell state at
+    each time step, both of shape ``NLH`` or ``LH``.
+
+    Args:
+        input_size (int): Dimension of the input, ``D``.
+        hidden_size (int): Dimension of the hidden state, ``H``.
+        bias (bool): Whether to use biases or not. Default: ``True``.
+    """
+    def __init__(self, input_size: int, hidden_size: int, bias: bool = ...) -> None: ...
+    def __call__(
+        self, x: mx.array, hidden=..., cell=...
+    ) -> tuple[mx.array, mx.array]: ...

.mlx_typings/mlx/nn/layers/transformer.pyi

@@ -0,0 +1,168 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Any, Callable, Optional
+
+import mlx.core as mx
+from base import Module
+
+class MultiHeadAttention(Module):
+    """Implements the scaled dot product attention with multiple heads.
+
+    Given inputs for queries, keys and values the ``MultiHeadAttention``
+    produces new values by aggregating information from the input values
+    according to the similarities of the input queries and keys.
+
+    All inputs as well as the output are linearly projected without biases by
+    default.
+
+    ``MultiHeadAttention`` also takes an optional additive attention mask that
+    should be broadcastable with ``(batch, num_heads, # queries, # keys)``. The
+    mask should have ``-inf`` or very large negative numbers at the positions
+    that should *not* be attended to.
+
+    Args:
+        dims (int): The model dimensions. This is also the default
+            value for the queries, keys, values, and the output.
+        num_heads (int): The number of attention heads to use.
+        query_input_dims (int, optional): The input dimensions of the queries.
+            Default: ``dims``.
+        key_input_dims (int, optional): The input dimensions of the keys.
+            Default: ``dims``.
+        value_input_dims (int, optional): The input dimensions of the values.
+            Default: ``key_input_dims``.
+        value_dims (int, optional): The dimensions of the values after the
+            projection. Default: ``dims``.
+        value_output_dims (int, optional): The dimensions the new values will
+            be projected to. Default: ``dims``.
+        bias (bool, optional): Whether or not to use a bias in the projections.
+            Default: ``False``.
+    """
+    def __init__(
+        self,
+        dims: int,
+        num_heads: int,
+        query_input_dims: Optional[int] = ...,
+        key_input_dims: Optional[int] = ...,
+        value_input_dims: Optional[int] = ...,
+        value_dims: Optional[int] = ...,
+        value_output_dims: Optional[int] = ...,
+        bias: bool = ...,
+    ) -> None: ...
+    def __call__(
+        self, queries: mx.array, keys: mx.array, values: mx.array, mask: mx.array = ...
+    ) -> mx.array: ...
+    @staticmethod
+    def create_additive_causal_mask(N: int, dtype: mx.Dtype = ...) -> mx.array: ...
+
+class TransformerEncoderLayer(Module):
+    def __init__(
+        self,
+        dims: int,
+        num_heads: int,
+        mlp_dims: Optional[int] = ...,
+        dropout: float = ...,
+        activation: Callable[[Any], Any] = ...,
+        norm_first: bool = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array, mask: mx.array) -> mx.array: ...
+
+class TransformerEncoder(Module):
+    def __init__(
+        self,
+        num_layers: int,
+        dims: int,
+        num_heads: int,
+        mlp_dims: Optional[int] = ...,
+        dropout: float = ...,
+        activation=...,
+        norm_first: bool = ...,
+        checkpoint: bool = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array, mask: mx.array) -> mx.array: ...
+
+class TransformerDecoderLayer(Module):
+    def __init__(
+        self,
+        dims: int,
+        num_heads: int,
+        mlp_dims: Optional[int] = ...,
+        dropout: float = ...,
+        activation: Callable[[Any], Any] = ...,
+        norm_first: bool = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array, memory, x_mask, memory_mask) -> mx.array: ...
+
+class TransformerDecoder(Module):
+    def __init__(
+        self,
+        num_layers: int,
+        dims: int,
+        num_heads: int,
+        mlp_dims: Optional[int] = ...,
+        dropout: float = ...,
+        activation=...,
+        norm_first: bool = ...,
+        checkpoint: bool = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array, memory, x_mask, memory_mask) -> mx.array: ...
+
+class Transformer(Module):
+    """
+    Implements a standard Transformer model.
+
+    The implementation is based on `Attention Is All You Need
+    <https://arxiv.org/abs/1706.03762>`_.
+
+    The Transformer model contains an encoder and a decoder. The encoder
+    processes the input sequence and the decoder generates the output sequence.
+    The interaction between encoder and decoder happens through the attention
+    mechanism.
+
+    Args:
+        dims (int, optional): The number of expected features in the
+            encoder/decoder inputs. Default: ``512``.
+        num_heads (int, optional): The number of attention heads. Default:
+            ``8``.
+        num_encoder_layers (int, optional): The number of encoder layers in the
+            Transformer encoder. Default: ``6``.
+        num_decoder_layers (int, optional): The number of decoder layers in the
+            Transformer decoder. Default: ``6``.
+        mlp_dims (int, optional): The hidden dimension of the MLP block in each
+            Transformer layer. Defaults to ``4*dims`` if not provided. Default:
+            ``None``.
+        dropout (float, optional): The dropout value for the Transformer
+            encoder and decoder. Dropout is used after each attention layer and
+            the activation in the MLP layer. Default: ``0.0``.
+        activation (function, optional): the activation function for the MLP
+            hidden layer. Default: :func:`relu`.
+        custom_encoder (nn.Module, optional): A custom encoder to replace the
+            standard Transformer encoder. Default: ``None``.
+        custom_decoder (nn.Module, optional): A custom decoder to replace the
+            standard Transformer decoder. Default: ``None``.
+        norm_first (bool, optional): if ``True``, encoder and decoder layers
+            will perform layer normalization before attention and MLP
+            operations, otherwise after. Default: ``True``.
+        checkpoint (bool, optional): if ``True`` perform gradient checkpointing
+            to reduce the memory usage at the expense of more computation.
+            Default: ``False``.
+    """
+    def __init__(
+        self,
+        dims: int = ...,
+        num_heads: int = ...,
+        num_encoder_layers: int = ...,
+        num_decoder_layers: int = ...,
+        mlp_dims: Optional[int] = ...,
+        dropout: float = ...,
+        activation: Callable[[Any], Any] = ...,
+        custom_encoder: Optional[Any] = ...,
+        custom_decoder: Optional[Any] = ...,
+        norm_first: bool = ...,
+        checkpoint: bool = ...,
+    ) -> None: ...
+    def __call__(
+        self, src, tgt, src_mask, tgt_mask, memory_mask
+    ) -> mx.array:  # -> array | Any:
+        ...

.mlx_typings/mlx/nn/layers/upsample.pyi

@@ -0,0 +1,87 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Literal, Tuple, Union
+
+import mlx.core as mx
+from base import Module
+
+def upsample_nearest(x: mx.array, scale_factor: Tuple) -> mx.array: ...
+def upsample_linear(
+    x: mx.array, scale_factor: Tuple, align_corners: bool = ...
+):  # -> int:
+    ...
+def upsample_cubic(
+    x: mx.array, scale_factor: Tuple, align_corners: bool = ...
+):  # -> int:
+    ...
+
+class Upsample(Module):
+    r"""Upsample the input signal spatially.
+
+    The spatial dimensions are by convention dimensions ``1`` to ``x.ndim -
+    2``. The first is the batch dimension and the last is the feature
+    dimension.
+
+    For example, an audio signal would be 3D with 1 spatial dimension, an image
+    4D with 2 and so on and so forth.
+
+    There are three upsampling algorithms implemented nearest neighbor upsampling,
+    linear interpolation, and cubic interpolation. All can be applied to any number
+    of spatial dimensions. The linear interpolation will be bilinear, trilinear etc
+    when applied to more than one spatial dimension. And cubic interpolation will be
+    bicubic when there are 2 spatial dimensions.
+
+    .. note::
+       When using one of the linear or cubic interpolation modes the ``align_corners``
+       argument changes how the corners are treated in the input image. If
+       ``align_corners=True`` then the top and left edge of the input and
+       output will be matching as will the bottom right edge.
+
+    Parameters:
+        scale_factor (float or tuple): The multiplier for the spatial size.
+            If a ``float`` is provided, it is the multiplier for all spatial dimensions.
+            Otherwise, the number of scale factors provided must match the
+            number of spatial dimensions.
+        mode (str, optional): The upsampling algorithm, either ``"nearest"``,
+            ``"linear"`` or ``"cubic"``. Default: ``"nearest"``.
+        align_corners (bool, optional): Changes the way the corners are treated
+            during ``"linear"`` and ``"cubic"`` upsampling.  See the note above and the
+            examples below for more details.  Default: ``False``.
+
+    Examples:
+        >>> import mlx.core as mx
+        >>> import mlx.nn as nn
+        >>> x = mx.arange(1, 5).reshape((1, 2, 2, 1))
+        >>> x
+        array([[[[1],
+                 [2]],
+                [[3],
+                 [4]]]], dtype=int32)
+        >>> n = nn.Upsample(scale_factor=2, mode='nearest')
+        >>> n(x).squeeze()
+        array([[1, 1, 2, 2],
+               [1, 1, 2, 2],
+               [3, 3, 4, 4],
+               [3, 3, 4, 4]], dtype=int32)
+        >>> b = nn.Upsample(scale_factor=2, mode='linear')
+        >>> b(x).squeeze()
+        array([[1, 1.25, 1.75, 2],
+               [1.5, 1.75, 2.25, 2.5],
+               [2.5, 2.75, 3.25, 3.5],
+               [3, 3.25, 3.75, 4]], dtype=float32)
+        >>> b = nn.Upsample(scale_factor=2, mode='linear', align_corners=True)
+        >>> b(x).squeeze()
+        array([[1, 1.33333, 1.66667, 2],
+               [1.66667, 2, 2.33333, 2.66667],
+               [2.33333, 2.66667, 3, 3.33333],
+               [3, 3.33333, 3.66667, 4]], dtype=float32)
+    """
+    def __init__(
+        self,
+        scale_factor: Union[float, Tuple],
+        mode: Literal["nearest", "linear", "cubic"] = ...,
+        align_corners: bool = ...,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...

.mlx_typings/mlx/nn/losses.pyi

@@ -0,0 +1,419 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Literal, Optional
+
+import mlx.core as mx
+
+Reduction = Literal["none", "mean", "sum"]
+
+def cross_entropy(
+    logits: mx.array,
+    targets: mx.array,
+    weights: Optional[mx.array] = ...,
+    axis: int = ...,
+    label_smoothing: float = ...,
+    reduction: Reduction = ...,
+) -> mx.array:
+    """
+    Computes the cross entropy loss.
+
+    Args:
+        logits (array): The unnormalized logits.
+        targets (array): The ground truth values. These can be class indices or
+            probabilities for each class. If the ``targets`` are class indices,
+            then ``targets`` shape should match the ``logits`` shape with
+            the ``axis`` dimension removed. If the ``targets`` are probabilities
+            (or one-hot encoded), then the ``targets`` shape should be the same as
+            the ``logits`` shape.
+        weights (array, optional): Optional weights for each target. Default: ``None``.
+        axis (int, optional): The axis over which to compute softmax. Default: ``-1``.
+        label_smoothing (float, optional): Label smoothing factor. Default: ``0``.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+            ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'none'``.
+
+    Returns:
+        array: The computed cross entropy loss.
+
+    Examples:
+        >>> import mlx.core as mx
+        >>> import mlx.nn as nn
+        >>>
+        >>> # Class indices as targets
+        >>> logits = mx.array([[2.0, -1.0], [-1.0, 2.0]])
+        >>> targets = mx.array([0, 1])
+        >>> nn.losses.cross_entropy(logits, targets)
+        array([0.0485873, 0.0485873], dtype=float32)
+        >>>
+        >>> # Probabilities (or one-hot vectors) as targets
+        >>> logits = mx.array([[2.0, -1.0], [-1.0, 2.0]])
+        >>> targets = mx.array([[0.9, 0.1], [0.1, 0.9]])
+        >>> nn.losses.cross_entropy(logits, targets)
+        array([0.348587, 0.348587], dtype=float32)
+    """
+
+def binary_cross_entropy(
+    inputs: mx.array,
+    targets: mx.array,
+    weights: Optional[mx.array] = ...,
+    with_logits: bool = ...,
+    reduction: Reduction = ...,
+) -> mx.array:
+    """
+    Computes the binary cross entropy loss.
+
+    By default, this function takes the pre-sigmoid logits, which results in a faster
+    and more precise loss. For improved numerical stability when ``with_logits=False``,
+    the loss calculation clips the input probabilities (in log-space) to a minimum value
+    of ``-100``.
+
+    Args:
+        inputs (array): The predicted values. If ``with_logits`` is ``True``, then
+            ``inputs`` are unnormalized logits. Otherwise, ``inputs`` are probabilities.
+        targets (array): The binary target values in {0, 1}.
+        with_logits (bool, optional): Whether ``inputs`` are logits. Default: ``True``.
+        weights (array, optional): Optional weights for each target. Default: ``None``.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'mean'``.
+
+    Returns:
+        array: The computed binary cross entropy loss.
+    Examples:
+        >>> import mlx.core as mx
+        >>> import mlx.nn as nn
+
+        >>> logits = mx.array([0.105361, 0.223144, 1.20397, 0.916291])
+        >>> targets = mx.array([0, 0, 1, 1])
+        >>> loss = nn.losses.binary_cross_entropy(logits, targets, reduction="mean")
+        >>> loss
+        array(0.539245, dtype=float32)
+
+        >>> probs = mx.array([0.1, 0.1, 0.4, 0.4])
+        >>> targets = mx.array([0, 0, 1, 1])
+        >>> loss = nn.losses.binary_cross_entropy(probs, targets, with_logits=False, reduction="mean")
+        >>> loss
+        array(0.510826, dtype=float32)
+    """
+
+def l1_loss(
+    predictions: mx.array, targets: mx.array, reduction: Reduction = ...
+) -> mx.array:
+    """
+    Computes the L1 loss.
+
+    Args:
+        predictions (array): The predicted values.
+        targets (array): The target values.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'mean'``.
+
+    Returns:
+        array: The computed L1 loss.
+    """
+
+def mse_loss(
+    predictions: mx.array, targets: mx.array, reduction: Reduction = ...
+) -> mx.array:
+    """
+    Computes the mean squared error loss.
+
+    Args:
+        predictions (array): The predicted values.
+        targets (array): The target values.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'mean'``.
+
+    Returns:
+        array: The computed mean squared error loss.
+    """
+
+def nll_loss(
+    inputs: mx.array, targets: mx.array, axis: int = ..., reduction: Reduction = ...
+) -> mx.array:
+    """
+    Computes the negative log likelihood loss.
+
+    Args:
+        inputs (array): The predicted distribution in log space.
+        targets (array): The target values.
+        axis (int, optional): The distribution axis. Default: ``-1``.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'none'``.
+
+    Returns:
+        array: The computed NLL loss.
+    """
+
+def gaussian_nll_loss(
+    inputs: mx.array,
+    targets: mx.array,
+    vars: mx.array,
+    full: bool = ...,
+    eps: float = ...,
+    reduction: Reduction = ...,
+) -> mx.array:
+    r"""
+    Computes the negative log likelihood loss for a Gaussian distribution.
+
+    The loss is given by:
+
+    .. math::
+        \frac{1}{2}\left(\log\left(\max\left(\text{vars},
+        \ \epsilon\right)\right) + \frac{\left(\text{inputs} - \text{targets} \right)^2}
+        {\max\left(\text{vars}, \ \epsilon \right)}\right) + \text{const.}
+
+    where ``inputs`` are the predicted means and ``vars`` are the the
+    predicted variances.
+
+    Args:
+        inputs (array): The predicted expectation of the Gaussian distribution.
+        targets (array): The target values (samples from the Gaussian distribution).
+        vars (array): The predicted variance of the Gaussian distribution.
+        full (bool, optional): Whether to include the constant term in the loss calculation.
+            Default: ``False``.
+        eps (float, optional): Small positive constant for numerical stability.
+            Default: ``1e-6``.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'none'``.
+
+    Returns:
+        array: The Gaussian NLL loss.
+    """
+
+def kl_div_loss(
+    inputs: mx.array, targets: mx.array, axis: int = ..., reduction: Reduction = ...
+) -> mx.array:
+    """
+    Computes the Kullback-Leibler divergence loss.
+
+    Computes the following when ``reduction == 'none'``:
+
+    .. code-block:: python
+
+        mx.exp(targets) * (targets - inputs).sum(axis)
+
+    Args:
+        inputs (array): Log probabilities for the predicted distribution.
+        targets (array): Log probabilities for the target distribution.
+        axis (int, optional): The distribution axis. Default: ``-1``.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'none'``.
+
+    Returns:
+        array: The computed Kullback-Leibler divergence loss.
+    """
+
+def smooth_l1_loss(
+    predictions: mx.array,
+    targets: mx.array,
+    beta: float = ...,
+    reduction: Reduction = ...,
+) -> mx.array:
+    r"""
+    Computes the smooth L1 loss.
+
+    The smooth L1 loss is a variant of the L1 loss which replaces the absolute
+    difference with a squared difference when the absolute difference is less
+    than ``beta``.
+
+    The formula for the smooth L1 Loss is:
+
+    .. math::
+
+      l = \begin{cases}
+            0.5 (x - y)^2 / \beta, & \text{if } |x - y| < \beta \\
+            |x - y| - 0.5 \beta, & \text{otherwise}
+          \end{cases}
+
+    Args:
+        predictions (array): Predicted values.
+        targets (array): Ground truth values.
+        beta (float, optional): The threshold after which the loss changes
+          from the squared to the absolute difference. Default: ``1.0``.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'mean'``.
+
+    Returns:
+        array: The computed smooth L1 loss.
+    """
+
+def triplet_loss(
+    anchors: mx.array,
+    positives: mx.array,
+    negatives: mx.array,
+    axis: int = ...,
+    p: int = ...,
+    margin: float = ...,
+    eps: float = ...,
+    reduction: Reduction = ...,
+) -> mx.array:
+    r"""
+    Computes the triplet loss for a set of anchor, positive, and negative samples.
+    Margin is represented with alpha in the math section.
+
+    .. math::
+
+       \max\left(\|A - P\|_p - \|A - N\|_p + \alpha, 0\right)
+
+    Args:
+        anchors (array): The anchor samples.
+        positives (array): The positive samples.
+        negatives (array): The negative samples.
+        axis (int, optional): The distribution axis. Default: ``-1``.
+        p (int, optional): The norm degree for pairwise distance. Default: ``2``.
+        margin (float, optional): Margin for the triplet loss. Defaults to ``1.0``.
+        eps (float, optional): Small positive constant to prevent numerical instability. Defaults to ``1e-6``.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'none'``.
+
+    Returns:
+        array: Computed triplet loss. If reduction is "none", returns a tensor of the same shape as input;
+                  if reduction is "mean" or "sum", returns a scalar tensor.
+    """
+
+def hinge_loss(
+    inputs: mx.array, targets: mx.array, reduction: Reduction = ...
+) -> mx.array:
+    r"""
+    Computes the hinge loss between inputs and targets.
+
+    .. math::
+
+       \text{hinge}(y, y_{\text{pred}}) = \max(0, 1 - y \cdot y_{\text{pred}})
+
+
+    Args:
+        inputs (array): The predicted values.
+        targets (array): The target values. They should be -1 or 1.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'none'``.
+
+    Returns:
+        array: The computed hinge loss.
+    """
+
+def huber_loss(
+    inputs: mx.array, targets: mx.array, delta: float = ..., reduction: Reduction = ...
+) -> mx.array:
+    r"""
+    Computes the Huber loss between inputs and targets.
+
+    .. math::
+
+        l_{\delta}(a) =
+        \left\{ \begin{array}{ll}
+            \frac{1}{2} a^2 & \text{for } |a| \leq \delta, \\
+            \delta \left( |a| - \frac{1}{2} \delta \right) & \text{otherwise.}
+        \end{array} \right.
+
+    Args:
+        inputs (array): The predicted values.
+        targets (array): The target values.
+        delta (float, optional): The threshold at which to change between L1 and L2 loss.
+          Default: ``1.0``.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'none'``.
+
+    Returns:
+        array: The computed Huber loss.
+    """
+
+def log_cosh_loss(
+    inputs: mx.array, targets: mx.array, reduction: Reduction = ...
+) -> mx.array:
+    r"""
+    Computes the log cosh loss between inputs and targets.
+
+    Logcosh acts like L2 loss for small errors, ensuring stable gradients,
+    and like the L1 loss for large errors, reducing sensitivity to outliers. This
+    dual behavior offers a balanced, robust approach for regression tasks.
+
+    .. math::
+
+       \text{logcosh}(y_{\text{true}}, y_{\text{pred}}) =
+            \frac{1}{n} \sum_{i=1}^{n}
+            \log(\cosh(y_{\text{pred}}^{(i)} - y_{\text{true}}^{(i)}))
+
+
+    Args:
+        inputs (array): The predicted values.
+        targets (array): The target values.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'none'``.
+
+    Returns:
+        array: The computed log cosh loss.
+    """
+
+def cosine_similarity_loss(
+    x1: mx.array,
+    x2: mx.array,
+    axis: int = ...,
+    eps: float = ...,
+    reduction: Reduction = ...,
+) -> mx.array:
+    r"""
+    Computes the cosine similarity between the two inputs.
+
+    The cosine similarity loss is given by
+
+    .. math::
+
+        \frac{x_1 \cdot x_2}{\max(\|x_1\|  \cdot \|x_2\|, \epsilon)}
+
+    Args:
+        x1 (mx.array): The first set of inputs.
+        x2 (mx.array): The second set of inputs.
+        axis (int, optional): The embedding axis. Default: ``1``.
+        eps (float, optional): The minimum value of the denominator used for
+          numerical stability. Default: ``1e-8``.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+          ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'none'``.
+
+    Returns:
+        mx.array: The computed cosine similarity loss.
+    """
+
+def margin_ranking_loss(
+    inputs1: mx.array,
+    inputs2: mx.array,
+    targets: mx.array,
+    margin: float = ...,
+    reduction: Reduction = ...,
+) -> mx.array:
+    r"""
+    Calculate the margin ranking loss that loss given inputs :math:`x_1`, :math:`x_2` and a label
+    :math:`y` (containing 1 or -1).
+
+    The loss is given by:
+
+    .. math::
+        \text{loss} = \max (0, -y * (x_1 - x_2) + \text{margin})
+
+    Where :math:`y` represents ``targets``, :math:`x_1` represents ``inputs1`` and :math:`x_2`
+    represents ``inputs2``.
+
+    Args:
+        inputs1 (array): Scores for the first input.
+        inputs2 (array): Scores for the second input.
+        targets (array): Labels indicating whether samples in ``inputs1`` should be ranked higher
+            than samples in ``inputs2``. Values should be 1 or -1.
+        margin (float, optional): The margin by which the scores should be separated.
+            Default: ``0.0``.
+        reduction (str, optional): Specifies the reduction to apply to the output:
+            ``'none'`` | ``'mean'`` | ``'sum'``. Default: ``'none'``.
+
+    Returns:
+        array: The computed margin ranking loss.
+
+    Examples:
+        >>> import mlx.core as mx
+        >>> import mlx.nn as nn
+        >>> targets = mx.array([1, 1, -1])
+        >>> inputs1 = mx.array([-0.573409, -0.765166, -0.0638])
+        >>> inputs2 = mx.array([0.75596, 0.225763, 0.256995])
+        >>> loss = nn.losses.margin_ranking_loss(inputs1, inputs2, targets)
+        >>> loss
+        array(0.773433, dtype=float32)
+    """

.mlx_typings/mlx/nn/utils.pyi

@@ -0,0 +1,73 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Any, Callable, Optional
+
+import mlx.core as mx
+
+from .layers.base import Module
+
+def value_and_grad(
+    model: Module, fn: Callable
+):  # -> _Wrapped[..., Any, ..., tuple[Any, Any]]:
+    """Transform the passed function ``fn`` to a function that computes the
+    gradients of ``fn`` wrt the model's trainable parameters and also its
+    value.
+
+    Args:
+        model (Module): The model whose trainable parameters to compute
+                               gradients for
+        fn (Callable): The scalar function to compute gradients for
+
+    Returns:
+        A callable that returns the value of ``fn`` and the gradients wrt the
+        trainable parameters of ``model``
+    """
+
+def checkpoint(
+    module: Module, fn: Optional[Callable] = ...
+):  # -> _Wrapped[..., Any, ..., Any]:
+    """Transform the passed callable to one that performs gradient
+    checkpointing with respect to the trainable parameters of the module (and
+    the callable's inputs).
+
+    Args:
+        module (Module): The module for whose parameters we will be
+            performing gradient checkpointing.
+        fn (Callable, optional): The function to checkpoint. If not provided it
+            defaults to the provided module.
+
+    Returns:
+        A callable that saves the inputs and outputs during the forward pass
+        and recomputes all intermediate states during the backward pass.
+    """
+
+def average_gradients(
+    gradients: Any,
+    group: Optional[mx.distributed.Group] = ...,
+    all_reduce_size: int = ...,
+    communication_type: Optional[mx.Dtype] = ...,
+    communication_stream: Optional[mx.Stream] = ...,
+):  # -> Any:
+    """Average the gradients across the distributed processes in the passed group.
+
+    This helper enables concatenating several gradients of small arrays to one
+    big all reduce call for better networking performance.
+
+    Args:
+        gradients (Any): The Python tree containing the gradients (it should
+            have the same structure across processes)
+        group (Optional[mlx.core.distributed.Group]): The group of processes to
+            average the gradients. If set to ``None`` the global group is used.
+            Default: ``None``.
+        all_reduce_size (int): Group arrays until their size in bytes exceeds
+            this number. Perform one communication step per group of arrays. If
+            less or equal to 0 array grouping is disabled. Default: ``32MiB``.
+        communication_type (Optional[mlx.core.Dtype]): If provided cast to this
+            type before performing the communication. Typically cast to a
+            smaller float to reduce the communication size. Default: ``None``.
+        communication_stream (Optional[mlx.core.Stream]): The stream to usse
+            for the communication. If unspecified the default communication
+            stream is used which can vary by back-end. Default: ``None``.
+    """

.mlx_typings/mlx/utils.pyi

@@ -0,0 +1,189 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Any, Callable, Dict, List, Optional, Tuple, Union
+
+from mlx.core import MX_ARRAY_TREE
+
+def tree_map(
+    fn: Callable, tree: Any, *rest: Any, is_leaf: Optional[Callable] = ...
+) -> Any:
+    """Applies ``fn`` to the leaves of the Python tree ``tree`` and
+    returns a new collection with the results.
+
+    If ``rest`` is provided, every item is assumed to be a superset of ``tree``
+    and the corresponding leaves are provided as extra positional arguments to
+    ``fn``. In that respect, :meth:`tree_map` is closer to :func:`itertools.starmap`
+    than to :func:`map`.
+
+    The keyword argument ``is_leaf`` decides what constitutes a leaf from
+    ``tree`` similar to :func:`tree_flatten`.
+
+    .. code-block:: python
+
+        import mlx.nn as nn
+        from mlx.utils import tree_map
+
+        model = nn.Linear(10, 10)
+        print(model.parameters().keys())
+        # dict_keys(['weight', 'bias'])
+
+        # square the parameters
+        model.update(tree_map(lambda x: x*x, model.parameters()))
+
+    Args:
+        fn (callable): The function that processes the leaves of the tree.
+        tree (Any): The main Python tree that will be iterated upon.
+        rest (tuple[Any]): Extra trees to be iterated together with ``tree``.
+        is_leaf (callable, optional): An optional callable that returns ``True``
+           if the passed object is considered a leaf or ``False`` otherwise.
+
+    Returns:
+        A Python tree with the new values returned by ``fn``.
+    """
+
+def tree_map_with_path(
+    fn: Callable,
+    tree: Any,
+    *rest: Any,
+    is_leaf: Optional[Callable] = ...,
+    path: Optional[Any] = ...,
+) -> Any:
+    """Applies ``fn`` to the path and leaves of the Python tree ``tree`` and
+    returns a new collection with the results.
+
+    This function is the same :func:`tree_map` but the ``fn`` takes the path as
+    the first argument followed by the remaining tree nodes.
+
+    Args:
+        fn (callable): The function that processes the leaves of the tree.
+        tree (Any): The main Python tree that will be iterated upon.
+        rest (tuple[Any]): Extra trees to be iterated together with ``tree``.
+        is_leaf (Optional[Callable]): An optional callable that returns ``True``
+           if the passed object is considered a leaf or ``False`` otherwise.
+        path (Optional[Any]): Prefix will be added to the result.
+
+    Returns:
+        A Python tree with the new values returned by ``fn``.
+
+    Example:
+        >>> from mlx.utils import tree_map_with_path
+        >>> tree = {"model": [{"w": 0, "b": 1}, {"w": 0, "b": 1}]}
+        >>> new_tree = tree_map_with_path(lambda path, _: print(path), tree)
+        model.0.w
+        model.0.b
+        model.1.w
+        model.1.b
+    """
+
+def tree_flatten(
+    tree: Any,
+    prefix: str = ...,
+    is_leaf: Optional[Callable] = ...,
+    destination: Optional[Union[List[Tuple[str, Any]], Dict[str, Any]]] = ...,
+) -> Union[List[Tuple[str, Any]], Dict[str, Any]]:
+    """Flattens a Python tree to a list of key, value tuples.
+
+    The keys are using the dot notation to define trees of arbitrary depth and
+    complexity.
+
+    .. code-block:: python
+
+        from mlx.utils import tree_flatten
+
+        print(tree_flatten([[[0]]]))
+        # [("0.0.0", 0)]
+
+        print(tree_flatten([[[0]]], prefix=".hello"))
+        # [("hello.0.0.0", 0)]
+
+        tree_flatten({"a": {"b": 1}}, destination={})
+        {"a.b": 1}
+
+    .. note::
+       Dictionaries should have keys that are valid Python identifiers.
+
+    Args:
+        tree (Any): The Python tree to be flattened.
+        prefix (str): A prefix to use for the keys. The first character is
+            always discarded.
+        is_leaf (callable): An optional callable that returns True if the
+            passed object is considered a leaf or False otherwise.
+        destination (list or dict, optional): A list or dictionary to store the
+            flattened tree. If None an empty list will be used. Default: ``None``.
+
+    Returns:
+        Union[List[Tuple[str, Any]], Dict[str, Any]]: The flat representation of
+            the Python tree.
+    """
+
+def tree_unflatten(tree: Union[List[Tuple[str, Any]], Dict[str, Any]]) -> Any:
+    """Recreate a Python tree from its flat representation.
+
+    .. code-block:: python
+
+        from mlx.utils import tree_unflatten
+
+        d = tree_unflatten([("hello.world", 42)])
+        print(d)
+        # {"hello": {"world": 42}}
+
+        d = tree_unflatten({"hello.world": 42})
+        print(d)
+        # {"hello": {"world": 42}}
+
+    Args:
+        tree (list[tuple[str, Any]] or dict[str, Any]): The flat representation of a Python tree.
+           For instance as returned by :meth:`tree_flatten`.
+
+    Returns:
+        A Python tree.
+    """
+
+def tree_reduce(
+    fn: Callable[[Any, Any], Any],
+    tree: list[MX_ARRAY_TREE] | tuple[MX_ARRAY_TREE, ...] | dict[str, MX_ARRAY_TREE],
+    initializer=...,
+    is_leaf=...,
+) -> None:
+    """Applies a reduction to the leaves of a Python tree.
+
+    This function reduces Python trees into an accumulated result by applying
+    the provided function ``fn`` to the leaves of the tree.
+
+    Example:
+        >>> from mlx.utils import tree_reduce
+        >>> tree = {"a": [1, 2, 3], "b": [4, 5]}
+        >>> tree_reduce(lambda acc, x: acc + x, tree, 0)
+        15
+
+    Args:
+        fn (callable): The reducer function that takes two arguments (accumulator,
+            current value) and returns the updated accumulator.
+        tree (Any): The Python tree to reduce. It can be any nested combination of
+            lists, tuples, or dictionaries.
+        initializer (Any, optional): The initial value to start the reduction. If
+            not provided, the first leaf value is used.
+        is_leaf (callable, optional): A function to determine if an object is a
+            leaf, returning ``True`` for leaf nodes and ``False`` otherwise.
+
+    Returns:
+        Any: The accumulated value.
+    """
+
+def tree_merge(
+    tree_a, tree_b, merge_fn=...
+):  # -> dict[Any, Any] | list[Any] | tuple[Any, *tuple[Any, ...]] | tuple[Any, ...]:
+    """Merge two Python trees in one containing the values of both. It can be
+    thought of as a deep dict.update method.
+
+    Args:
+        tree_a (Any): The first Python tree.
+        tree_b (Any): The second Python tree.
+        merge_fn (callable, optional): A function to merge leaves.
+
+    Returns:
+        The Python tree containing the values of both ``tree_a`` and
+        ``tree_b``.
+    """

.mlx_typings/mlx_lm/__init__.pyi

@@ -0,0 +1,3 @@
+import models as models
+import tokenizer_utils as tokenizer_utils
+from generate import *

.mlx_typings/mlx_lm/convert.pyi

@@ -0,0 +1,45 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+import argparse
+from typing import Callable, Optional, Union
+
+import mlx.nn as nn
+
+def mixed_quant_predicate_builder(
+    recipe: str, model: nn.Module, group_size: int = ...
+) -> Callable[[str, nn.Module, dict], Union[bool, dict]]: ...
+
+QUANT_RECIPES = ...
+MODEL_CONVERSION_DTYPES = ...
+
+def convert(
+    hf_path: str,
+    mlx_path: str = ...,
+    quantize: bool = ...,
+    q_group_size: int = ...,
+    q_bits: int = ...,
+    q_mode: str = ...,
+    dtype: Optional[str] = ...,
+    upload_repo: str = ...,
+    revision: Optional[str] = ...,
+    dequantize: bool = ...,
+    quant_predicate: Optional[
+        Union[Callable[[str, nn.Module, dict], Union[bool, dict]], str]
+    ] = ...,
+    trust_remote_code: bool = ...,
+):  # -> None:
+    ...
+def configure_parser() -> argparse.ArgumentParser:
+    """
+    Configures and returns the argument parser for the script.
+
+    Returns:
+        argparse.ArgumentParser: Configured argument parser.
+    """
+
+def main():  # -> None:
+    ...
+
+if __name__ == "__main__": ...

.mlx_typings/mlx_lm/generate.pyi

@@ -0,0 +1,324 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+import contextlib
+from dataclasses import dataclass
+from typing import Any, Callable, Generator, List, Optional, Tuple, Union
+
+import mlx.core as mx
+import mlx.nn as nn
+from transformers import PreTrainedTokenizer
+
+from .tokenizer_utils import TokenizerWrapper
+
+DEFAULT_PROMPT = ...
+DEFAULT_MAX_TOKENS = ...
+DEFAULT_TEMP = ...
+DEFAULT_TOP_P = ...
+DEFAULT_MIN_P = ...
+DEFAULT_TOP_K = ...
+DEFAULT_XTC_PROBABILITY = ...
+DEFAULT_XTC_THRESHOLD = ...
+DEFAULT_MIN_TOKENS_TO_KEEP = ...
+DEFAULT_SEED = ...
+DEFAULT_MODEL = ...
+DEFAULT_QUANTIZED_KV_START = ...
+
+def str2bool(string):  # -> bool:
+    ...
+def setup_arg_parser():  # -> ArgumentParser:
+    """Set up and return the argument parser."""
+
+generation_stream = ...
+
+@contextlib.contextmanager
+def wired_limit(
+    model: nn.Module, streams: Optional[List[mx.Stream]] = ...
+):  # -> Generator[None, Any, None]:
+    """
+    A context manager to temporarily change the wired limit.
+
+    Note, the wired limit should not be changed during an async eval.  If an
+    async eval could be running pass in the streams to synchronize with prior
+    to exiting the context manager.
+    """
+@dataclass
+class GenerationResponse:
+    """
+    The output of :func:`stream_generate`.
+
+    Args:
+        text (str): The next segment of decoded text. This can be an empty string.
+        token (int): The next token.
+        from_draft (bool): Whether the token was generated by the draft model.
+        logprobs (mx.array): A vector of log probabilities.
+        prompt_tokens (int): The number of tokens in the prompt.
+        prompt_tps (float): The prompt processing tokens-per-second.
+        generation_tokens (int): The number of generated tokens.
+        generation_tps (float): The tokens-per-second for generation.
+        peak_memory (float): The peak memory used so far in GB.
+        finish_reason (str): The reason the response is being sent: "length", "stop" or `None`
+    """
+
+    text: str
+    token: int
+    logprobs: mx.array
+    from_draft: bool
+    prompt_tokens: int
+    prompt_tps: float
+    generation_tokens: int
+    generation_tps: float
+    peak_memory: float
+    finish_reason: Optional[str] = ...
+
+def maybe_quantize_kv_cache(
+    prompt_cache, quantized_kv_start, kv_group_size, kv_bits
+):  # -> None:
+    ...
+def generate_step(
+    prompt: mx.array,
+    model: nn.Module,
+    *,
+    max_tokens: int = ...,
+    sampler: Optional[Callable[[mx.array], mx.array]] = ...,
+    logits_processors: Optional[List[Callable[[mx.array, mx.array], mx.array]]] = ...,
+    max_kv_size: Optional[int] = ...,
+    prompt_cache: Optional[Any] = ...,
+    prefill_step_size: int = ...,
+    kv_bits: Optional[int] = ...,
+    kv_group_size: int = ...,
+    quantized_kv_start: int = ...,
+    prompt_progress_callback: Optional[Callable[[int], int]] = ...,
+    input_embeddings: Optional[mx.array] = ...,
+) -> Generator[Tuple[mx.array, mx.array], None, None]:
+    """
+    A generator producing token ids based on the given prompt from the model.
+
+    Args:
+        prompt (mx.array): The input prompt.
+        model (nn.Module): The model to use for generation.
+        max_tokens (int): The maximum number of tokens. Use``-1`` for an infinite
+          generator. Default: ``256``.
+        sampler (Callable[mx.array, mx.array], optional): A sampler for sampling a
+          token from a vector of log probabilities. Default: ``None``.
+        logits_processors (List[Callable[[mx.array, mx.array], mx.array]], optional):
+          A list of functions that take tokens and logits and return the processed
+          logits. Default: ``None``.
+        max_kv_size (int, optional): Maximum size of the key-value cache. Old
+          entries (except the first 4 tokens) will be overwritten.
+        prompt_cache (List[Any], optional): A pre-computed prompt cache. Note, if
+          provided, the cache will be updated in place.
+        prefill_step_size (int): Step size for processing the prompt.
+        kv_bits (int, optional): Number of bits to use for KV cache quantization.
+          None implies no cache quantization. Default: ``None``.
+        kv_group_size (int): Group size for KV cache quantization. Default: ``64``.
+        quantized_kv_start (int): Step to begin using a quantized KV cache.
+           when ``kv_bits`` is non-None. Default: ``0``.
+        prompt_progress_callback (Callable[[int], int]): A call-back which takes the
+           prompt tokens processed so far and the total number of prompt tokens.
+        input_embeddings (mx.array, optional): Input embeddings to use instead of or in
+          conjunction with prompt tokens. Default: ``None``.
+
+    Yields:
+        Tuple[mx.array, mx.array]: One token and a vector of log probabilities.
+    """
+
+def speculative_generate_step(
+    prompt: mx.array,
+    model: nn.Module,
+    draft_model: nn.Module,
+    *,
+    num_draft_tokens: int = ...,
+    max_tokens: int = ...,
+    sampler: Optional[Callable[[mx.array], mx.array]] = ...,
+    logits_processors: Optional[List[Callable[[mx.array, mx.array], mx.array]]] = ...,
+    prompt_cache: Optional[Any] = ...,
+    prefill_step_size: int = ...,
+    kv_bits: Optional[int] = ...,
+    kv_group_size: int = ...,
+    quantized_kv_start: int = ...,
+) -> Generator[Tuple[mx.array, mx.array, bool], None, None]:
+    """
+    A generator producing token ids based on the given prompt from the model.
+
+    Args:
+        prompt (mx.array): The input prompt.
+        model (nn.Module): The model to use for generation.
+        draft_model (nn.Module): The draft model for speculative decoding.
+        num_draft_tokens (int, optional): The number of draft tokens for
+          speculative decoding. Default: ``2``.
+        max_tokens (int): The maximum number of tokens. Use``-1`` for an infinite
+          generator. Default: ``256``.
+        sampler (Callable[[mx.array], mx.array], optional): A sampler for sampling a
+          token from a vector of log probabilities. Default: ``None``.
+        logits_processors (List[Callable[[mx.array, mx.array], mx.array]], optional):
+          A list of functions that take tokens and logits and return the processed
+          logits. Default: ``None``.
+        prompt_cache (List[Any], optional): A pre-computed prompt cache. Note, if
+          provided, the cache will be updated in place. The cache must be trimmable.
+        prefill_step_size (int): Step size for processing the prompt.
+        kv_bits (int, optional): Number of bits to use for KV cache quantization.
+          None implies no cache quantization. Default: ``None``.
+        kv_group_size (int): Group size for KV cache quantization. Default: ``64``.
+        quantized_kv_start (int): Step to begin using a quantized KV cache.
+           when ``kv_bits`` is non-None. Default: ``0``.
+
+    Yields:
+        Tuple[mx.array, mx.array, bool]: One token, a vector of log probabilities,
+          and a bool indicating if the token was generated by the draft model
+    """
+
+def stream_generate(
+    model: nn.Module,
+    tokenizer: Union[PreTrainedTokenizer, TokenizerWrapper],
+    prompt: Union[str, mx.array, List[int]],
+    max_tokens: int = ...,
+    draft_model: Optional[nn.Module] = ...,
+    **kwargs: object,
+) -> Generator[GenerationResponse, None, None]:
+    """
+    A generator producing text based on the given prompt from the model.
+
+    Args:
+        model (nn.Module): The model to use for generation.
+        tokenizer (PreTrainedTokenizer): The tokenizer.
+        prompt (Union[str, mx.array, List[int]]): The input prompt string or
+          integer tokens.
+        max_tokens (int): The maximum number of tokens to generate.
+          Default: ``256``.
+        draft_model (Optional[nn.Module]): An optional draft model. If provided
+          then speculative decoding is used. The draft model must use the same
+          tokenizer as the main model. Default: ``None``.
+        kwargs: The remaining options get passed to :func:`generate_step`.
+          See :func:`generate_step` for more details.
+
+    Yields:
+        GenerationResponse: An instance containing the generated text segment and
+            associated metadata. See :class:`GenerationResponse` for details.
+    """
+
+def generate(
+    model: nn.Module,
+    tokenizer: Union[PreTrainedTokenizer, TokenizerWrapper],
+    prompt: Union[str, List[int]],
+    verbose: bool = ...,
+    **kwargs,
+) -> str:
+    """
+    Generate a complete response from the model.
+
+    Args:
+       model (nn.Module): The language model.
+       tokenizer (PreTrainedTokenizer): The tokenizer.
+       prompt (Union[str, List[int]]): The input prompt string or integer tokens.
+       verbose (bool): If ``True``, print tokens and timing information.
+           Default: ``False``.
+       kwargs: The remaining options get passed to :func:`stream_generate`.
+          See :func:`stream_generate` for more details.
+    """
+@dataclass
+class BatchStats:
+    """
+    An data object to hold generation stats.
+
+    Args:
+        prompt_tokens (int): The number of prompt tokens processed.
+        prompt_tps (float): The prompt processing tokens-per-second.
+        prompt_time (float): The time in seconds spent in prompt processing.
+        generation_tokens (int): The number of generated tokens.
+        generation_tps (float): The tokens-per-second for generation.
+        generation_time (float): The time in seconds spent in generation .
+        peak_memory (float): The peak memory used so far in GB.
+    """
+
+    prompt_tokens: int = ...
+    prompt_tps: float = ...
+    prompt_time: float = ...
+    generation_tokens: int = ...
+    generation_tps: float = ...
+    generation_time: float = ...
+    peak_memory: float = ...
+
+@dataclass
+class BatchResponse:
+    """
+    An data object to hold a batch generation response.
+
+    Args:
+        texts: (List[str]): The generated text for each prompt.
+        stats (BatchStats): Statistics about the generation.
+    """
+
+    texts: List[str]
+    stats: BatchStats
+
+@dataclass
+class Batch:
+    uids: List[int]
+    y: mx.array
+    logprobs: mx.array
+    max_tokens: List[int]
+    num_tokens: List[int]
+    cache: List[Any]
+    def __len__(self):  # -> int:
+        ...
+    def filter(self, keep_idx: List[int]):  # -> None:
+        ...
+    def extend(self, other):  # -> None:
+        ...
+
+class BatchGenerator:
+    @dataclass
+    class Response:
+        uid: int
+        token: int
+        logprobs: mx.array
+        finish_reason: Optional[str]
+
+    def __init__(
+        self,
+        model,
+        max_tokens: int = ...,
+        stop_tokens: Optional[set] = ...,
+        sampler: Optional[Callable[[mx.array], mx.array]] = ...,
+        completion_batch_size: int = ...,
+        prefill_batch_size: int = ...,
+        prefill_step_size: int = ...,
+    ) -> None: ...
+    def insert(
+        self, prompts, max_tokens: Union[List[int], int, None] = ...
+    ):  # -> list[Any]:
+        ...
+    def stats(self):  # -> BatchStats:
+        ...
+    def next(self):  # -> list[Any]:
+        ...
+
+def batch_generate(
+    model,
+    tokenizer,
+    prompts: List[int],
+    max_tokens: Union[int, List[int]] = ...,
+    verbose: bool = ...,
+    **kwargs,
+) -> BatchResponse:
+    """
+    Generate responses for the given batch of prompts.
+
+    Args:
+       model (nn.Module): The language model.
+       tokenizer (PreTrainedTokenizer): The tokenizer.
+       prompt (List[List[int]]): The input prompts.
+       verbose (bool): If ``True``, print tokens and timing information.
+          Default: ``False``.
+       max_tokens (Union[int, List[int]): Maximum number of output tokens. This
+          can be per prompt if a list is provided.
+       kwargs: The remaining options get passed to :obj:`BatchGenerator`.
+          See :obj:`BatchGenerator` for more details.
+    """
+
+def main():  # -> None:
+    ...
+
+if __name__ == "__main__": ...

.mlx_typings/mlx_lm/models/__init__.pyi

@@ -0,0 +1 @@
+import cache as cache

.mlx_typings/mlx_lm/models/base.pyi

@@ -0,0 +1,47 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from dataclasses import dataclass
+from typing import Optional
+
+import mlx.core as mx
+
+@dataclass
+class BaseModelArgs:
+    @classmethod
+    def from_dict(cls, params):  # -> Self:
+        ...
+
+def create_causal_mask(
+    N: int,
+    offset: int = ...,
+    window_size: Optional[int] = ...,
+    right_padding: Optional[mx.array] = ...,
+    left_padding: Optional[mx.array] = ...,
+):  # -> array:
+    ...
+def create_attention_mask(
+    h, cache=..., window_size: Optional[int] = ..., return_array: bool = ...
+):  # -> array | Literal['causal'] | None:
+    ...
+def create_ssm_mask(h, cache=...):  # -> None:
+    ...
+def quantized_scaled_dot_product_attention(
+    queries: mx.array,
+    q_keys: tuple[mx.array, mx.array, mx.array],
+    q_values: tuple[mx.array, mx.array, mx.array],
+    scale: float,
+    mask: Optional[mx.array],
+    group_size: int = ...,
+    bits: int = ...,
+) -> mx.array: ...
+def scaled_dot_product_attention(
+    queries,
+    keys,
+    values,
+    cache,
+    scale: float,
+    mask: Optional[mx.array],
+    sinks: Optional[mx.array] = ...,
+) -> mx.array: ...

.mlx_typings/mlx_lm/models/bitlinear_layers.pyi

@@ -0,0 +1,26 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+import mlx.nn as nn
+
+def bitnet_quantize(model, quantization_config: dict): ...
+def make_bitlinear_kernel():
+    """
+    Custom Metal kernel that performs matrix multiplication directly on
+    packed weights and scales the output. This eliminates the need to
+    store unpacked weights in memory.
+    """
+
+_bitlinear_kernel = ...
+
+class BitLinear(nn.Module):
+    """
+    BitLinear module with memory-efficient weight handling.
+    """
+    def __init__(
+        self, in_features, out_features, bias=..., invert_weight_scales=...
+    ) -> None: ...
+    def execute_matmul_kernel(self, x, packed_weights): ...
+    def __call__(self, x):  # -> array:
+        ...

.mlx_typings/mlx_lm/models/cache.pyi

@@ -0,0 +1,357 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from typing import Any, Dict, List, Optional, Protocol, Literal, Self
+
+import mlx.nn as nn
+from mlx.core import array
+import mlx.core as mx
+
+class Cache(Protocol):
+    keys: mx.array
+    values: mx.array
+    def update_and_fetch(self, keys: mx.array, values: mx.array) -> None: ...
+    @property
+    def state(self) -> tuple[mx.array, mx.array]: ...
+    @state.setter
+    def state(self, v) -> None: ...
+
+def make_prompt_cache(
+    model: nn.Module, max_kv_size: Optional[int] = ...
+) -> List[Cache | Any]:
+    """
+    Construct the model's cache for use in generation.
+
+    This function will defer the cache construction to the model if it has a
+    ``make_cache`` method, otherwise it will make a default KV cache.
+
+    Args:
+        model (nn.Module): The language model.
+        max_kv_size (Optional[int]): If provided and the model does not have a
+            ``make_cache`` method, a ``RotatingKVCache`` is used with a maximum
+            size of ``max_kv_size``
+    """
+
+def save_prompt_cache(
+    file_name: str, cache: List[Cache], metadata: Dict[str, str] = ...
+) -> None:
+    """
+    Save a pre-computed prompt cache to a file.
+
+    Args:
+        file_name (str): The ``.safetensors`` file name.
+        cache (List[Any]): The model state.
+        metadata (Dict[str, str]): Optional metadata to save along with model
+            state.
+    """
+
+def load_prompt_cache(file_name: str, return_metadata=...) -> array:
+    """
+    Load a prompt cache from a file.
+
+    Args:
+        file_name (str): The ``.safetensors`` file name.
+        return_metadata (bool): Whether or not to return metadata.
+            Default: ``False``.
+
+    Returns:
+        List[Any] or Tuple[List[Any], Dict[str, str]]: The prompt cache and
+            the metadata if requested.
+    """
+
+def can_trim_prompt_cache(cache: List[Cache]) -> bool:
+    """
+    Check if model's cache can be trimmed.
+    """
+
+def trim_prompt_cache(cache: List[Cache], num_tokens: int) -> List[Cache]:
+    """
+    Trim the model's cache by the given number of tokens.
+
+    This function will trim the cache if possible (in-place) and return the
+    number of tokens that were trimmed.
+
+    Args:
+        cache (List[Any]): The model's cache.
+        num_tokens (int): The number of tokens to trim.
+
+    Returns:
+        (int): The number of tokens that were trimmed.
+    """
+
+def create_attention_mask(
+    N: int, offset: int, return_array: bool, window_size: Optional[int]
+) -> array | Literal["causal"] | None: ...
+
+class _BaseCache(Cache):
+    keys: mx.array
+    values: mx.array
+    @property
+    def state(self) -> tuple[mx.array, mx.array]: ...
+    @state.setter
+    def state(self, v) -> None: ...
+    @property
+    def meta_state(self) -> Literal[""]: ...
+    @meta_state.setter
+    def meta_state(self, v) -> None: ...
+    def is_trimmable(self) -> Literal[False]: ...
+    @classmethod
+    def from_state(cls, state, meta_state) -> Self: ...
+
+class ConcatenateKVCache(_BaseCache):
+    """ConcatenateKVCache the simplest KV cache implementation.
+
+    Can be used as a mock KV cache or when large blocks are being processed at
+    a time in which case KVCache isn't necessarily faster. Consider using the
+    KVCache with a larger step size before using this cache.
+    """
+    def __init__(self) -> None: ...
+    def update_and_fetch(self, keys, values):  # -> tuple[Any | array, Any | array]:
+        ...
+    @property
+    def state(self):  # -> tuple[Any | array | None, Any | array | None]:
+        ...
+    @state.setter
+    def state(self, v):  # -> None:
+        ...
+    def is_trimmable(self):  # -> Literal[True]:
+        ...
+    def trim(self, n):  # -> int:
+        ...
+    def make_mask(self, *args, **kwargs):  # -> array | Literal['causal'] | None:
+        ...
+
+class QuantizedKVCache(_BaseCache):
+    step = ...
+    def __init__(self, group_size: int = ..., bits: int = ...) -> None: ...
+    def update_and_fetch(self, keys, values):  # -> Any:
+        ...
+    @property
+    def state(
+        self,
+    ):  # -> tuple[Any | tuple[array, array, array] | None, Any | tuple[array, array, array] | None] | Any:
+        ...
+    @state.setter
+    def state(self, v):  # -> None:
+        ...
+    @property
+    def meta_state(self):  # -> tuple[str, ...]:
+        ...
+    @meta_state.setter
+    def meta_state(self, v):  # -> None:
+        ...
+    def is_trimmable(self):  # -> Literal[True]:
+        ...
+    def trim(self, n):  # -> int:
+        ...
+    def make_mask(self, *args, **kwargs):  # -> array | Literal['causal'] | None:
+        ...
+
+class KVCache(_BaseCache):
+    step = ...
+    def __init__(self) -> None: ...
+    def update_and_fetch(self, keys, values):  # -> tuple[array | Any, array | Any]:
+        ...
+    @property
+    def state(
+        self,
+    ) -> tuple[array, array]: ...
+    @state.setter
+    def state(self, v) -> None: ...
+    def is_trimmable(self):  # -> Literal[True]:
+        ...
+    def trim(self, n):  # -> int:
+        ...
+    def to_quantized(
+        self, group_size: int = ..., bits: int = ...
+    ) -> QuantizedKVCache: ...
+    def make_mask(self, *args, **kwargs):  # -> array | Literal['causal'] | None:
+        ...
+
+class RotatingKVCache(_BaseCache):
+    step = ...
+    def __init__(self, max_size, keep=...) -> None: ...
+    def update_and_fetch(
+        self, keys, values
+    ):  # -> tuple[array | Any, array | Any] | tuple[array | Any, array | Any | None]:
+        ...
+    @property
+    def state(
+        self,
+    ):  # -> tuple[Any | array, Any | array] | tuple[Any | array | None, Any | array | None]:
+        ...
+    @state.setter
+    def state(self, v):  # -> None:
+        ...
+    @property
+    def meta_state(self):  # -> tuple[str, ...]:
+        ...
+    @meta_state.setter
+    def meta_state(self, v):  # -> None:
+        ...
+    def is_trimmable(self):  # -> bool:
+        ...
+    def trim(self, n):  # -> int:
+        ...
+    def to_quantized(
+        self, group_size: int = ..., bits: int = ...
+    ) -> QuantizedKVCache: ...
+    def make_mask(
+        self, N: int, window_size: Optional[int] = ..., return_array: bool = ...
+    ):  # -> array | Literal['causal'] | None:
+        ...
+
+class ArraysCache(_BaseCache):
+    def __init__(self, size, left_padding: Optional[List[int]] = ...) -> None: ...
+    def __setitem__(self, idx, value):  # -> None:
+        ...
+    def __getitem__(self, idx): ...
+    @property
+    def state(self):  # -> list[Any | array] | list[array]:
+        ...
+    @state.setter
+    def state(self, v):  # -> None:
+        ...
+    def filter(self, batch_indices):  # -> None:
+        """
+        In-place filter to keep just the given indices in the cache.
+        """
+
+    def extend(self, other):  # -> None:
+        """
+        In-place extend this cache with the other cache.
+        """
+
+    def make_mask(self, N: int):  # -> array | None:
+        ...
+
+class MambaCache(ArraysCache):
+    def __init__(self, left_padding: Optional[List[int]] = ...) -> None: ...
+
+class ChunkedKVCache(KVCache):
+    def __init__(self, chunk_size) -> None: ...
+    def maybe_trim_front(self):  # -> None:
+        ...
+    def update_and_fetch(self, keys, values):  # -> tuple[array, array]:
+        ...
+    def trim(self, n):  # -> int:
+        ...
+    @property
+    def meta_state(self):  # -> tuple[str, ...]:
+        ...
+    @meta_state.setter
+    def meta_state(self, v):  # -> None:
+        ...
+
+class CacheList(_BaseCache):
+    def __init__(self, *caches) -> None: ...
+    def __getitem__(self, idx): ...
+    def is_trimmable(self):  # -> bool:
+        ...
+    def trim(self, n): ...
+    @property
+    def state(self):  # -> list[Any]:
+        ...
+    @state.setter
+    def state(self, v):  # -> None:
+        ...
+    def filter(self, batch_indices):  # -> None:
+        """
+        In-place filter to keep just the given indices in the cache.
+        """
+
+    def extend(self, other):  # -> None:
+        """
+        In-place extend this cache with the other cache.
+        """
+
+class BatchKVCache(_BaseCache):
+    step = ...
+    def __init__(self, left_padding: List[int]) -> None:
+        """
+        The BatchKV cache expects inputs to be left-padded.
+
+        E.g. the following prompts:
+
+            [1, 3, 5]
+            [7]
+            [2, 6, 8, 9]
+
+        Should be padded like so:
+
+            [0, 1, 3, 5]
+            [0, 0, 0, 7]
+            [2, 6, 8, 9]
+
+        And ``left_padding`` specifies the amount of padding for each.
+        In this case, ``left_padding = [1, 3, 0]``.
+        """
+
+    def update_and_fetch(self, keys, values):  # -> tuple[array | Any, array | Any]:
+        ...
+    @property
+    def state(
+        self,
+    ):  # -> tuple[Any | array | None, Any | array | None, array | Any, array | Any]:
+        ...
+    @state.setter
+    def state(self, v):  # -> None:
+        ...
+    def is_trimmable(self):  # -> Literal[True]:
+        ...
+    def trim(self, n):  # -> int | float:
+        ...
+    def make_mask(self, N: int, return_array: bool = ..., **kwargs):  # -> array:
+        ...
+    def filter(self, batch_indices):  # -> None:
+        """
+        In-place filter to keep just the given indices in the cache.
+        """
+
+    def extend(self, other):  # -> None:
+        """
+        In-place extend this cache with the other cache.
+        """
+
+class BatchRotatingKVCache(_BaseCache):
+    step = ...
+    def __init__(self, max_size, left_padding: List[int]) -> None: ...
+    def update_and_fetch(
+        self, keys, values
+    ):  # -> tuple[array | Any, array | Any] | tuple[array | Any, array | Any | None]:
+        ...
+    @property
+    def state(
+        self,
+    ):  # -> tuple[Any | array | None, Any | array | None, array | Any, array | Any]:
+        ...
+    @state.setter
+    def state(self, v):  # -> None:
+        ...
+    @property
+    def meta_state(self):  # -> tuple[str, ...]:
+        ...
+    @meta_state.setter
+    def meta_state(self, v):  # -> None:
+        ...
+    def is_trimmable(self):  # -> bool:
+        ...
+    def trim(self, n):  # -> int:
+        ...
+    def to_quantized(
+        self, group_size: int = ..., bits: int = ...
+    ) -> QuantizedKVCache: ...
+    def make_mask(
+        self, N: int, window_size: Optional[int] = ..., return_array: bool = ...
+    ):  # -> array:
+        ...
+    def filter(self, batch_indices):  # -> None:
+        """
+        In-place filter to keep just the given indices in the cache.
+        """
+
+    def extend(self, other):  # -> None:
+        """
+        In-place extend this cache with the other cache.
+        """

.mlx_typings/mlx_lm/models/switch_layers.pyi

@@ -0,0 +1,79 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from functools import partial
+
+import mlx.core as mx
+import mlx.nn as nn
+
+class QuantizedSwitchLinear(nn.Module):
+    def __init__(
+        self,
+        input_dims: int,
+        output_dims: int,
+        num_experts: int,
+        bias: bool = ...,
+        group_size: int = ...,
+        bits: int = ...,
+        mode: str = ...,
+    ) -> None: ...
+    @property
+    def input_dims(self):  # -> int:
+        ...
+    @property
+    def output_dims(self):  # -> int:
+        ...
+    @property
+    def num_experts(self):  # -> int:
+        ...
+    def __call__(self, x, indices, sorted_indices=...):  # -> array:
+        ...
+
+class SwitchLinear(nn.Module):
+    def __init__(
+        self, input_dims: int, output_dims: int, num_experts: int, bias: bool = ...
+    ) -> None: ...
+    @property
+    def input_dims(self):  # -> int:
+        ...
+    @property
+    def output_dims(self):  # -> int:
+        ...
+    @property
+    def num_experts(self):  # -> int:
+        ...
+    def __call__(self, x, indices, sorted_indices=...): ...
+    def to_quantized(
+        self, group_size: int = ..., bits: int = ..., mode: str = ...
+    ):  # -> QuantizedSwitchLinear:
+        ...
+
+@partial(mx.compile, shapeless=True)
+def swiglu(x, gate): ...
+
+class SwiGLU(nn.Module):
+    def __init__(self) -> None: ...
+    def __call__(self, x, gate): ...
+
+class SwitchGLU(nn.Module):
+    def __init__(
+        self,
+        input_dims: int,
+        hidden_dims: int,
+        num_experts: int,
+        activation=...,
+        bias: bool = ...,
+    ) -> None: ...
+    def __call__(self, x, indices) -> mx.array: ...
+
+class SwitchMLP(nn.Module):
+    def __init__(
+        self,
+        input_dims: int,
+        hidden_dims: int,
+        num_experts: int,
+        activation=...,
+        bias: bool = ...,
+    ) -> None: ...
+    def __call__(self, x, indices) -> mx.array: ...

.mlx_typings/mlx_lm/sample_utils.pyi

@@ -0,0 +1,148 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from functools import partial
+from typing import Callable, Dict, List, Optional
+
+import mlx.core as mx
+
+def make_sampler(
+    temp: float = ...,
+    top_p: float = ...,
+    min_p: float = ...,
+    min_tokens_to_keep: int = ...,
+    top_k: int = ...,
+    xtc_probability: float = ...,
+    xtc_threshold: float = ...,
+    xtc_special_tokens: List[int] = ...,
+) -> Callable[[mx.array], mx.array]:
+    """
+    Make a sampler function for use with ``generate_step``.
+
+    Args:
+        temp (float): The temperature for sampling, if 0 the argmax is used.
+          Default: ``0``.
+        top_p (float, optional): Nulceus sampling, higher means model considers
+          more less likely words.
+        min_p (float, optional): The minimum value (scaled by the top token's
+          probability) that a token probability must have to be considered.
+        min_tokens_to_keep (int, optional): Minimum number of tokens that cannot
+          be filtered by min_p sampling.
+        top_k (int, optional): The top k tokens ranked by probability to constrain
+          the sampling to.
+        xtc_probability (float, optional): The probability of applying XTC
+            sampling.
+        xtc_threshold (float, optional): The threshold the probs need to reach
+            for being sampled.
+        xtc_special_tokens (list(int), optional): List of special tokens IDs to
+            be excluded from XTC sampling.
+
+
+    Returns:
+        Callable[mx.array, mx.array]:
+            A sampler which takes log-probabilities and returns tokens.
+    """
+
+def make_logits_processors(
+    logit_bias: Optional[Dict[int, float]] = ...,
+    repetition_penalty: Optional[float] = ...,
+    repetition_context_size: Optional[int] = ...,
+):  # -> list[Any]:
+    """
+    Make logits processors for use with ``generate_step``.
+
+    Args:
+        repetition_penalty (float, optional): The penalty factor for repeating
+          tokens.
+        repetition_context_size (int, optional): The number of tokens to
+          consider for repetition penalty. Default: ``20``.
+        logit_bias (dictionary, optional): Additive logit bias.
+
+    Returns:
+        List[Callable[[mx.array, mx.array], mx.array]]:
+            A list of logits processors. Each processor in the list is a
+            callable which takes an array of tokens and an array of logits
+            and returns the updated logits.
+    """
+
+@partial(mx.compile, inputs=mx.random.state, outputs=mx.random.state)
+def apply_top_k(logprobs: mx.array, top_k: int) -> mx.array:
+    """
+    Sample from only the top K tokens ranked by probability.
+
+    Args:
+        logprobs: A vector of log probabilities.
+        top_k (int): Top k tokens to sample from.
+    """
+
+@partial(mx.compile, inputs=mx.random.state, outputs=mx.random.state)
+def apply_min_p(
+    logprobs: mx.array, min_p: float, min_tokens_to_keep: int = ...
+) -> mx.array:
+    """
+    Apply min-p sampling to the logprobs.
+
+    Min-p keeps all tokens that are above a minimum probability, scaled by the
+    probability of the most likely token. As a result, the filter is more
+    aggressive given a very high-probability token.
+
+    Args:
+        logprobs: A vector of log probabilities.
+        min_p (float): Minimum token probability. Typical values are in the
+            0.01-0.2 range, comparably selective as setting `top_p` in the
+            0.99-0.8 range.
+        min_tokens_to_keep (int, optional): Minimum number of tokens that cannot
+            be filtered. Default: ``1``.
+
+    """
+
+@partial(mx.compile, inputs=mx.random.state, outputs=mx.random.state)
+def apply_top_p(logprobs: mx.array, top_p: float) -> mx.array:
+    """
+    Apply top-p (nucleus) sampling to logits.
+
+    Args:
+        logprobs: A vector of log probabilities.
+        top_p: The cumulative probability threshold for top-p filtering.
+    Returns:
+        token selected based on the top-p criterion.
+    """
+
+@partial(mx.compile, inputs=mx.random.state, outputs=mx.random.state)
+def apply_xtc(
+    logits: mx.array,
+    xtc_probability: float,
+    xtc_threshold: float,
+    xtc_special_tokens: List[int],
+) -> mx.array:
+    """
+    Apply XTC sampling to the logits.
+
+    Args:
+        logits: The logits from the model's output.
+        xtc_probability (float): Probability of XTC sampling to happen for each token
+        xtc_threshold (float): The threshold the probs need to reach for being sampled.
+        special_tokens_ids (list(int)): List of special tokens IDs to be excluded from XTC sampling.
+    """
+
+@partial(mx.compile, inputs=mx.random.state, outputs=mx.random.state)
+def categorical_sampling(logits, temp):  # -> array:
+    ...
+def make_repetition_penalty(
+    penalty: float, context_size: int = ...
+):  # -> Callable[..., Any]:
+    """
+    Make repetition penalty processor.
+
+    Paper: https://arxiv.org/abs/1909.05858
+
+    Args:
+        penalty (float): The repetition penalty factor to be applied.
+        context_size (int): The number of previous tokens to use.
+            Default: ``20``.
+
+    Returns:
+        Callable[[mx.array, List[int]], mx.array]:
+            The repetition penalty processor.
+    """

.mlx_typings/mlx_lm/tokenizer_utils.pyi

@@ -0,0 +1,168 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from functools import partial
+from pathlib import Path
+
+from transformers import PreTrainedTokenizerFast
+
+class StreamingDetokenizer:
+    """The streaming detokenizer interface so that we can detokenize one token at a time.
+
+    Example usage is as follows:
+
+        detokenizer = ...
+
+        # Reset the tokenizer state
+        detokenizer.reset()
+
+        for token in generate(...):
+            detokenizer.add_token(token.item())
+
+            # Contains the whole text so far. Some tokens may not be included
+            # since it contains whole words usually.
+            detokenizer.text
+
+            # Contains the printable segment (usually a word) since the last
+            # time it was accessed
+            detokenizer.last_segment
+
+            # Contains all the tokens added so far
+            detokenizer.tokens
+
+        # Make sure that we detokenize any remaining tokens
+        detokenizer.finalize()
+
+        # Now detokenizer.text should match tokenizer.decode(detokenizer.tokens)
+    """
+
+    __slots__ = ...
+    def reset(self): ...
+    def add_token(self, token): ...
+    def finalize(self): ...
+    @property
+    def last_segment(self):
+        """Return the last segment of readable text since last time this property was accessed."""
+
+class NaiveStreamingDetokenizer(StreamingDetokenizer):
+    """NaiveStreamingDetokenizer relies on the underlying tokenizer
+    implementation and should work with every tokenizer.
+
+    Its complexity is O(T^2) where T is the longest line since it will
+    repeatedly detokenize the same tokens until a new line is generated.
+    """
+    def __init__(self, tokenizer) -> None: ...
+    def reset(self):  # -> None:
+        ...
+    def add_token(self, token):  # -> None:
+        ...
+    def finalize(self):  # -> None:
+        ...
+    @property
+    def text(self):  # -> str:
+        ...
+
+class SPMStreamingDetokenizer(StreamingDetokenizer):
+    """A streaming detokenizer for SPM models.
+
+    It adds tokens to the text if the next token starts with the special SPM
+    underscore which results in linear complexity.
+    """
+    def __init__(self, tokenizer, trim_space=...) -> None: ...
+    def reset(self):  # -> None:
+        ...
+    def add_token(self, token):  # -> None:
+        ...
+    def finalize(self):  # -> None:
+        ...
+
+class BPEStreamingDetokenizer(StreamingDetokenizer):
+    """A streaming detokenizer for OpenAI style BPE models.
+
+    It adds tokens to the text if the next token starts with a space similar to
+    the SPM detokenizer.
+    """
+
+    _byte_decoder = ...
+    _space_matches = ...
+    def __init__(self, tokenizer) -> None: ...
+    def reset(self):  # -> None:
+        ...
+    def add_token(self, token):  # -> None:
+        ...
+    def finalize(self):  # -> None:
+        ...
+    @classmethod
+    def make_byte_decoder(cls):  # -> None:
+        """See https://github.com/openai/gpt-2/blob/master/src/encoder.py for the rationale."""
+
+class TokenizerWrapper:
+    """A wrapper that combines an HF tokenizer and a detokenizer.
+
+    Accessing any attribute other than the ``detokenizer`` is forwarded to the
+    huggingface tokenizer.
+    """
+    def __init__(self, tokenizer, detokenizer_class=..., eos_token_ids=...) -> None: ...
+    def add_eos_token(self, token: str):  # -> None:
+        ...
+    @property
+    def has_thinking(self):  # -> bool:
+        ...
+    @property
+    def think_start(self):  # -> str | None:
+        ...
+    @property
+    def think_end(self):  # -> str | None:
+        ...
+    @property
+    def has_tool_calling(self):  # -> bool:
+        ...
+    @property
+    def tool_call_start(self):  # -> str | None:
+        ...
+    @property
+    def tool_call_end(self):  # -> str | None:
+        ...
+    @property
+    def detokenizer(self):  # -> NaiveStreamingDetokenizer:
+        """
+        Get a stateful streaming detokenizer.
+        """
+
+    def __getattr__(self, attr):  # -> set[Any] | Any:
+        ...
+    def __setattr__(self, attr, value):  # -> None:
+        ...
+
+class NewlineTokenizer(PreTrainedTokenizerFast):
+    """A tokenizer that replaces newlines with <n> and <n> with new line."""
+    def __init__(self, *args, **kwargs) -> None: ...
+    def encode(self, text, **kwargs):  # -> list[int]:
+        ...
+    def encode_batch(self, texts, **kwargs): ...
+    def decode(self, *args, **kwargs):  # -> str:
+        ...
+    def batch_decode(self, *args, **kwargs):  # -> list[str]:
+        ...
+
+def load_tokenizer(
+    model_path: Path,
+    tokenizer_config_extra=...,
+    return_tokenizer=...,
+    eos_token_ids=...,
+) -> (
+    TokenizerWrapper
+    | type[SPMStreamingDetokenizer]
+    | partial[SPMStreamingDetokenizer]
+    | type[BPEStreamingDetokenizer]
+    | type[NaiveStreamingDetokenizer]
+):
+    """Load a huggingface tokenizer and try to infer the type of streaming
+    detokenizer to use.
+
+    Note, to use a fast streaming tokenizer, pass a local file path rather than
+    a Hugging Face repo ID.
+    """
+
+def no_bos_or_eos(sequence: list, bos: int, eos: int) -> list: ...

.mlx_typings/mlx_lm/utils.pyi

@@ -0,0 +1,195 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+import os
+from pathlib import Path
+from typing import Any, Callable, Dict, Optional, Tuple, Type, Union
+
+import mlx.nn as nn
+from transformers.utils.auto_docstring import ModelArgs
+
+from .tokenizer_utils import TokenizerWrapper
+
+if os.getenv("MLXLM_USE_MODELSCOPE", "False").lower() == "true": ...
+else: ...
+MODEL_REMAPPING = ...
+MAX_FILE_SIZE_GB = ...
+
+def compute_bits_per_weight(model): ...
+def hf_repo_to_path(hf_repo):  # -> Path:
+    ...
+def load_config(model_path: Path) -> dict: ...
+def load_model(
+    model_path: Path,
+    lazy: bool = False,
+    strict: bool = True,
+    model_config: dict[str, Any] = {},
+    get_model_classes: Callable[
+        [dict[str, Any]], Tuple[Type[nn.Module], Type[ModelArgs]]
+    ] = ...,
+) -> Tuple[nn.Module, dict[str, Any]]:
+    """
+    Load and initialize the model from a given path.
+
+    Args:
+        model_path (Path): The path to load the model from.
+        lazy (bool): If False eval the model parameters to make sure they are
+            loaded in memory before returning, otherwise they will be loaded
+            when needed. Default: ``False``
+        strict (bool): Whether or not to raise an exception if weights don't
+            match. Default: ``True``
+        model_config (dict, optional): Optional configuration parameters for the
+            model. Defaults to an empty dictionary.
+        get_model_classes (Callable[[dict], Tuple[Type[nn.Module], Type]], optional):
+            A function that returns the model class and model args class given a config.
+            Defaults to the ``_get_classes`` function.
+
+    Returns:
+        Tuple[nn.Module, dict[str, Any]]: The loaded and initialized model and config.
+
+    Raises:
+        FileNotFoundError: If the weight files (.safetensors) are not found.
+        ValueError: If the model class or args class are not found or cannot be instantiated.
+    """
+
+def load(
+    path_or_hf_repo: str,
+    tokenizer_config=...,
+    model_config=...,
+    adapter_path: Optional[str] = ...,
+    lazy: bool = ...,
+    return_config: bool = ...,
+    revision: str = ...,
+) -> Union[
+    Tuple[nn.Module, TokenizerWrapper],
+    Tuple[nn.Module, TokenizerWrapper, Dict[str, Any]],
+]:
+    """
+    Load the model and tokenizer from a given path or a huggingface repository.
+
+    Args:
+        path_or_hf_repo (Path): The path or the huggingface repository to load the model from.
+        tokenizer_config (dict, optional): Configuration parameters specifically for the tokenizer.
+            Defaults to an empty dictionary.
+        model_config(dict, optional): Configuration parameters specifically for the model.
+            Defaults to an empty dictionary.
+        adapter_path (str, optional): Path to the LoRA adapters. If provided, applies LoRA layers
+            to the model. Default: ``None``.
+        lazy (bool): If ``False`` eval the model parameters to make sure they are
+            loaded in memory before returning, otherwise they will be loaded
+            when needed. Default: ``False``
+        return_config (bool: If ``True`` return the model config as the last item..
+        revision (str, optional): A revision id which can be a branch name, a tag, or a commit hash.
+    Returns:
+        Union[Tuple[nn.Module, TokenizerWrapper], Tuple[nn.Module, TokenizerWrapper, Dict[str, Any]]]:
+            A tuple containing the loaded model, tokenizer and, if requested, the model config.
+
+    Raises:
+        FileNotFoundError: If config file or safetensors are not found.
+        ValueError: If model class or args class are not found.
+    """
+
+def make_shards(weights: dict, max_file_size_gb: int = ...) -> list:
+    """
+    Splits the weights into smaller shards.
+
+    Args:
+        weights (dict): Model weights.
+        max_file_size_gb (int): Maximum size of each shard in gigabytes.
+
+    Returns:
+        list: List of weight shards.
+    """
+
+def create_model_card(
+    path: Union[str, Path], hf_path: Union[str, Path, None]
+):  # -> None:
+    """
+    Uploads the model to Hugging Face hub.
+
+    Args:
+        path (Union[str, Path]): Local path to the model.
+        hf_path (Union[str, Path, None]): Path to the original Hugging Face model.
+    """
+
+def upload_to_hub(path: str, upload_repo: str):  # -> None:
+    """
+    Uploads the model to Hugging Face hub.
+
+    Args:
+        path (str): Local path to the model.
+        upload_repo (str): Name of the HF repo to upload to.
+    """
+
+def save_model(
+    save_path: Union[str, Path], model: nn.Module, *, donate_model: bool = ...
+) -> None:
+    """Save model weights and metadata index into specified directory."""
+
+def quantize_model(
+    model: nn.Module,
+    config: dict,
+    group_size: int,
+    bits: int,
+    mode: str = ...,
+    quant_predicate: Optional[Callable[[str, nn.Module], Union[bool, dict]]] = ...,
+) -> Tuple[nn.Module, dict]:
+    """
+    Applies quantization to the model weights.
+
+    Args:
+        model (nn.Module): The model to be quantized.
+        config (dict): Model configuration.
+        group_size (int): Group size for quantization.
+        bits (int): Bits per weight for quantization.
+        mode (str): The quantization mode.
+        quant_predicate (Callable): A callable that decides how to quantize
+          each layer based on the path. Accepts the layer `path` and the
+          `module`. Returns either a bool to signify quantize/no quantize or
+          a dict of quantization parameters to pass to `to_quantized`.
+
+    Returns:
+        Tuple: Tuple containing quantized model and config.
+    """
+
+def save_config(config: dict, config_path: Union[str, Path]) -> None:
+    """Save the model configuration to the ``config_path``.
+
+    The final configuration will be sorted before saving for better readability.
+
+    Args:
+        config (dict): The model configuration.
+        config_path (Union[str, Path]): Model configuration file path.
+    """
+
+def save(
+    dst_path: Union[str, Path],
+    src_path_or_repo: Union[str, Path],
+    model: nn.Module,
+    tokenizer: TokenizerWrapper,
+    config: Dict[str, Any],
+    donate_model: bool = ...,
+):  # -> None:
+    ...
+def common_prefix_len(list1, list2):  # -> int:
+    """
+    Calculates the length of the common prefix of two lists.
+
+    Args:
+        list1: The first list of strings.
+        list2: The second list of strings.
+
+    Returns:
+        The length of the common prefix. Returns 0 if lists are empty
+        or do not match at the first element.
+    """
+
+def does_model_support_input_embeddings(model: nn.Module) -> bool:
+    """
+    Check if the model supports input_embeddings in its call signature.
+    Args:
+        model (nn.Module): The model to check.
+    Returns:
+        bool: True if the model supports input_embeddings, False otherwise.
+    """

.python-version

@@ -0,0 +1 @@
+3.13

.style.yapf

@@ -1,19 +0,0 @@
-[style]
-based_on_style = pep8
-indent_width = 2
-column_limit = 200
-allow_split_before_dict_value = False
-dedent_closing_brackets = True
-split_before_first_argument = False
-split_complex_comprehension = False
-continuation_indent_width = 2
-indent_dictionary_value = True
-allow_multiline_dictionary_keys = True
-each_dict_entry_on_separate_line = False
-allow_multiline_lambdas = True
-blank_line_before_nested_class_or_def = False
-arithmetic_precedence_indication = True
-no_spaces_around_selected_binary_operators = "*,/"
-coalesce_brackets = True
-space_between_ending_comma_and_closing_bracket = False
-split_before_expression_after_opening_paren = False

.vscode/extensions.json

@@ -0,0 +1,11 @@
+{
+    "recommendations": [
+        "detachhead.basedpyright",
+        "ms-python.python"
+    ],
+    "unwantedRecommendations": [
+        "ms-python.vscode-pylance",
+        "ms-python.pyright",
+        "ms-python.mypy-type-checker"
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "basedpyright.importStrategy": "fromEnvironment"
+}

.zed/settings.json

@@ -0,0 +1,29 @@
+// Folder-specific settings
+//
+// For a full list of overridable settings, and general information on folder-specific settings,
+// see the documentation: https://zed.dev/docs/configuring-zed#settings-files
+{
+  "lsp": {
+    "nix_python": {
+      "binary": {
+        "path": "nix",
+        "arguments": [
+          "run",
+          "--quiet",
+          "--no-warn-dirty",
+          "--no-allow-import-from-derivation",
+          "--print-build-logs",
+          "never",
+          "${projectRoot}#python-lsp",
+          "--",
+          "--stdio"
+        ]
+      }
+    }
+  },
+  "languages": {
+    "Python": {
+      "language_servers": ["nix_python"]
+    }
+  }
+}

CONTRIBUTING.md

@@ -0,0 +1,65 @@
+# Contributing to EXO
+
+Thank you for your interest in contributing to EXO!
+
+## Getting Started
+
+To run EXO from source:
+
+**Prerequisites:**
+- [uv](https://github.com/astral-sh/uv) (for Python dependency management)
+  ```bash
+  brew install uv
+  ```
+- [macmon](https://github.com/vladkens/macmon) (for hardware monitoring on Apple Silicon)
+  ```bash
+  brew install macmon
+  ```
+
+```bash
+git clone https://github.com/exo-explore/exo.git
+cd exo/dashboard
+npm install && npm run build && cd ..
+uv run exo
+```
+
+## Development
+
+EXO is built with a mix of Rust, Python, and TypeScript (Svelte for the dashboard), and the codebase is actively evolving. Before starting work:
+
+- Pull the latest source to ensure you're working with the most recent code
+- Keep your changes focused - implement one feature or fix per pull request
+- Avoid combining unrelated changes, even if they seem small
+
+This makes reviews faster and helps us maintain code quality as the project evolves.
+
+## Code Style
+
+Write pure functions where possible. When adding new code, prefer Rust unless there's a good reason otherwise. Leverage the type systems available to you - Rust's type system, Python type hints, and TypeScript types. Comments should explain why you're doing something, not what the code does - especially for non-obvious decisions.
+
+Run `nix fmt` to auto-format your code before submitting.
+
+## Testing
+
+EXO relies heavily on manual testing at this point in the project, but this is evolving. Before submitting a change, test both before and after to demonstrate how your change improves behavior. Do the best you can with the hardware you have available - if you need help testing, ask and we'll do our best to assist. Add automated tests where possible - we're actively working to substantially improve our automated testing story.
+
+## Submitting Changes
+
+1. Fork the repository
+2. Create a feature branch (`git checkout -b feature/your-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin feature/your-feature`)
+5. Open a Pull Request and follow the PR template
+
+## Reporting Issues
+
+If you find a bug or have a feature request, please open an issue on GitHub with:
+- A clear description of the problem or feature
+- Steps to reproduce (for bugs)
+- Expected vs actual behavior
+- Your environment (macOS version, hardware, etc.)
+
+## Questions?
+
+Join our community:
+- [X](https://x.com/exolabs)

Cargo.toml

@@ -0,0 +1,165 @@
+[workspace]
+resolver = "3"
+members = [
+    "rust/networking",
+    "rust/exo_pyo3_bindings",
+    "rust/system_custodian",
+    "rust/util",
+]
+
+[workspace.package]
+version = "0.0.1"
+edition = "2024"
+
+[profile.dev]
+opt-level = 1
+debug = true
+
+[profile.release]
+opt-level = 3
+
+# Common shared dependendencies configured once at the workspace
+# level, to be re-used more easily across workspace member crates.
+#
+# Common configurations include versions, paths, features, etc.
+[workspace.dependencies]
+## Crate members as common dependencies
+networking = { path = "rust/networking" }
+system_custodian = { path = "rust/system_custodian" }
+util = { path = "rust/util" }
+
+# Proc-macro authoring tools
+syn = "2.0"
+quote = "1.0"
+proc-macro2 = "1.0"
+darling = "0.20"
+
+# Macro dependecies
+extend = "1.2"
+delegate = "0.13"
+impl-trait-for-tuples = "0.2"
+clap = "4.5"
+derive_more = { version = "2.0.1", features = ["display"] }
+pin-project = "1"
+
+# Utility dependencies
+itertools = "0.14"
+thiserror = "2"
+internment = "0.8"
+recursion = "0.5"
+regex = "1.11"
+once_cell = "1.21"
+thread_local = "1.1"
+bon = "3.4"
+generativity = "1.1"
+anyhow = "1.0"
+keccak-const = "0.2"
+
+# Functional generics/lenses frameworks
+frunk_core = "0.4"
+frunk = "0.4"
+frunk_utils = "0.2"
+frunk-enum-core = "0.3"
+
+# Async dependencies
+tokio = "1.46"
+futures = "0.3"
+futures-util = "0.3"
+futures-timer = "3.0"
+
+# Data structures
+either = "1.15"
+ordered-float = "5.0"
+ahash = "0.8"
+
+# Tracing/logging
+log = "0.4"
+
+# networking
+libp2p = "0.56"
+libp2p-tcp = "0.44"
+
+[workspace.lints.rust]
+static_mut_refs = "warn"      # Or use "warn" instead of deny
+incomplete_features = "allow"
+
+# Clippy's lint category level configurations;
+# every member crate needs to inherit these by adding
+#
+#     ```toml
+#     [lints]
+#     workspace = true
+#     ```
+#
+# to their `Cargo.toml` files
+[workspace.lints.clippy]
+# Clippy lint categories meant to be enabled all at once
+correctness = { level = "deny", priority = -1 }
+suspicious = { level = "warn", priority = -1 }
+style = { level = "warn", priority = -1 }
+complexity = { level = "warn", priority = -1 }
+perf = { level = "warn", priority = -1 }
+pedantic = { level = "warn", priority = -1 }
+nursery = { level = "warn", priority = -1 }
+cargo = { level = "warn", priority = -1 }
+
+# Individual Clippy lints from the `restriction` category
+arithmetic_side_effects = "warn"
+as_conversions = "warn"
+assertions_on_result_states = "warn"
+clone_on_ref_ptr = "warn"
+decimal_literal_representation = "warn"
+default_union_representation = "warn"
+deref_by_slicing = "warn"
+disallowed_script_idents = "deny"
+else_if_without_else = "warn"
+empty_enum_variants_with_brackets = "warn"
+empty_structs_with_brackets = "warn"
+error_impl_error = "warn"
+exit = "deny"
+expect_used = "warn"
+float_cmp_const = "warn"
+get_unwrap = "warn"
+if_then_some_else_none = "warn"
+impl_trait_in_params = "warn"
+indexing_slicing = "warn"
+infinite_loop = "warn"
+let_underscore_must_use = "warn"
+let_underscore_untyped = "warn"
+lossy_float_literal = "warn"
+mem_forget = "warn"
+missing_inline_in_public_items = "warn"
+multiple_inherent_impl = "warn"
+multiple_unsafe_ops_per_block = "warn"
+mutex_atomic = "warn"
+non_zero_suggestions = "warn"
+panic = "warn"
+partial_pub_fields = "warn"
+pattern_type_mismatch = "warn"
+pub_without_shorthand = "warn"
+rc_buffer = "warn"
+rc_mutex = "warn"
+redundant_type_annotations = "warn"
+renamed_function_params = "warn"
+rest_pat_in_fully_bound_structs = "warn"
+same_name_method = "warn"
+self_named_module_files = "deny"
+semicolon_inside_block = "warn"
+shadow_same = "warn"
+shadow_unrelated = "warn"
+str_to_string = "warn"
+string_add = "warn"
+string_lit_chars_any = "warn"
+string_to_string = "warn"
+tests_outside_test_module = "warn"
+todo = "warn"
+try_err = "warn"
+undocumented_unsafe_blocks = "warn"
+unnecessary_safety_comment = "warn"
+unnecessary_safety_doc = "warn"
+unneeded_field_pattern = "warn"
+unseparated_literal_suffix = "warn"
+unused_result_ok = "warn"
+unused_trait_names = "warn"
+unwrap_used = "warn"
+verbose_file_reads = "warn"

LICENSE

@@ -1,675 +1,202 @@
-                    GNU GENERAL PUBLIC LICENSE
-                       Version 3, 29 June 2007
-
- Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
- Everyone is permitted to copy and distribute verbatim copies
- of this license document, but changing it is not allowed.
-
-                            Preamble
-
-  The GNU General Public License is a free, copyleft license for
-software and other kinds of works.
-
-  The licenses for most software and other practical works are designed
-to take away your freedom to share and change the works.  By contrast,
-the GNU General Public License is intended to guarantee your freedom to
-share and change all versions of a program--to make sure it remains free
-software for all its users.  We, the Free Software Foundation, use the
-GNU General Public License for most of our software; it applies also to
-any other work released this way by its authors.  You can apply it to
-your programs, too.
-
-  When we speak of free software, we are referring to freedom, not
-price.  Our General Public Licenses are designed to make sure that you
-have the freedom to distribute copies of free software (and charge for
-them if you wish), that you receive source code or can get it if you
-want it, that you can change the software or use pieces of it in new
-free programs, and that you know you can do these things.
-
-  To protect your rights, we need to prevent others from denying you
-these rights or asking you to surrender the rights.  Therefore, you have
-certain responsibilities if you distribute copies of the software, or if
-you modify it: responsibilities to respect the freedom of others.
-
-  For example, if you distribute copies of such a program, whether
-gratis or for a fee, you must pass on to the recipients the same
-freedoms that you received.  You must make sure that they, too, receive
-or can get the source code.  And you must show them these terms so they
-know their rights.
-
-  Developers that use the GNU GPL protect your rights with two steps:
-(1) assert copyright on the software, and (2) offer you this License
-giving you legal permission to copy, distribute and/or modify it.
-
-  For the developers' and authors' protection, the GPL clearly explains
-that there is no warranty for this free software.  For both users' and
-authors' sake, the GPL requires that modified versions be marked as
-changed, so that their problems will not be attributed erroneously to
-authors of previous versions.
-
-  Some devices are designed to deny users access to install or run
-modified versions of the software inside them, although the manufacturer
-can do so.  This is fundamentally incompatible with the aim of
-protecting users' freedom to change the software.  The systematic
-pattern of such abuse occurs in the area of products for individuals to
-use, which is precisely where it is most unacceptable.  Therefore, we
-have designed this version of the GPL to prohibit the practice for those
-products.  If such problems arise substantially in other domains, we
-stand ready to extend this provision to those domains in future versions
-of the GPL, as needed to protect the freedom of users.
-
-  Finally, every program is threatened constantly by software patents.
-States should not allow patents to restrict development and use of
-software on general-purpose computers, but in those that do, we wish to
-avoid the special danger that patents applied to a free program could
-make it effectively proprietary.  To prevent this, the GPL assures that
-patents cannot be used to render the program non-free.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.
-
-                       TERMS AND CONDITIONS
-
-  0. Definitions.
-
-  "This License" refers to version 3 of the GNU General Public License.
-
-  "Copyright" also means copyright-like laws that apply to other kinds of
-works, such as semiconductor masks.
-
-  "The Program" refers to any copyrightable work licensed under this
-License.  Each licensee is addressed as "you".  "Licensees" and
-"recipients" may be individuals or organizations.
-
-  To "modify" a work means to copy from or adapt all or part of the work
-in a fashion requiring copyright permission, other than the making of an
-exact copy.  The resulting work is called a "modified version" of the
-earlier work or a work "based on" the earlier work.
-
-  A "covered work" means either the unmodified Program or a work based
-on the Program.
-
-  To "propagate" a work means to do anything with it that, without
-permission, would make you directly or secondarily liable for
-infringement under applicable copyright law, except executing it on a
-computer or modifying a private copy.  Propagation includes copying,
-distribution (with or without modification), making available to the
-public, and in some countries other activities as well.
-
-  To "convey" a work means any kind of propagation that enables other
-parties to make or receive copies.  Mere interaction with a user through
-a computer network, with no transfer of a copy, is not conveying.
-
-  An interactive user interface displays "Appropriate Legal Notices"
-to the extent that it includes a convenient and prominently visible
-feature that (1) displays an appropriate copyright notice, and (2)
-tells the user that there is no warranty for the work (except to the
-extent that warranties are provided), that licensees may convey the
-work under this License, and how to view a copy of this License.  If
-the interface presents a list of user commands or options, such as a
-menu, a prominent item in the list meets this criterion.
-
-  1. Source Code.
-
-  The "source code" for a work means the preferred form of the work
-for making modifications to it.  "Object code" means any non-source
-form of a work.
-
-  A "Standard Interface" means an interface that either is an official
-standard defined by a recognized standards body, or, in the case of
-interfaces specified for a particular programming language, one that
-is widely used among developers working in that language.
-
-  The "System Libraries" of an executable work include anything, other
-than the work as a whole, that (a) is included in the normal form of
-packaging a Major Component, but which is not part of that Major
-Component, and (b) serves only to enable use of the work with that
-Major Component, or to implement a Standard Interface for which an
-implementation is available to the public in source code form.  A
-"Major Component", in this context, means a major essential component
-(kernel, window system, and so on) of the specific operating system
-(if any) on which the executable work runs, or a compiler used to
-produce the work, or an object code interpreter used to run it.
-
-  The "Corresponding Source" for a work in object code form means all
-the source code needed to generate, install, and (for an executable
-work) run the object code and to modify the work, including scripts to
-control those activities.  However, it does not include the work's
-System Libraries, or general-purpose tools or generally available free
-programs which are used unmodified in performing those activities but
-which are not part of the work.  For example, Corresponding Source
-includes interface definition files associated with source files for
-the work, and the source code for shared libraries and dynamically
-linked subprograms that the work is specifically designed to require,
-such as by intimate data communication or control flow between those
-subprograms and other parts of the work.
-
-  The Corresponding Source need not include anything that users
-can regenerate automatically from other parts of the Corresponding
-Source.
-
-  The Corresponding Source for a work in source code form is that
-same work.
-
-  2. Basic Permissions.
-
-  All rights granted under this License are granted for the term of
-copyright on the Program, and are irrevocable provided the stated
-conditions are met.  This License explicitly affirms your unlimited
-permission to run the unmodified Program.  The output from running a
-covered work is covered by this License only if the output, given its
-content, constitutes a covered work.  This License acknowledges your
-rights of fair use or other equivalent, as provided by copyright law.
-
-  You may make, run and propagate covered works that you do not
-convey, without conditions so long as your license otherwise remains
-in force.  You may convey covered works to others for the sole purpose
-of having them make modifications exclusively for you, or provide you
-with facilities for running those works, provided that you comply with
-the terms of this License in conveying all material for which you do
-not control copyright.  Those thus making or running the covered works
-for you must do so exclusively on your behalf, under your direction
-and control, on terms that prohibit them from making any copies of
-your copyrighted material outside their relationship with you.
-
-  Conveying under any other circumstances is permitted solely under
-the conditions stated below.  Sublicensing is not allowed; section 10
-makes it unnecessary.
-
-  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
-
-  No covered work shall be deemed part of an effective technological
-measure under any applicable law fulfilling obligations under article
-11 of the WIPO copyright treaty adopted on 20 December 1996, or
-similar laws prohibiting or restricting circumvention of such
-measures.
-
-  When you convey a covered work, you waive any legal power to forbid
-circumvention of technological measures to the extent such circumvention
-is effected by exercising rights under this License with respect to
-the covered work, and you disclaim any intention to limit operation or
-modification of the work as a means of enforcing, against the work's
-users, your or third parties' legal rights to forbid circumvention of
-technological measures.
-
-  4. Conveying Verbatim Copies.
-
-  You may convey verbatim copies of the Program's source code as you
-receive it, in any medium, provided that you conspicuously and
-appropriately publish on each copy an appropriate copyright notice;
-keep intact all notices stating that this License and any
-non-permissive terms added in accord with section 7 apply to the code;
-keep intact all notices of the absence of any warranty; and give all
-recipients a copy of this License along with the Program.
-
-  You may charge any price or no price for each copy that you convey,
-and you may offer support or warranty protection for a fee.
-
-  5. Conveying Modified Source Versions.
-
-  You may convey a work based on the Program, or the modifications to
-produce it from the Program, in the form of source code under the
-terms of section 4, provided that you also meet all of these conditions:
-
-    a) The work must carry prominent notices stating that you modified
-    it, and giving a relevant date.
-
-    b) The work must carry prominent notices stating that it is
-    released under this License and any conditions added under section
-    7.  This requirement modifies the requirement in section 4 to
-    "keep intact all notices".
-
-    c) You must license the entire work, as a whole, under this
-    License to anyone who comes into possession of a copy.  This
-    License will therefore apply, along with any applicable section 7
-    additional terms, to the whole of the work, and all its parts,
-    regardless of how they are packaged.  This License gives no
-    permission to license the work in any other way, but it does not
-    invalidate such permission if you have separately received it.
-
-    d) If the work has interactive user interfaces, each must display
-    Appropriate Legal Notices; however, if the Program has interactive
-    interfaces that do not display Appropriate Legal Notices, your
-    work need not make them do so.
-
-  A compilation of a covered work with other separate and independent
-works, which are not by their nature extensions of the covered work,
-and which are not combined with it such as to form a larger program,
-in or on a volume of a storage or distribution medium, is called an
-"aggregate" if the compilation and its resulting copyright are not
-used to limit the access or legal rights of the compilation's users
-beyond what the individual works permit.  Inclusion of a covered work
-in an aggregate does not cause this License to apply to the other
-parts of the aggregate.
-
-  6. Conveying Non-Source Forms.
-
-  You may convey a covered work in object code form under the terms
-of sections 4 and 5, provided that you also convey the
-machine-readable Corresponding Source under the terms of this License,
-in one of these ways:
-
-    a) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by the
-    Corresponding Source fixed on a durable physical medium
-    customarily used for software interchange.
-
-    b) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by a
-    written offer, valid for at least three years and valid for as
-    long as you offer spare parts or customer support for that product
-    model, to give anyone who possesses the object code either (1) a
-    copy of the Corresponding Source for all the software in the
-    product that is covered by this License, on a durable physical
-    medium customarily used for software interchange, for a price no
-    more than your reasonable cost of physically performing this
-    conveying of source, or (2) access to copy the
-    Corresponding Source from a network server at no charge.
-
-    c) Convey individual copies of the object code with a copy of the
-    written offer to provide the Corresponding Source.  This
-    alternative is allowed only occasionally and noncommercially, and
-    only if you received the object code with such an offer, in accord
-    with subsection 6b.
-
-    d) Convey the object code by offering access from a designated
-    place (gratis or for a charge), and offer equivalent access to the
-    Corresponding Source in the same way through the same place at no
-    further charge.  You need not require recipients to copy the
-    Corresponding Source along with the object code.  If the place to
-    copy the object code is a network server, the Corresponding Source
-    may be on a different server (operated by you or a third party)
-    that supports equivalent copying facilities, provided you maintain
-    clear directions next to the object code saying where to find the
-    Corresponding Source.  Regardless of what server hosts the
-    Corresponding Source, you remain obligated to ensure that it is
-    available for as long as needed to satisfy these requirements.
-
-    e) Convey the object code using peer-to-peer transmission, provided
-    you inform other peers where the object code and Corresponding
-    Source of the work are being offered to the general public at no
-    charge under subsection 6d.
-
-  A separable portion of the object code, whose source code is excluded
-from the Corresponding Source as a System Library, need not be
-included in conveying the object code work.
-
-  A "User Product" is either (1) a "consumer product", which means any
-tangible personal property which is normally used for personal, family,
-or household purposes, or (2) anything designed or sold for incorporation
-into a dwelling.  In determining whether a product is a consumer product,
-doubtful cases shall be resolved in favor of coverage.  For a particular
-product received by a particular user, "normally used" refers to a
-typical or common use of that class of product, regardless of the status
-of the particular user or of the way in which the particular user
-actually uses, or expects or is expected to use, the product.  A product
-is a consumer product regardless of whether the product has substantial
-commercial, industrial or non-consumer uses, unless such uses represent
-the only significant mode of use of the product.
-
-  "Installation Information" for a User Product means any methods,
-procedures, authorization keys, or other information required to install
-and execute modified versions of a covered work in that User Product from
-a modified version of its Corresponding Source.  The information must
-suffice to ensure that the continued functioning of the modified object
-code is in no case prevented or interfered with solely because
-modification has been made.
-
-  If you convey an object code work under this section in, or with, or
-specifically for use in, a User Product, and the conveying occurs as
-part of a transaction in which the right of possession and use of the
-User Product is transferred to the recipient in perpetuity or for a
-fixed term (regardless of how the transaction is characterized), the
-Corresponding Source conveyed under this section must be accompanied
-by the Installation Information.  But this requirement does not apply
-if neither you nor any third party retains the ability to install
-modified object code on the User Product (for example, the work has
-been installed in ROM).
-
-  The requirement to provide Installation Information does not include a
-requirement to continue to provide support service, warranty, or updates
-for a work that has been modified or installed by the recipient, or for
-the User Product in which it has been modified or installed.  Access to a
-network may be denied when the modification itself materially and
-adversely affects the operation of the network or violates the rules and
-protocols for communication across the network.
-
-  Corresponding Source conveyed, and Installation Information provided,
-in accord with this section must be in a format that is publicly
-documented (and with an implementation available to the public in
-source code form), and must require no special password or key for
-unpacking, reading or copying.
-
-  7. Additional Terms.
-
-  "Additional permissions" are terms that supplement the terms of this
-License by making exceptions from one or more of its conditions.
-Additional permissions that are applicable to the entire Program shall
-be treated as though they were included in this License, to the extent
-that they are valid under applicable law.  If additional permissions
-apply only to part of the Program, that part may be used separately
-under those permissions, but the entire Program remains governed by
-this License without regard to the additional permissions.
-
-  When you convey a copy of a covered work, you may at your option
-remove any additional permissions from that copy, or from any part of
-it.  (Additional permissions may be written to require their own
-removal in certain cases when you modify the work.)  You may place
-additional permissions on material, added by you to a covered work,
-for which you have or can give appropriate copyright permission.
-
-  Notwithstanding any other provision of this License, for material you
-add to a covered work, you may (if authorized by the copyright holders of
-that material) supplement the terms of this License with terms:
-
-    a) Disclaiming warranty or limiting liability differently from the
-    terms of sections 15 and 16 of this License; or
-
-    b) Requiring preservation of specified reasonable legal notices or
-    author attributions in that material or in the Appropriate Legal
-    Notices displayed by works containing it; or
-
-    c) Prohibiting misrepresentation of the origin of that material, or
-    requiring that modified versions of such material be marked in
-    reasonable ways as different from the original version; or
-
-    d) Limiting the use for publicity purposes of names of licensors or
-    authors of the material; or
-
-    e) Declining to grant rights under trademark law for use of some
-    trade names, trademarks, or service marks; or
-
-    f) Requiring indemnification of licensors and authors of that
-    material by anyone who conveys the material (or modified versions of
-    it) with contractual assumptions of liability to the recipient, for
-    any liability that these contractual assumptions directly impose on
-    those licensors and authors.
-
-  All other non-permissive additional terms are considered "further
-restrictions" within the meaning of section 10.  If the Program as you
-received it, or any part of it, contains a notice stating that it is
-governed by this License along with a term that is a further
-restriction, you may remove that term.  If a license document contains
-a further restriction but permits relicensing or conveying under this
-License, you may add to a covered work material governed by the terms
-of that license document, provided that the further restriction does
-not survive such relicensing or conveying.
-
-  If you add terms to a covered work in accord with this section, you
-must place, in the relevant source files, a statement of the
-additional terms that apply to those files, or a notice indicating
-where to find the applicable terms.
-
-  Additional terms, permissive or non-permissive, may be stated in the
-form of a separately written license, or stated as exceptions;
-the above requirements apply either way.
-
-  8. Termination.
-
-  You may not propagate or modify a covered work except as expressly
-provided under this License.  Any attempt otherwise to propagate or
-modify it is void, and will automatically terminate your rights under
-this License (including any patent licenses granted under the third
-paragraph of section 11).
-
-  However, if you cease all violation of this License, then your
-license from a particular copyright holder is reinstated (a)
-provisionally, unless and until the copyright holder explicitly and
-finally terminates your license, and (b) permanently, if the copyright
-holder fails to notify you of the violation by some reasonable means
-prior to 60 days after the cessation.
-
-  Moreover, your license from a particular copyright holder is
-reinstated permanently if the copyright holder notifies you of the
-violation by some reasonable means, this is the first time you have
-received notice of violation of this License (for any work) from that
-copyright holder, and you cure the violation prior to 30 days after
-your receipt of the notice.
-
-  Termination of your rights under this section does not terminate the
-licenses of parties who have received copies or rights from you under
-this License.  If your rights have been terminated and not permanently
-reinstated, you do not qualify to receive new licenses for the same
-material under section 10.
-
-  9. Acceptance Not Required for Having Copies.
-
-  You are not required to accept this License in order to receive or
-run a copy of the Program.  Ancillary propagation of a covered work
-occurring solely as a consequence of using peer-to-peer transmission
-to receive a copy likewise does not require acceptance.  However,
-nothing other than this License grants you permission to propagate or
-modify any covered work.  These actions infringe copyright if you do
-not accept this License.  Therefore, by modifying or propagating a
-covered work, you indicate your acceptance of this License to do so.
-
-  10. Automatic Licensing of Downstream Recipients.
-
-  Each time you convey a covered work, the recipient automatically
-receives a license from the original licensors, to run, modify and
-propagate that work, subject to this License.  You are not responsible
-for enforcing compliance by third parties with this License.
-
-  An "entity transaction" is a transaction transferring control of an
-organization, or substantially all assets of one, or subdividing an
-organization, or merging organizations.  If propagation of a covered
-work results from an entity transaction, each party to that
-transaction who receives a copy of the work also receives whatever
-licenses to the work the party's predecessor in interest had or could
-give under the previous paragraph, plus a right to possession of the
-Corresponding Source of the work from the predecessor in interest, if
-the predecessor has it or can get it with reasonable efforts.
-
-  You may not impose any further restrictions on the exercise of the
-rights granted or affirmed under this License.  For example, you may
-not impose a license fee, royalty, or other charge for exercise of
-rights granted under this License, and you may not initiate litigation
-(including a cross-claim or counterclaim in a lawsuit) alleging that
-any patent claim is infringed by making, using, selling, offering for
-sale, or importing the Program or any portion of it.
-
-  11. Patents.
-
-  A "contributor" is a copyright holder who authorizes use under this
-License of the Program or a work on which the Program is based.  The
-work thus licensed is called the contributor's "contributor version".
-
-  A contributor's "essential patent claims" are all patent claims
-owned or controlled by the contributor, whether already acquired or
-hereafter acquired, that would be infringed by some manner, permitted
-by this License, of making, using, or selling its contributor version,
-but do not include claims that would be infringed only as a
-consequence of further modification of the contributor version.  For
-purposes of this definition, "control" includes the right to grant
-patent sublicenses in a manner consistent with the requirements of
-this License.
-
-  Each contributor grants you a non-exclusive, worldwide, royalty-free
-patent license under the contributor's essential patent claims, to
-make, use, sell, offer for sale, import and otherwise run, modify and
-propagate the contents of its contributor version.
-
-  In the following three paragraphs, a "patent license" is any express
-agreement or commitment, however denominated, not to enforce a patent
-(such as an express permission to practice a patent or covenant not to
-sue for patent infringement).  To "grant" such a patent license to a
-party means to make such an agreement or commitment not to enforce a
-patent against the party.
-
-  If you convey a covered work, knowingly relying on a patent license,
-and the Corresponding Source of the work is not available for anyone
-to copy, free of charge and under the terms of this License, through a
-publicly available network server or other readily accessible means,
-then you must either (1) cause the Corresponding Source to be so
-available, or (2) arrange to deprive yourself of the benefit of the
-patent license for this particular work, or (3) arrange, in a manner
-consistent with the requirements of this License, to extend the patent
-license to downstream recipients.  "Knowingly relying" means you have
-actual knowledge that, but for the patent license, your conveying the
-covered work in a country, or your recipient's use of the covered work
-in a country, would infringe one or more identifiable patents in that
-country that you have reason to believe are valid.
-
-  If, pursuant to or in connection with a single transaction or
-arrangement, you convey, or propagate by procuring conveyance of, a
-covered work, and grant a patent license to some of the parties
-receiving the covered work authorizing them to use, propagate, modify
-or convey a specific copy of the covered work, then the patent license
-you grant is automatically extended to all recipients of the covered
-work and works based on it.
-
-  A patent license is "discriminatory" if it does not include within
-the scope of its coverage, prohibits the exercise of, or is
-conditioned on the non-exercise of one or more of the rights that are
-specifically granted under this License.  You may not convey a covered
-work if you are a party to an arrangement with a third party that is
-in the business of distributing software, under which you make payment
-to the third party based on the extent of your activity of conveying
-the work, and under which the third party grants, to any of the
-parties who would receive the covered work from you, a discriminatory
-patent license (a) in connection with copies of the covered work
-conveyed by you (or copies made from those copies), or (b) primarily
-for and in connection with specific products or compilations that
-contain the covered work, unless you entered into that arrangement,
-or that patent license was granted, prior to 28 March 2007.
-
-  Nothing in this License shall be construed as excluding or limiting
-any implied license or other defenses to infringement that may
-otherwise be available to you under applicable patent law.
-
-  12. No Surrender of Others' Freedom.
-
-  If conditions are imposed on you (whether by court order, agreement or
-otherwise) that contradict the conditions of this License, they do not
-excuse you from the conditions of this License.  If you cannot convey a
-covered work so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you may
-not convey it at all.  For example, if you agree to terms that obligate you
-to collect a royalty for further conveying from those to whom you convey
-the Program, the only way you could satisfy both those terms and this
-License would be to refrain entirely from conveying the Program.
-
-  13. Use with the GNU Affero General Public License.
-
-  Notwithstanding any other provision of this License, you have
-permission to link or combine any covered work with a work licensed
-under version 3 of the GNU Affero General Public License into a single
-combined work, and to convey the resulting work.  The terms of this
-License will continue to apply to the part which is the covered work,
-but the special requirements of the GNU Affero General Public License,
-section 13, concerning interaction through a network will apply to the
-combination as such.
-
-  14. Revised Versions of this License.
-
-  The Free Software Foundation may publish revised and/or new versions of
-the GNU General Public License from time to time.  Such new versions will
-be similar in spirit to the present version, but may differ in detail to
-address new problems or concerns.
-
-  Each version is given a distinguishing version number.  If the
-Program specifies that a certain numbered version of the GNU General
-Public License "or any later version" applies to it, you have the
-option of following the terms and conditions either of that numbered
-version or of any later version published by the Free Software
-Foundation.  If the Program does not specify a version number of the
-GNU General Public License, you may choose any version ever published
-by the Free Software Foundation.
-
-  If the Program specifies that a proxy can decide which future
-versions of the GNU General Public License can be used, that proxy's
-public statement of acceptance of a version permanently authorizes you
-to choose that version for the Program.
-
-  Later license versions may give you additional or different
-permissions.  However, no additional obligations are imposed on any
-author or copyright holder as a result of your choosing to follow a
-later version.
-
-  15. Disclaimer of Warranty.
-
-  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
-APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
-HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
-OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
-THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
-IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
-ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
-
-  16. Limitation of Liability.
-
-  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
-WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
-THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
-GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
-USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
-DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
-PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
-EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
-SUCH DAMAGES.
-
-  17. Interpretation of Sections 15 and 16.
-
-  If the disclaimer of warranty and limitation of liability provided
-above cannot be given local legal effect according to their terms,
-reviewing courts shall apply local law that most closely approximates
-an absolute waiver of all civil liability in connection with the
-Program, unless a warranty or assumption of liability accompanies a
-copy of the Program in return for a fee.
-
-                     END OF TERMS AND CONDITIONS
-
-            How to Apply These Terms to Your New Programs
-
-  If you develop a new program, and you want it to be of the greatest
-possible use to the public, the best way to achieve this is to make it
-free software which everyone can redistribute and change under these terms.
-
-  To do so, attach the following notices to the program.  It is safest
-to attach them to the start of each source file to most effectively
-state the exclusion of warranty; and each file should have at least
-the "copyright" line and a pointer to where the full notice is found.
-
-    <one line to give the program's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
-
-    This program is free software: you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation, either version 3 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License
-    along with this program.  If not, see <https://www.gnu.org/licenses/>.
-
-Also add information on how to contact you by electronic and paper mail.
-
-  If the program does terminal interaction, make it output a short
-notice like this when it starts in an interactive mode:
-
-    <program>  Copyright (C) <year>  <name of author>
-    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
-    This is free software, and you are welcome to redistribute it
-    under certain conditions; type `show c' for details.
-
-The hypothetical commands `show w' and `show c' should show the appropriate
-parts of the General Public License.  Of course, your program's commands
-might be different; for a GUI interface, you would use an "about box".
-
-  You should also get your employer (if you work as a programmer) or school,
-if any, to sign a "copyright disclaimer" for the program, if necessary.
-For more information on this, and how to apply and follow the GNU GPL, see
-<https://www.gnu.org/licenses/>.
-
-  The GNU General Public License does not permit incorporating your program
-into proprietary programs.  If your program is a subroutine library, you
-may consider it more useful to permit linking proprietary applications with
-the library.  If this is what you want to do, use the GNU Lesser General
-Public License instead of this License.  But first, please read
-<https://www.gnu.org/licenses/why-not-lgpl.html>.
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2025 Exo Technologies Ltd
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
 

PLATFORMS.md

@@ -0,0 +1,38 @@
+# EXO Platform support (partial roadmap)
+
+## Tier 1 support - tested and maintained
+
+Apple Silicon MacOS
+- Mac Studio: M3 Ultra
+- Mac Mini: M4 Pro
+- Macbook Pro: M5, M4 Max
+
+## Tier 2 support - checked occasionally, should run without crashing
+
+
+## Tier 3 support - minimal support and testing, but no theoretical reason it shouldnt work
+
+
+# Planned
+
+## Tier 1
+
+Linux CUDA Support
+- Nvidia DGX Spark
+
+Linux CPU Support
+
+## Tier 2
+
+Linux Vulkan Support -- depends heavily on ecosystem
+- Framework Desktop
+
+Linux CUDA Support -- depends heavily on ecosystem
+- Framework Desktop
+
+## Longer term!
+
+Windows CUDA Support
+
+Windows CPU Support
+

README.md

@@ -1,270 +1,223 @@
 <div align="center">
 
 <picture>
-  <source media="(prefers-color-scheme: light)" srcset="/docs/exo-logo-black-bg.jpg">
-  <img alt="exo logo" src="/docs/exo-logo-transparent.png" width="50%" height="50%">
+  <source media="(prefers-color-scheme: light)" srcset="/docs/imgs/exo-logo-black-bg.jpg">
+  <img alt="exo logo" src="/docs/imgs/exo-logo-transparent.png" width="50%" height="50%">
 </picture>
 
 exo: Run your own AI cluster at home with everyday devices. Maintained by [exo labs](https://x.com/exolabs).
 
-
-<h3>
-
-[Discord](https://discord.gg/EUnjGpsmWw) | [Telegram](https://t.me/+Kh-KqHTzFYg3MGNk) | [X](https://x.com/exolabs)
-
-</h3>
-
-[![GitHub Repo stars](https://img.shields.io/github/stars/exo-explore/exo)](https://github.com/exo-explore/exo/stargazers)
-[![Tests](https://dl.circleci.com/status-badge/img/circleci/TrkofJDoGzdQAeL6yVHKsg/4i5hJuafuwZYZQxbRAWS71/tree/main.svg?style=svg)](https://dl.circleci.com/status-badge/redirect/circleci/TrkofJDoGzdQAeL6yVHKsg/4i5hJuafuwZYZQxbRAWS71/tree/main)
-[![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0)
-
-<a href="https://trendshift.io/repositories/11849" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11849" alt="exo-explore%2Fexo | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+<p align="center">
+  <a href="https://discord.gg/72NsF6ux" target="_blank" rel="noopener noreferrer"><img src="https://img.shields.io/badge/Discord-Join%20Server-5865F2?logo=discord&logoColor=white" alt="Discord"></a>
+  <a href="https://x.com/exolabs" target="_blank" rel="noopener noreferrer"><img src="https://img.shields.io/twitter/follow/exolabs?style=social" alt="X"></a>
+  <a href="https://www.apache.org/licenses/LICENSE-2.0.html" target="_blank" rel="noopener noreferrer"><img src="https://img.shields.io/badge/License-Apache2.0-blue.svg" alt="License: Apache-2.0"></a>
+</p>
 
 </div>
 
 ---
 
-Forget expensive NVIDIA GPUs, unify your existing devices into one powerful GPU: iPhone, iPad, Android, Mac, Linux, pretty much any device!
-
-<div align="center">
-  <h2>Update: exo is hiring. See <a href="https://exolabs.net">here</a> for more details.</h2>
-</div>
-
-## Get Involved
-
-exo is **experimental** software. Expect bugs early on. Create issues so they can be fixed. The [exo labs](https://x.com/exolabs) team will strive to resolve issues quickly.
-
-We also welcome contributions from the community. We have a list of bounties in [this sheet](https://docs.google.com/spreadsheets/d/1cTCpTIp48UnnIvHeLEUNg1iMy_Q6lRybgECSFCoVJpE/edit?usp=sharing).
+exo connects all your devices into an AI cluster. Not only does exo enable running models larger than would fit on a single device, but with [day-0 support for RDMA over Thunderbolt](https://x.com/exolabs/status/2001817749744476256?s=20), makes models run faster as you add more devices.
 
 ## Features
 
-### Wide Model Support
+- **Automatic Device Discovery**: Devices running exo automatically discover each other - no manual configuration.
+- **RDMA over Thunderbolt**: exo ships with [day-0 support for RDMA over Thunderbolt 5](https://x.com/exolabs/status/2001817749744476256?s=20), enabling 99% reduction in latency between devices.
+- **Topology-Aware Auto Parallel**: exo figures out the best way to split your model across all available devices based on a realtime view of your device topology. It takes into account device resources and network latency/bandwidth between each link.
+- **Tensor Parallelism**: exo supports sharding models, for up to 1.8x speedup on 2 devices and 3.2x speedup on 4 devices.
+- **MLX Support**: exo uses [MLX](https://github.com/ml-explore/mlx) as an inference backend and [MLX distributed](https://ml-explore.github.io/mlx/build/html/usage/distributed.html) for distributed communication.
 
-exo supports different models including LLaMA ([MLX](exo/inference/mlx/models/llama.py) and [tinygrad](exo/inference/tinygrad/models/llama.py)), Mistral, LlaVA, Qwen, and Deepseek.
+## Benchmarks
 
-### Dynamic Model Partitioning
+<details>
+  <summary>Qwen3-235B (8-bit) on 4 × M3 Ultra Mac Studio with Tensor Parallel RDMA</summary>
+  <img src="docs/benchmarks/jeffgeerling/mac-studio-cluster-ai-full-1-qwen3-235b.jpeg" alt="Benchmark - Qwen3-235B (8-bit) on 4 × M3 Ultra Mac Studio with Tensor Parallel RDMA" width="80%" />
+  <p>
+    <strong>Source:</strong> <a href="https://www.jeffgeerling.com/blog/2025/15-tb-vram-on-mac-studio-rdma-over-thunderbolt-5">Jeff Geerling: 15 TB VRAM on Mac Studio – RDMA over Thunderbolt 5</a>
+  </p>
+</details>
 
-exo [optimally splits up models](exo/topology/ring_memory_weighted_partitioning_strategy.py) based on the current network topology and device resources available. This enables you to run larger models than you would be able to on any single device.
+<details>
+  <summary>DeepSeek v3.1 671B (8-bit) on 4 × M3 Ultra Mac Studio with Tensor Parallel RDMA</summary>
+  <img src="docs/benchmarks/jeffgeerling/mac-studio-cluster-ai-full-2-deepseek-3.1-671b.jpeg" alt="Benchmark - DeepSeek v3.1 671B (8-bit) on 4 × M3 Ultra Mac Studio with Tensor Parallel RDMA" width="80%" />
+  <p>
+    <strong>Source:</strong> <a href="https://www.jeffgeerling.com/blog/2025/15-tb-vram-on-mac-studio-rdma-over-thunderbolt-5">Jeff Geerling: 15 TB VRAM on Mac Studio – RDMA over Thunderbolt 5</a>
+  </p>
+</details>
 
-### Automatic Device Discovery
+<details>
+  <summary>Kimi K2 Thinking (native 4-bit) on 4 × M3 Ultra Mac Studio with Tensor Parallel RDMA</summary>
+  <img src="docs/benchmarks/jeffgeerling/mac-studio-cluster-ai-full-3-kimi-k2-thinking.jpeg" alt="Benchmark - Kimi K2 Thinking (native 4-bit) on 4 × M3 Ultra Mac Studio with Tensor Parallel RDMA" width="80%" />
+  <p>
+    <strong>Source:</strong> <a href="https://www.jeffgeerling.com/blog/2025/15-tb-vram-on-mac-studio-rdma-over-thunderbolt-5">Jeff Geerling: 15 TB VRAM on Mac Studio – RDMA over Thunderbolt 5</a>
+  </p>
+</details>
 
-exo will [automatically discover](https://github.com/exo-explore/exo/blob/945f90f676182a751d2ad7bcf20987ab7fe0181e/exo/orchestration/node.py#L154) other devices using the best method available. Zero manual configuration.
+---
 
-### ChatGPT-compatible API
+## Quick Start
 
-exo provides a [ChatGPT-compatible API](exo/api/chatgpt_api.py) for running models. It's a [one-line change](examples/chatgpt_api.sh) in your application to run models on your own hardware using exo.
+Devices running exo automatically discover each other, without needing any manual configuration. Each device provides an API and a dashboard for interacting with your cluster (runs at `http://localhost:52415`).
 
-### Device Equality
+There are two ways to run exo:
 
-Unlike other distributed inference frameworks, exo does not use a master-worker architecture. Instead, exo devices [connect p2p](https://github.com/exo-explore/exo/blob/945f90f676182a751d2ad7bcf20987ab7fe0181e/exo/orchestration/node.py#L161). As long as a device is connected somewhere in the network, it can be used to run models.
+### Run from Source (Mac & Linux)
 
-Exo supports different [partitioning strategies](exo/topology/partitioning_strategy.py) to split up a model across devices. The default partitioning strategy is [ring memory weighted partitioning](exo/topology/ring_memory_weighted_partitioning_strategy.py). This runs an inference in a ring where each device runs a number of model layers proportional to the memory of the device.
+**Prerequisites:**
+- [brew](https://github.com/Homebrew/brew) (for simple package management on MacOS)
+  
+  ```bash
+  /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
+  ```
+- [uv](https://github.com/astral-sh/uv) (for Python dependency management)
+- [macmon](https://github.com/vladkens/macmon) (for hardware monitoring on Apple Silicon)
+- [node](https://github.com/nodejs/node) (for building the dashboard)
+  
+  ```bash
+  brew install uv macmon node
+  ```
+- [rust](https://github.com/rust-lang/rustup) (to build Rust bindings, nightly for now)
 
-!["A screenshot of exo running 5 nodes](docs/exo-screenshot.png)
+  ```bash
+  curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
+  rustup toolchain install nightly
+  ```
 
-## Installation
+Clone the repo, build the dashboard, and run exo:
 
-The current recommended way to install exo is from source.
+```bash
+# Clone exo
+git clone https://github.com/exo-explore/exo
 
-### Prerequisites
+# Build dashboard
+cd exo/dashboard && npm install && npm run build && cd ..
 
-- Python>=3.12.0 is required because of [issues with asyncio](https://github.com/exo-explore/exo/issues/5) in previous versions.
-- For Linux with NVIDIA GPU support (Linux-only, skip if not using Linux or NVIDIA):
-  - NVIDIA driver - verify with `nvidia-smi`
-  - CUDA toolkit - install from [NVIDIA CUDA guide](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#cuda-cross-platform-installation), verify with `nvcc --version`
-  - cuDNN library - download from [NVIDIA cuDNN page](https://developer.nvidia.com/cudnn-downloads), verify installation by following [these steps](https://docs.nvidia.com/deeplearning/cudnn/latest/installation/linux.html#verifying-the-install-on-linux:~:text=at%20a%20time.-,Verifying%20the%20Install%20on%20Linux,Test%20passed!,-Upgrading%20From%20Older)
-
-### Hardware Requirements
-
-- The only requirement to run exo is to have enough memory across all your devices to fit the entire model into memory. For example, if you are running llama 3.1 8B (fp16), you need 16GB of memory across all devices. Any of the following configurations would work since they each have more than 16GB of memory in total:
-  - 2 x 8GB M3 MacBook Airs
-  - 1 x 16GB NVIDIA RTX 4070 Ti Laptop
-  - 2 x Raspberry Pi 400 with 4GB of RAM each (running on CPU) + 1 x 8GB Mac Mini
-- exo is designed to run on devices with heterogeneous capabilities. For example, you can have some devices with powerful GPUs and others with integrated GPUs or even CPUs. Adding less capable devices will slow down individual inference latency but will increase the overall throughput of the cluster.
-
-### From source
-
-
-```sh
-git clone https://github.com/exo-explore/exo.git
-cd exo
-pip install -e .
-# alternatively, with venv
-source install.sh
+# Run exo
+uv run exo
 ```
 
+This starts the exo dashboard and API at http://localhost:52415/
 
-### Troubleshooting
+### macOS App
 
-- If running on Mac, MLX has an [install guide](https://ml-explore.github.io/mlx/build/html/install.html) with troubleshooting steps.
+exo ships a macOS app that runs in the background on your Mac.
 
-### Performance
+<img src="docs/imgs/macos-app-one-macbook.png" alt="exo macOS App - running on a MacBook" width="35%" />
 
-- There are a number of things users have empirically found to improve performance on Apple Silicon Macs:
+The macOS app requires macOS Tahoe 26.2 or later.
 
-1. Upgrade to the latest version of macOS Sequoia.
-2. Run `./configure_mlx.sh`. This runs commands to optimize GPU memory allocation on Apple Silicon Macs.
+Download the latest build here: [EXO-latest.dmg](https://assets.exolabs.net/EXO-latest.dmg).
 
+The app will ask for permission to modify system settings and install a new Network profile. Improvements to this are being worked on.
 
-## Documentation
+---
 
-### Example Usage on Multiple macOS Devices
+### Using the API
 
-#### Device 1:
+If you prefer to interact with exo via the API, here is an example creating an instance of a small model (`mlx-community/Llama-3.2-1B-Instruct-4bit`), sending a chat completions request and deleting the instance.
 
-```sh
-exo
+---
+
+**1. Preview instance placements**
+
+The `/instance/previews` endpoint will preview all valid placements for your model.
+
+```bash
+curl "http://localhost:52415/instance/previews?model_id=llama-3.2-1b"
 ```
 
-#### Device 2:
-```sh
-exo
+Sample response:
+
+```json
+{
+  "previews": [
+    {
+      "model_id": "mlx-community/Llama-3.2-1B-Instruct-4bit",
+      "sharding": "Pipeline",
+      "instance_meta": "MlxRing",
+      "instance": {...},
+      "memory_delta_by_node": {"local": 729808896},
+      "error": null
+    }
+    // ...possibly more placements...
+  ]
+}
 ```
 
-That's it! No configuration required - exo will automatically discover the other device(s).
+This will return all valid placements for this model. Pick a placement that you like.
+To pick the first one, pipe into `jq`:
 
-exo starts a ChatGPT-like WebUI (powered by [tinygrad tinychat](https://github.com/tinygrad/tinygrad/tree/master/examples/tinychat)) on http://localhost:52415
+```bash
+curl "http://localhost:52415/instance/previews?model_id=llama-3.2-1b" | jq -c '.previews[] | select(.error == null) | .instance' | head -n1
+```
 
-For developers, exo also starts a ChatGPT-compatible API endpoint on http://localhost:52415/v1/chat/completions. Examples with curl:
+---
 
-#### Llama 3.2 3B:
+**2. Create a model instance**
 
-```sh
-curl http://localhost:52415/v1/chat/completions \
-  -H "Content-Type: application/json" \
+Send a POST to `/instance` with your desired placement in the `instance` field (the full payload must match types as in `CreateInstanceParams`), which you can copy from step 1:
+
+```bash
+curl -X POST http://localhost:52415/instance \
+  -H 'Content-Type: application/json' \
   -d '{
-     "model": "llama-3.2-3b",
-     "messages": [{"role": "user", "content": "What is the meaning of exo?"}],
-     "temperature": 0.7
-   }'
+    "instance": {...}
+  }'
 ```
 
-#### Llama 3.1 405B:
 
-```sh
-curl http://localhost:52415/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -d '{
-     "model": "llama-3.1-405b",
-     "messages": [{"role": "user", "content": "What is the meaning of exo?"}],
-     "temperature": 0.7
-   }'
+Sample response:
+
+```json
+{
+  "message": "Command received.",
+  "command_id": "e9d1a8ab-...."
+}
 ```
 
-#### Llava 1.5 7B (Vision Language Model):
+---
 
-```sh
-curl http://localhost:52415/v1/chat/completions \
-  -H "Content-Type: application/json" \
+**3. Send a chat completion**
+
+Now, make a POST to `/v1/chat/completions` (the same format as OpenAI's API):
+
+```bash
+curl -N -X POST http://localhost:52415/v1/chat/completions \
+  -H 'Content-Type: application/json' \
   -d '{
-     "model": "llava-1.5-7b-hf",
-     "messages": [
-      {
-        "role": "user",
-        "content": [
-          {
-            "type": "text",
-            "text": "What are these?"
-          },
-          {
-            "type": "image_url",
-            "image_url": {
-              "url": "http://images.cocodataset.org/val2017/000000039769.jpg"
-            }
-          }
-        ]
-      }
+    "model": "mlx-community/Llama-3.2-1B-Instruct-4bit",
+    "messages": [
+      {"role": "user", "content": "What is Llama 3.2 1B?"}
     ],
-     "temperature": 0.0
-   }'
+    "stream": true
+  }'
 ```
 
-### Example Usage on Multiple Heterogenous Devices (macOS + Linux)
+---
 
-#### Device 1 (macOS):
+**4. Delete the instance**
 
-```sh
-exo
+When you're done, delete the instance by its ID (find it via `/state` or `/instance` endpoints):
+
+```bash
+curl -X DELETE http://localhost:52415/instance/YOUR_INSTANCE_ID
 ```
 
-Note: We don't need to explicitly tell exo to use the **tinygrad** inference engine. **MLX** and **tinygrad** are interoperable!
+**Other useful API endpoints*:**
 
-#### Device 2 (Linux):
-```sh
-exo
-```
+- List all models: `curl http://localhost:52415/models`
+- Inspect instance IDs and deployment state: `curl http://localhost:52415/state`
 
-Linux devices will automatically default to using the **tinygrad** inference engine.
+For further details, see API types and endpoints in [src/exo/master/api.py](src/exo/master/api.py).
 
-You can read about tinygrad-specific env vars [here](https://docs.tinygrad.org/env_vars/). For example, you can configure tinygrad to use the cpu by specifying `CLANG=1`.
+---
 
-### Example Usage on a single device with "exo run" command
+## Hardware Accelerator Support
 
-```sh
-exo run llama-3.2-3b
-```
+On macOS, exo uses the GPU. On Linux, exo currently runs on CPU. We are working on extending hardware accelerator support. If you'd like support for a new hardware platform, please [search for an existing feature request](https://github.com/exo-explore/exo/issues) and add a thumbs up so we know what hardware is important to the community.
 
-With a custom prompt:
+---
 
-```sh
-exo run llama-3.2-3b --prompt "What is the meaning of exo?"
-```
+## Contributing
 
-### Model Storage
-
-Models by default are stored in `~/.cache/huggingface/hub`.
-
-You can set a different model storage location by setting the `HF_HOME` env var.
-
-## Debugging
-
-Enable debug logs with the DEBUG environment variable (0-9).
-
-```sh
-DEBUG=9 exo
-```
-
-For the **tinygrad** inference engine specifically, there is a separate DEBUG flag `TINYGRAD_DEBUG` that can be used to enable debug logs (1-6).
-
-```sh
-TINYGRAD_DEBUG=2 exo
-```
-
-## Formatting
-
-We use [yapf](https://github.com/google/yapf) to format the code. To format the code, first install the formatting requirements:
-
-```sh
-pip3 install -e '.[formatting]'
-```
-
-Then run the formatting script:
-
-```sh
-python3 format.py ./exo
-```
-
-## Known Issues
-
-- On certain versions of Python on macOS, certificates may not installed correctly, potentially causing SSL errors (e.g., when accessing huggingface.co). To resolve this, run the `Install Certificates` command, typicall as follows:
-
-```sh
-/Applications/Python 3.x/Install Certificates.command
-```
-
-- 🚧 As the library is evolving so quickly, the iOS implementation has fallen behind Python. We have decided for now not to put out the buggy iOS version and receive a bunch of GitHub issues for outdated code. We are working on solving this properly and will make an announcement when it's ready. If you would like access to the iOS implementation now, please email alex@exolabs.net with your GitHub username explaining your use-case and you will be granted access on GitHub.
-
-## Inference Engines
-
-exo supports the following inference engines:
-
-- ✅ [MLX](exo/inference/mlx/sharded_inference_engine.py)
-- ✅ [tinygrad](exo/inference/tinygrad/inference.py)
-- 🚧 [PyTorch](https://github.com/exo-explore/exo/pull/139)
-- 🚧 [llama.cpp](https://github.com/exo-explore/exo/issues/167)
-
-## Networking Modules
-
-- ✅ [GRPC](exo/networking/grpc)
-- 🚧 [Radio](TODO)
-- 🚧 [Bluetooth](TODO)
+See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on how to contribute to exo.

RULES.md

@@ -0,0 +1,84 @@
+# Repository Rules
+
+* if you see any code that violates these rules, raise it with me directly rather than trying to fix.
+  * where applicable, file a GitHub Issue.
+* adhere to these rules strictly.
+
+## General Rules
+
+* if its possible to eliminate an extra try-catch or if-statement at runtime using type-level discipline, do it!
+* name your types, functions, and classes appropriately.
+  * no three-letter acronyms.
+  * no non-standard contractions.
+  * each data type has a meaning, pick a name which is accurate and descriptive.
+  * the average layman should be able to easily understand what your function does using the function signature alone!
+    * sometimes, there will be exceptions. eg, when you're using specific technical terms that are well understood (saga, event, etc).
+    * usually, you'll think that your code is an exception to the rules, but it won't be.
+
+## State, Functions and Classes
+
+* every function, given the same inputs, should produce the same outputs. ie, no hidden state.
+* use classes to prevent fixed state from being mutated arbitrarily (unsafely); methods provide a safe way of interfacing with state.
+* if your logic doesn't mutate fixed state, it probably belongs in a standalone function rather than a class.
+* functions shouldn't usually produce side-effects (they should be computationally pure).
+  * if, for example, you're updating a state using an event (computationally pure), and you want to trigger a saga (computational side-effect), store the logic for triggering the saga into an effect handler (a function, capable of producing side-effects, that you pass into an otherwise computationally pure function, so that it may trigger side-effects safely).
+
+## Pydantic
+
+* read the Pydantic docs.
+* respect the Pydantic docs.
+* pydantic is all you need.
+* declare and re-use a central `ConfigDict` for your use-case, you'll usually want `frozen` and `strict` to be `True`.
+
+## Unique ID (UUID) Generation
+
+* inherit from Pydantic's `UUID4` class to create your own UUID class.
+* use `uuid.uuid4()` to initialize your class with a fresh UUID where possible.
+* ensure that idempotency tags are generated by taking the salted hash of persisted state.
+  * rationale: if a node crashes and resumes from an older state, it should not accidentally re-publish the same event twice under different idempotency tags. 
+  * every distinct function should feature a unique salt, so that there are no accidental collisions in idempotency tags.
+
+## Type Wrappers
+
+* reuse types that already exist in the Python standard library.
+* when two distinct data types are structurally identical (for example, different IDs which are both UUIDs but shouldn't never mixed up), make sure they can't be conflated by the type system.
+  * if you're working with a primitive data type (`str`, `int`, etc), use `NewType` (it has zero runtime overhead).
+  * if you're working with serializable data objects, consider adding a field (type `str`) that states its type.
+
+## Type Discipline
+
+* do not bypass the type-checker, preserve strict typing by any means necessary.
+* by default, use literal types (like `Literal['one', 'two']`) where an enum seems appropriate.
+
+pro-tip: Python's type system is quite complex and feature-rich, so reading the documentation is often advisable; Matt discovered that Python `typing` library allows you to check that you've implemented a `match` exhaustively using `Literal` and `get_args(type)` after reading the docs.
+
+## Use of `@final`, Freezing
+
+* use wherever applicable.
+
+## Error Handling
+
+* don't try-catch for no reason.
+* make sure that you always know where and when the exceptions your code produces are meant to be handled, so that it's never a nasty surprise.
+  * always write the rationale for your error-handling down in the docstring!
+  * communicate the details to your colleagues when appropriate.
+
+## Dependencies
+
+* don't introduce any new dependencies without asking.
+* don't ask for any dependencies that aren't ubiquitous within production environments.
+
+## Commit Messages
+
+*   use the imperative mood in the subject line.
+*   prefix the subject line with a change type. our change types are:
+    *   `documentation`: documentation changes.
+    *   `feature`: a new feature.
+    *   `refactor`: a code change that neither fixes a bug nor adds a feature.
+    *   `bugfix`: a bug fix.
+    *   `chore`: routine tasks, maintenance, or tooling changes.
+    *   `test`: adding or correcting tests.
+*   restrict the subject line to fifty characters or less.
+*   capitalize the subject line.
+*   do not end the subject line with a period.
+*   separate subject from body with a blank line.

TODO.md

@@ -0,0 +1,27 @@
+2. Currently a lot of requests from the API are timing out, but we still process those requests internally. If an API request times out, we should cancel all corresponding tasks to that API request (why process a request with nobody listening).
+3. Task cancellation. When API http request gets cancelled, it should cancel corresponding task.
+4. I'd like to see profiled network latency / bandwidth.
+5. I'd like to see how much bandwidth each link is using.
+6. We should handle the case where one machine doesn't have the model downloaded and then other machines are waiting on it. In this case we get loads of timeout errors because the others are waiting for the one that needs to download the model.
+7. Solve the problem of in continuous batching when a new prompt comes in, it will block decode of the current batch until the prefill is complete.
+8. We want people to be able to copy models over to a new device without ever connecting EXO to the internet. Right now EXO require internet connection once to cache some files to check if a download is complete. Instead, we should simply check if there is a non-empty model folder locally with no .partial files. This indicates it's a fully downloaded model that can be loaded.
+10. More granular control over how to deploy instances.
+12. Nix is great but installing it is a pain and we have ended up in a lot of cases having PATH issues or installation issues. For example, after rebooting mike it seemed to no longer have a nix installation and needed reinstalling. It has a bunch of broken symlinks left over from nix that caused ssh to fail, making it even harder to debug. We need consistent environments (perhaps MDM) so we can guarantee nix is installed properly on each machine.
+13. Memory pressure instead of memory used.
+14. Show the type of each connection (TB5, Ethernet, etc.) in the UI. Refer to old exo: https://github.com/exo-explore/exo/blob/56f783b38dc6b08ce606b07a5386dc40dae00330/exo/helpers.py#L251
+15. Prioritise certain connection types (or by latency). TB5 > Ethernet > WiFi. Refer to old exo: https://github.com/exo-explore/exo/blob/56f783b38dc6b08ce606b07a5386dc40dae00330/exo/helpers.py#L251
+16. Dynamically switch to higher priority connection when it becomes available. Probably bring back InstanceReplacedAtomically.
+17. Faster model loads by streaming model from other devices in cluster.
+18. Add support for specifying the type of network connection to use in a test. Depends on 15/16.
+20. Add chat completion cancellations (e.g OpenWebUI has something for cancelling an ongoing request).
+23. Do we need cache_limit? We went back and forth on that a lot because we thought it might be causing issues. One problem is it sets it relative to model size. So if you have multiple models loaded in it will take the most recent model size for the cache_limit. This is problematic if you launch DeepSeek -> Llama for example.
+24. further openai/lmstudio api compatibility
+25. Rethink retry logic
+26. Task cancellation. When API http request gets cancelled, it should cancel corresponding task.
+27. Log cleanup - per-module log filters and default to DEBUG log levels
+
+Potential refactors:
+
+2. Topology can be simplified
+
+Random errors we've run into:

app/EXO/EXO.xcodeproj/project.pbxproj

@@ -0,0 +1,602 @@
+// !$*UTF8*$!
+{
+	archiveVersion = 1;
+	classes = {
+	};
+	objectVersion = 77;
+	objects = {
+
+/* Begin PBXBuildFile section */
+		E0140D402ED1F909001F3171 /* exo in Resources */ = {isa = PBXBuildFile; fileRef = E0140D3F2ED1F909001F3171 /* exo */; };
+		E0A1B1002F5A000100000003 /* Sparkle in Frameworks */ = {isa = PBXBuildFile; productRef = E0A1B1002F5A000100000002 /* Sparkle */; };
+/* End PBXBuildFile section */
+
+/* Begin PBXContainerItemProxy section */
+		E0140D212ED1F79B001F3171 /* PBXContainerItemProxy */ = {
+			isa = PBXContainerItemProxy;
+			containerPortal = E0140D072ED1F79A001F3171 /* Project object */;
+			proxyType = 1;
+			remoteGlobalIDString = E0140D0E2ED1F79A001F3171;
+			remoteInfo = EXO;
+		};
+		E0140D2B2ED1F79B001F3171 /* PBXContainerItemProxy */ = {
+			isa = PBXContainerItemProxy;
+			containerPortal = E0140D072ED1F79A001F3171 /* Project object */;
+			proxyType = 1;
+			remoteGlobalIDString = E0140D0E2ED1F79A001F3171;
+			remoteInfo = EXO;
+		};
+/* End PBXContainerItemProxy section */
+
+/* Begin PBXFileReference section */
+		E0140D0F2ED1F79A001F3171 /* EXO.app */ = {isa = PBXFileReference; explicitFileType = wrapper.application; includeInIndex = 0; path = EXO.app; sourceTree = BUILT_PRODUCTS_DIR; };
+		E0140D202ED1F79B001F3171 /* EXOTests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = EXOTests.xctest; sourceTree = BUILT_PRODUCTS_DIR; };
+		E0140D2A2ED1F79B001F3171 /* EXOUITests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = EXOUITests.xctest; sourceTree = BUILT_PRODUCTS_DIR; };
+		E0140D3F2ED1F909001F3171 /* exo */ = {isa = PBXFileReference; lastKnownFileType = folder; name = exo; path = ../../dist/exo; sourceTree = "<group>"; };
+/* End PBXFileReference section */
+
+/* Begin PBXFileSystemSynchronizedRootGroup section */
+		E0140D112ED1F79A001F3171 /* EXO */ = {
+			isa = PBXFileSystemSynchronizedRootGroup;
+			path = EXO;
+			sourceTree = "<group>";
+		};
+		E0140D232ED1F79B001F3171 /* EXOTests */ = {
+			isa = PBXFileSystemSynchronizedRootGroup;
+			path = EXOTests;
+			sourceTree = "<group>";
+		};
+		E0140D2D2ED1F79B001F3171 /* EXOUITests */ = {
+			isa = PBXFileSystemSynchronizedRootGroup;
+			path = EXOUITests;
+			sourceTree = "<group>";
+		};
+/* End PBXFileSystemSynchronizedRootGroup section */
+
+/* Begin PBXFrameworksBuildPhase section */
+		E0140D0C2ED1F79A001F3171 /* Frameworks */ = {
+			isa = PBXFrameworksBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+				E0A1B1002F5A000100000003 /* Sparkle in Frameworks */,
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E0140D1D2ED1F79B001F3171 /* Frameworks */ = {
+			isa = PBXFrameworksBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E0140D272ED1F79B001F3171 /* Frameworks */ = {
+			isa = PBXFrameworksBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+/* End PBXFrameworksBuildPhase section */
+
+/* Begin PBXGroup section */
+		E0140D062ED1F79A001F3171 = {
+			isa = PBXGroup;
+			children = (
+				E0140D3F2ED1F909001F3171 /* exo */,
+				E0140D112ED1F79A001F3171 /* EXO */,
+				E0140D232ED1F79B001F3171 /* EXOTests */,
+				E0140D2D2ED1F79B001F3171 /* EXOUITests */,
+				E0140D102ED1F79A001F3171 /* Products */,
+			);
+			sourceTree = "<group>";
+		};
+		E0140D102ED1F79A001F3171 /* Products */ = {
+			isa = PBXGroup;
+			children = (
+				E0140D0F2ED1F79A001F3171 /* EXO.app */,
+				E0140D202ED1F79B001F3171 /* EXOTests.xctest */,
+				E0140D2A2ED1F79B001F3171 /* EXOUITests.xctest */,
+			);
+			name = Products;
+			sourceTree = "<group>";
+		};
+/* End PBXGroup section */
+
+/* Begin PBXNativeTarget section */
+		E0140D0E2ED1F79A001F3171 /* EXO */ = {
+			isa = PBXNativeTarget;
+			buildConfigurationList = E0140D342ED1F79B001F3171 /* Build configuration list for PBXNativeTarget "EXO" */;
+			buildPhases = (
+				E0140D0B2ED1F79A001F3171 /* Sources */,
+				E0140D0C2ED1F79A001F3171 /* Frameworks */,
+				E0140D0D2ED1F79A001F3171 /* Resources */,
+			);
+			buildRules = (
+			);
+			dependencies = (
+			);
+			fileSystemSynchronizedGroups = (
+				E0140D112ED1F79A001F3171 /* EXO */,
+			);
+			name = EXO;
+			packageProductDependencies = (
+				E0A1B1002F5A000100000002 /* Sparkle */,
+			);
+			productName = EXO;
+			productReference = E0140D0F2ED1F79A001F3171 /* EXO.app */;
+			productType = "com.apple.product-type.application";
+		};
+		E0140D1F2ED1F79B001F3171 /* EXOTests */ = {
+			isa = PBXNativeTarget;
+			buildConfigurationList = E0140D372ED1F79B001F3171 /* Build configuration list for PBXNativeTarget "EXOTests" */;
+			buildPhases = (
+				E0140D1C2ED1F79B001F3171 /* Sources */,
+				E0140D1D2ED1F79B001F3171 /* Frameworks */,
+				E0140D1E2ED1F79B001F3171 /* Resources */,
+			);
+			buildRules = (
+			);
+			dependencies = (
+				E0140D222ED1F79B001F3171 /* PBXTargetDependency */,
+			);
+			fileSystemSynchronizedGroups = (
+				E0140D232ED1F79B001F3171 /* EXOTests */,
+			);
+			name = EXOTests;
+			packageProductDependencies = (
+			);
+			productName = EXOTests;
+			productReference = E0140D202ED1F79B001F3171 /* EXOTests.xctest */;
+			productType = "com.apple.product-type.bundle.unit-test";
+		};
+		E0140D292ED1F79B001F3171 /* EXOUITests */ = {
+			isa = PBXNativeTarget;
+			buildConfigurationList = E0140D3A2ED1F79B001F3171 /* Build configuration list for PBXNativeTarget "EXOUITests" */;
+			buildPhases = (
+				E0140D262ED1F79B001F3171 /* Sources */,
+				E0140D272ED1F79B001F3171 /* Frameworks */,
+				E0140D282ED1F79B001F3171 /* Resources */,
+			);
+			buildRules = (
+			);
+			dependencies = (
+				E0140D2C2ED1F79B001F3171 /* PBXTargetDependency */,
+			);
+			fileSystemSynchronizedGroups = (
+				E0140D2D2ED1F79B001F3171 /* EXOUITests */,
+			);
+			name = EXOUITests;
+			packageProductDependencies = (
+			);
+			productName = EXOUITests;
+			productReference = E0140D2A2ED1F79B001F3171 /* EXOUITests.xctest */;
+			productType = "com.apple.product-type.bundle.ui-testing";
+		};
+/* End PBXNativeTarget section */
+
+/* Begin PBXProject section */
+		E0140D072ED1F79A001F3171 /* Project object */ = {
+			isa = PBXProject;
+			attributes = {
+				BuildIndependentTargetsInParallel = 1;
+				LastSwiftUpdateCheck = 1610;
+				LastUpgradeCheck = 1610;
+				TargetAttributes = {
+					E0140D0E2ED1F79A001F3171 = {
+						CreatedOnToolsVersion = 16.1;
+					};
+					E0140D1F2ED1F79B001F3171 = {
+						CreatedOnToolsVersion = 16.1;
+						TestTargetID = E0140D0E2ED1F79A001F3171;
+					};
+					E0140D292ED1F79B001F3171 = {
+						CreatedOnToolsVersion = 16.1;
+						TestTargetID = E0140D0E2ED1F79A001F3171;
+					};
+				};
+			};
+			buildConfigurationList = E0140D0A2ED1F79A001F3171 /* Build configuration list for PBXProject "EXO" */;
+			developmentRegion = en;
+			hasScannedForEncodings = 0;
+			knownRegions = (
+				en,
+				Base,
+			);
+			mainGroup = E0140D062ED1F79A001F3171;
+			minimizedProjectReferenceProxies = 1;
+			packageReferences = (
+				E0A1B1002F5A000100000001 /* XCRemoteSwiftPackageReference "Sparkle" */,
+			);
+			preferredProjectObjectVersion = 77;
+			productRefGroup = E0140D102ED1F79A001F3171 /* Products */;
+			projectDirPath = "";
+			projectRoot = "";
+			targets = (
+				E0140D0E2ED1F79A001F3171 /* EXO */,
+				E0140D1F2ED1F79B001F3171 /* EXOTests */,
+				E0140D292ED1F79B001F3171 /* EXOUITests */,
+			);
+		};
+/* End PBXProject section */
+
+/* Begin PBXResourcesBuildPhase section */
+		E0140D0D2ED1F79A001F3171 /* Resources */ = {
+			isa = PBXResourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+				E0140D402ED1F909001F3171 /* exo in Resources */,
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E0140D1E2ED1F79B001F3171 /* Resources */ = {
+			isa = PBXResourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E0140D282ED1F79B001F3171 /* Resources */ = {
+			isa = PBXResourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+/* End PBXResourcesBuildPhase section */
+
+/* Begin PBXSourcesBuildPhase section */
+		E0140D0B2ED1F79A001F3171 /* Sources */ = {
+			isa = PBXSourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E0140D1C2ED1F79B001F3171 /* Sources */ = {
+			isa = PBXSourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E0140D262ED1F79B001F3171 /* Sources */ = {
+			isa = PBXSourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+/* End PBXSourcesBuildPhase section */
+
+/* Begin PBXTargetDependency section */
+		E0140D222ED1F79B001F3171 /* PBXTargetDependency */ = {
+			isa = PBXTargetDependency;
+			target = E0140D0E2ED1F79A001F3171 /* EXO */;
+			targetProxy = E0140D212ED1F79B001F3171 /* PBXContainerItemProxy */;
+		};
+		E0140D2C2ED1F79B001F3171 /* PBXTargetDependency */ = {
+			isa = PBXTargetDependency;
+			target = E0140D0E2ED1F79A001F3171 /* EXO */;
+			targetProxy = E0140D2B2ED1F79B001F3171 /* PBXContainerItemProxy */;
+		};
+/* End PBXTargetDependency section */
+
+/* Begin XCBuildConfiguration section */
+		E0140D322ED1F79B001F3171 /* Debug */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				ALWAYS_SEARCH_USER_PATHS = NO;
+				ASSETCATALOG_COMPILER_GENERATE_SWIFT_ASSET_SYMBOL_EXTENSIONS = YES;
+				CLANG_ANALYZER_NONNULL = YES;
+				CLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;
+				CLANG_CXX_LANGUAGE_STANDARD = "gnu++20";
+				CLANG_ENABLE_MODULES = YES;
+				CLANG_ENABLE_OBJC_ARC = YES;
+				CLANG_ENABLE_OBJC_WEAK = YES;
+				CLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;
+				CLANG_WARN_BOOL_CONVERSION = YES;
+				CLANG_WARN_COMMA = YES;
+				CLANG_WARN_CONSTANT_CONVERSION = YES;
+				CLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;
+				CLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;
+				CLANG_WARN_DOCUMENTATION_COMMENTS = YES;
+				CLANG_WARN_EMPTY_BODY = YES;
+				CLANG_WARN_ENUM_CONVERSION = YES;
+				CLANG_WARN_INFINITE_RECURSION = YES;
+				CLANG_WARN_INT_CONVERSION = YES;
+				CLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;
+				CLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;
+				CLANG_WARN_OBJC_LITERAL_CONVERSION = YES;
+				CLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;
+				CLANG_WARN_QUOTED_INCLUDE_IN_FRAMEWORK_HEADER = YES;
+				CLANG_WARN_RANGE_LOOP_ANALYSIS = YES;
+				CLANG_WARN_STRICT_PROTOTYPES = YES;
+				CLANG_WARN_SUSPICIOUS_MOVE = YES;
+				CLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;
+				CLANG_WARN_UNREACHABLE_CODE = YES;
+				CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
+				COPY_PHASE_STRIP = NO;
+				DEBUG_INFORMATION_FORMAT = dwarf;
+				ENABLE_STRICT_OBJC_MSGSEND = YES;
+				ENABLE_TESTABILITY = YES;
+				ENABLE_USER_SCRIPT_SANDBOXING = YES;
+				GCC_C_LANGUAGE_STANDARD = gnu17;
+				GCC_DYNAMIC_NO_PIC = NO;
+				GCC_NO_COMMON_BLOCKS = YES;
+				GCC_OPTIMIZATION_LEVEL = 0;
+				GCC_PREPROCESSOR_DEFINITIONS = (
+					"DEBUG=1",
+					"$(inherited)",
+				);
+				GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
+				GCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;
+				GCC_WARN_UNDECLARED_SELECTOR = YES;
+				GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;
+				GCC_WARN_UNUSED_FUNCTION = YES;
+				GCC_WARN_UNUSED_VARIABLE = YES;
+				LOCALIZATION_PREFERS_STRING_CATALOGS = YES;
+				MACOSX_DEPLOYMENT_TARGET = 15.1;
+				MTL_ENABLE_DEBUG_INFO = INCLUDE_SOURCE;
+				MTL_FAST_MATH = YES;
+				ONLY_ACTIVE_ARCH = YES;
+				SDKROOT = macosx;
+				SWIFT_ACTIVE_COMPILATION_CONDITIONS = "DEBUG $(inherited)";
+				SWIFT_OPTIMIZATION_LEVEL = "-Onone";
+			};
+			name = Debug;
+		};
+		E0140D332ED1F79B001F3171 /* Release */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				ALWAYS_SEARCH_USER_PATHS = NO;
+				ASSETCATALOG_COMPILER_GENERATE_SWIFT_ASSET_SYMBOL_EXTENSIONS = YES;
+				CLANG_ANALYZER_NONNULL = YES;
+				CLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;
+				CLANG_CXX_LANGUAGE_STANDARD = "gnu++20";
+				CLANG_ENABLE_MODULES = YES;
+				CLANG_ENABLE_OBJC_ARC = YES;
+				CLANG_ENABLE_OBJC_WEAK = YES;
+				CLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;
+				CLANG_WARN_BOOL_CONVERSION = YES;
+				CLANG_WARN_COMMA = YES;
+				CLANG_WARN_CONSTANT_CONVERSION = YES;
+				CLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;
+				CLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;
+				CLANG_WARN_DOCUMENTATION_COMMENTS = YES;
+				CLANG_WARN_EMPTY_BODY = YES;
+				CLANG_WARN_ENUM_CONVERSION = YES;
+				CLANG_WARN_INFINITE_RECURSION = YES;
+				CLANG_WARN_INT_CONVERSION = YES;
+				CLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;
+				CLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;
+				CLANG_WARN_OBJC_LITERAL_CONVERSION = YES;
+				CLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;
+				CLANG_WARN_QUOTED_INCLUDE_IN_FRAMEWORK_HEADER = YES;
+				CLANG_WARN_RANGE_LOOP_ANALYSIS = YES;
+				CLANG_WARN_STRICT_PROTOTYPES = YES;
+				CLANG_WARN_SUSPICIOUS_MOVE = YES;
+				CLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;
+				CLANG_WARN_UNREACHABLE_CODE = YES;
+				CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
+				COPY_PHASE_STRIP = NO;
+				DEBUG_INFORMATION_FORMAT = "dwarf-with-dsym";
+				ENABLE_NS_ASSERTIONS = NO;
+				ENABLE_STRICT_OBJC_MSGSEND = YES;
+				ENABLE_USER_SCRIPT_SANDBOXING = YES;
+				GCC_C_LANGUAGE_STANDARD = gnu17;
+				GCC_NO_COMMON_BLOCKS = YES;
+				GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
+				GCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;
+				GCC_WARN_UNDECLARED_SELECTOR = YES;
+				GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;
+				GCC_WARN_UNUSED_FUNCTION = YES;
+				GCC_WARN_UNUSED_VARIABLE = YES;
+				LOCALIZATION_PREFERS_STRING_CATALOGS = YES;
+				MACOSX_DEPLOYMENT_TARGET = 15.1;
+				MTL_ENABLE_DEBUG_INFO = NO;
+				MTL_FAST_MATH = YES;
+				SDKROOT = macosx;
+				SWIFT_COMPILATION_MODE = wholemodule;
+			};
+			name = Release;
+		};
+		E0140D352ED1F79B001F3171 /* Debug */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				ASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;
+				ASSETCATALOG_COMPILER_GLOBAL_ACCENT_COLOR_NAME = AccentColor;
+				CODE_SIGN_ENTITLEMENTS = EXO/EXO.entitlements;
+				CODE_SIGN_STYLE = Automatic;
+				COMBINE_HIDPI_IMAGES = YES;
+				CURRENT_PROJECT_VERSION = 1;
+				DEVELOPMENT_ASSET_PATHS = "\"EXO/Preview Content\"";
+				ENABLE_PREVIEWS = YES;
+				GENERATE_INFOPLIST_FILE = YES;
+				INFOPLIST_FILE = EXO/Info.plist;
+				INFOPLIST_KEY_LSUIElement = YES;
+				INFOPLIST_KEY_EXOBuildCommit = "$(EXO_BUILD_COMMIT)";
+				INFOPLIST_KEY_EXOBuildTag = "$(EXO_BUILD_TAG)";
+				INFOPLIST_KEY_NSAppleEventsUsageDescription = "EXO needs to run a signed network setup script with administrator privileges.";
+				INFOPLIST_KEY_NSHumanReadableCopyright = "";
+				INFOPLIST_KEY_SUEnableAutomaticChecks = YES;
+				INFOPLIST_KEY_SUFeedURL = "$(SPARKLE_FEED_URL)";
+				INFOPLIST_KEY_SUPublicEDKey = "$(SPARKLE_ED25519_PUBLIC)";
+				LD_RUNPATH_SEARCH_PATHS = (
+					"$(inherited)",
+					"@executable_path/../Frameworks",
+				);
+				MARKETING_VERSION = 1.0.1;
+				PRODUCT_BUNDLE_IDENTIFIER = exolabs.EXO;
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				EXO_BUILD_COMMIT = local;
+				EXO_BUILD_TAG = dev;
+				SPARKLE_ED25519_PUBLIC = "";
+				SPARKLE_FEED_URL = "";
+				SWIFT_EMIT_LOC_STRINGS = YES;
+				SWIFT_VERSION = 5.0;
+			};
+			name = Debug;
+		};
+		E0140D362ED1F79B001F3171 /* Release */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				ASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;
+				ASSETCATALOG_COMPILER_GLOBAL_ACCENT_COLOR_NAME = AccentColor;
+				CODE_SIGN_ENTITLEMENTS = EXO/EXO.entitlements;
+				CODE_SIGN_STYLE = Automatic;
+				COMBINE_HIDPI_IMAGES = YES;
+				CURRENT_PROJECT_VERSION = 1;
+				DEVELOPMENT_ASSET_PATHS = "\"EXO/Preview Content\"";
+				ENABLE_PREVIEWS = YES;
+				GENERATE_INFOPLIST_FILE = YES;
+				INFOPLIST_FILE = EXO/Info.plist;
+				INFOPLIST_KEY_LSUIElement = YES;
+				INFOPLIST_KEY_EXOBuildCommit = "$(EXO_BUILD_COMMIT)";
+				INFOPLIST_KEY_EXOBuildTag = "$(EXO_BUILD_TAG)";
+				INFOPLIST_KEY_NSAppleEventsUsageDescription = "EXO needs to run a signed network setup script with administrator privileges.";
+				INFOPLIST_KEY_NSHumanReadableCopyright = "";
+				INFOPLIST_KEY_SUEnableAutomaticChecks = YES;
+				INFOPLIST_KEY_SUFeedURL = "$(SPARKLE_FEED_URL)";
+				INFOPLIST_KEY_SUPublicEDKey = "$(SPARKLE_ED25519_PUBLIC)";
+				LD_RUNPATH_SEARCH_PATHS = (
+					"$(inherited)",
+					"@executable_path/../Frameworks",
+				);
+				MARKETING_VERSION = 1.0.1;
+				PRODUCT_BUNDLE_IDENTIFIER = exolabs.EXO;
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				EXO_BUILD_COMMIT = local;
+				EXO_BUILD_TAG = dev;
+				SPARKLE_ED25519_PUBLIC = "";
+				SPARKLE_FEED_URL = "";
+				SWIFT_EMIT_LOC_STRINGS = YES;
+				SWIFT_VERSION = 5.0;
+			};
+			name = Release;
+		};
+		E0140D382ED1F79B001F3171 /* Debug */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				BUNDLE_LOADER = "$(TEST_HOST)";
+				CODE_SIGN_STYLE = Automatic;
+				CURRENT_PROJECT_VERSION = 1;
+				GENERATE_INFOPLIST_FILE = YES;
+				MACOSX_DEPLOYMENT_TARGET = 15.1;
+				MARKETING_VERSION = 1.0;
+				PRODUCT_BUNDLE_IDENTIFIER = exolabs.EXOTests;
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				SWIFT_EMIT_LOC_STRINGS = NO;
+				SWIFT_VERSION = 5.0;
+				TEST_HOST = "$(BUILT_PRODUCTS_DIR)/EXO.app/$(BUNDLE_EXECUTABLE_FOLDER_PATH)/EXO";
+			};
+			name = Debug;
+		};
+		E0140D392ED1F79B001F3171 /* Release */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				BUNDLE_LOADER = "$(TEST_HOST)";
+				CODE_SIGN_STYLE = Automatic;
+				CURRENT_PROJECT_VERSION = 1;
+				GENERATE_INFOPLIST_FILE = YES;
+				MACOSX_DEPLOYMENT_TARGET = 15.1;
+				MARKETING_VERSION = 1.0;
+				PRODUCT_BUNDLE_IDENTIFIER = exolabs.EXOTests;
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				SWIFT_EMIT_LOC_STRINGS = NO;
+				SWIFT_VERSION = 5.0;
+				TEST_HOST = "$(BUILT_PRODUCTS_DIR)/EXO.app/$(BUNDLE_EXECUTABLE_FOLDER_PATH)/EXO";
+			};
+			name = Release;
+		};
+		E0140D3B2ED1F79B001F3171 /* Debug */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				CODE_SIGN_STYLE = Automatic;
+				CURRENT_PROJECT_VERSION = 1;
+				GENERATE_INFOPLIST_FILE = YES;
+				MARKETING_VERSION = 1.0;
+				PRODUCT_BUNDLE_IDENTIFIER = exolabs.EXOUITests;
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				SWIFT_EMIT_LOC_STRINGS = NO;
+				SWIFT_VERSION = 5.0;
+				TEST_TARGET_NAME = EXO;
+			};
+			name = Debug;
+		};
+		E0140D3C2ED1F79B001F3171 /* Release */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				CODE_SIGN_STYLE = Automatic;
+				CURRENT_PROJECT_VERSION = 1;
+				GENERATE_INFOPLIST_FILE = YES;
+				MARKETING_VERSION = 1.0;
+				PRODUCT_BUNDLE_IDENTIFIER = exolabs.EXOUITests;
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				SWIFT_EMIT_LOC_STRINGS = NO;
+				SWIFT_VERSION = 5.0;
+				TEST_TARGET_NAME = EXO;
+			};
+			name = Release;
+		};
+/* End XCBuildConfiguration section */
+
+/* Begin XCConfigurationList section */
+		E0140D0A2ED1F79A001F3171 /* Build configuration list for PBXProject "EXO" */ = {
+			isa = XCConfigurationList;
+			buildConfigurations = (
+				E0140D322ED1F79B001F3171 /* Debug */,
+				E0140D332ED1F79B001F3171 /* Release */,
+			);
+			defaultConfigurationIsVisible = 0;
+			defaultConfigurationName = Release;
+		};
+		E0140D342ED1F79B001F3171 /* Build configuration list for PBXNativeTarget "EXO" */ = {
+			isa = XCConfigurationList;
+			buildConfigurations = (
+				E0140D352ED1F79B001F3171 /* Debug */,
+				E0140D362ED1F79B001F3171 /* Release */,
+			);
+			defaultConfigurationIsVisible = 0;
+			defaultConfigurationName = Release;
+		};
+		E0140D372ED1F79B001F3171 /* Build configuration list for PBXNativeTarget "EXOTests" */ = {
+			isa = XCConfigurationList;
+			buildConfigurations = (
+				E0140D382ED1F79B001F3171 /* Debug */,
+				E0140D392ED1F79B001F3171 /* Release */,
+			);
+			defaultConfigurationIsVisible = 0;
+			defaultConfigurationName = Release;
+		};
+		E0140D3A2ED1F79B001F3171 /* Build configuration list for PBXNativeTarget "EXOUITests" */ = {
+			isa = XCConfigurationList;
+			buildConfigurations = (
+				E0140D3B2ED1F79B001F3171 /* Debug */,
+				E0140D3C2ED1F79B001F3171 /* Release */,
+			);
+			defaultConfigurationIsVisible = 0;
+			defaultConfigurationName = Release;
+		};
+/* End XCConfigurationList section */
+
+/* Begin XCRemoteSwiftPackageReference section */
+		E0A1B1002F5A000100000001 /* XCRemoteSwiftPackageReference "Sparkle" */ = {
+			isa = XCRemoteSwiftPackageReference;
+			repositoryURL = "https://github.com/sparkle-project/Sparkle.git";
+			requirement = {
+				kind = upToNextMajorVersion;
+				minimumVersion = 2.8.1;
+			};
+		};
+/* End XCRemoteSwiftPackageReference section */
+
+/* Begin XCSwiftPackageProductDependency section */
+		E0A1B1002F5A000100000002 /* Sparkle */ = {
+			isa = XCSwiftPackageProductDependency;
+			package = E0A1B1002F5A000100000001 /* XCRemoteSwiftPackageReference "Sparkle" */;
+			productName = Sparkle;
+		};
+/* End XCSwiftPackageProductDependency section */
+	};
+	rootObject = E0140D072ED1F79A001F3171 /* Project object */;
+}

app/EXO/EXO.xcodeproj/project.xcworkspace/xcshareddata/swiftpm/Package.resolved

@@ -0,0 +1,15 @@
+{
+  "originHash" : "5751fcbe53b64441ed73aceb16987d6b3fc3ebc666cb9ec2de1f6a2d441f2515",
+  "pins" : [
+    {
+      "identity" : "sparkle",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/sparkle-project/Sparkle.git",
+      "state" : {
+        "revision" : "5581748cef2bae787496fe6d61139aebe0a451f6",
+        "version" : "2.8.1"
+      }
+    }
+  ],
+  "version" : 3
+}

app/EXO/EXO.xcodeproj/xcshareddata/xcschemes/EXO.xcscheme

@@ -0,0 +1,114 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<Scheme
+   LastUpgradeVersion = "1610"
+   version = "1.7">
+   <BuildAction
+      parallelizeBuildables = "YES"
+      buildImplicitDependencies = "YES"
+      buildArchitectures = "Automatic">
+      <BuildActionEntries>
+         <BuildActionEntry
+            buildForTesting = "YES"
+            buildForRunning = "YES"
+            buildForProfiling = "YES"
+            buildForArchiving = "YES"
+            buildForAnalyzing = "YES">
+            <BuildableReference
+               BuildableIdentifier = "primary"
+               BlueprintIdentifier = "E0140D0E2ED1F79A001F3171"
+               BuildableName = "EXO.app"
+               BlueprintName = "EXO"
+               ReferencedContainer = "container:EXO.xcodeproj">
+            </BuildableReference>
+         </BuildActionEntry>
+      </BuildActionEntries>
+   </BuildAction>
+   <TestAction
+      buildConfiguration = "Debug"
+      selectedDebuggerIdentifier = "Xcode.DebuggerFoundation.Debugger.LLDB"
+      selectedLauncherIdentifier = "Xcode.DebuggerFoundation.Launcher.LLDB"
+      shouldUseLaunchSchemeArgsEnv = "YES"
+      shouldAutocreateTestPlan = "YES">
+      <Testables>
+         <TestableReference
+            skipped = "NO"
+            parallelizable = "YES">
+            <BuildableReference
+               BuildableIdentifier = "primary"
+               BlueprintIdentifier = "E0140D1F2ED1F79B001F3171"
+               BuildableName = "EXOTests.xctest"
+               BlueprintName = "EXOTests"
+               ReferencedContainer = "container:EXO.xcodeproj">
+            </BuildableReference>
+         </TestableReference>
+         <TestableReference
+            skipped = "NO"
+            parallelizable = "YES">
+            <BuildableReference
+               BuildableIdentifier = "primary"
+               BlueprintIdentifier = "E0140D292ED1F79B001F3171"
+               BuildableName = "EXOUITests.xctest"
+               BlueprintName = "EXOUITests"
+               ReferencedContainer = "container:EXO.xcodeproj">
+            </BuildableReference>
+         </TestableReference>
+      </Testables>
+   </TestAction>
+   <LaunchAction
+      buildConfiguration = "Debug"
+      selectedDebuggerIdentifier = "Xcode.DebuggerFoundation.Debugger.LLDB"
+      selectedLauncherIdentifier = "Xcode.DebuggerFoundation.Launcher.LLDB"
+      launchStyle = "0"
+      useCustomWorkingDirectory = "NO"
+      ignoresPersistentStateOnLaunch = "NO"
+      debugDocumentVersioning = "YES"
+      debugServiceExtension = "internal"
+      allowLocationSimulation = "YES">
+      <BuildableProductRunnable
+         runnableDebuggingMode = "0">
+         <BuildableReference
+            BuildableIdentifier = "primary"
+            BlueprintIdentifier = "E0140D0E2ED1F79A001F3171"
+            BuildableName = "EXO.app"
+            BlueprintName = "EXO"
+            ReferencedContainer = "container:EXO.xcodeproj">
+         </BuildableReference>
+      </BuildableProductRunnable>
+      <EnvironmentVariables>
+         <EnvironmentVariable
+            key = "EXO_BUG_AWS_ACCESS_KEY_ID"
+            value = "AKIAYEKP5EMXTOBYDGHX"
+            isEnabled = "YES">
+         </EnvironmentVariable>
+         <EnvironmentVariable
+            key = "EXO_BUG_AWS_SECRET_ACCESS_KEY"
+            value = "Ep5gIlUZ1o8ssTLQwmyy34yPGfTPEYQ4evE8NdPE"
+            isEnabled = "YES">
+         </EnvironmentVariable>
+      </EnvironmentVariables>
+   </LaunchAction>
+   <ProfileAction
+      buildConfiguration = "Release"
+      shouldUseLaunchSchemeArgsEnv = "YES"
+      savedToolIdentifier = ""
+      useCustomWorkingDirectory = "NO"
+      debugDocumentVersioning = "YES">
+      <BuildableProductRunnable
+         runnableDebuggingMode = "0">
+         <BuildableReference
+            BuildableIdentifier = "primary"
+            BlueprintIdentifier = "E0140D0E2ED1F79A001F3171"
+            BuildableName = "EXO.app"
+            BlueprintName = "EXO"
+            ReferencedContainer = "container:EXO.xcodeproj">
+         </BuildableReference>
+      </BuildableProductRunnable>
+   </ProfileAction>
+   <AnalyzeAction
+      buildConfiguration = "Debug">
+   </AnalyzeAction>
+   <ArchiveAction
+      buildConfiguration = "Release"
+      revealArchiveInOrganizer = "YES">
+   </ArchiveAction>
+</Scheme>