vllm loads!

.cuda_typings/openai_harmony/__init__.pyi

@@ -0,0 +1,20 @@
+from enum import Enum
+
+class HarmonyEncodingName(Enum):
+    HARMONY_GPT_OSS = ...
+
+class HarmonyEncoding: ...
+class HarmonyError(Exception): ...
+
+class Role(Enum):
+    ASSISTANT = ...
+
+class StreamableParser:
+    last_content_delta: str
+    current_channel: str | None
+    current_recipient: str | None
+
+    def __init__(self, encoding: HarmonyEncoding, role: Role = ...) -> None: ...
+    def process(self, token_id: int) -> None: ...
+
+def load_harmony_encoding(name: HarmonyEncodingName) -> HarmonyEncoding: ...

.cuda_typings/pynvml/__init__.pyi

@@ -0,0 +1,17 @@
+class NvmlMemoryInfo:
+    used: int
+    total: int
+    free: int
+
+class NvmlUtilizationRates:
+    gpu: int
+    memory: int
+
+def nvmlInit() -> None: ...
+def nvmlShutdown() -> None: ...
+def nvmlDeviceGetCount() -> int: ...
+def nvmlDeviceGetHandleByIndex(index: int) -> object: ...
+def nvmlDeviceGetUtilizationRates(handle: object) -> NvmlUtilizationRates: ...
+def nvmlDeviceGetTemperature(handle: object, sensor_type: int) -> int: ...
+def nvmlDeviceGetPowerUsage(handle: object) -> int: ...
+def nvmlDeviceGetMemoryInfo(handle: object) -> NvmlMemoryInfo: ...

.cuda_typings/torch/__init__.pyi

@@ -0,0 +1,61 @@
+from typing import Any, Sequence
+
+from torch import backends as backends
+from torch import cuda as cuda
+from torch import distributed as distributed
+
+__version__: str
+
+class version:
+    cuda: str
+
+class dtype: ...
+
+bfloat16: dtype
+float16: dtype
+float32: dtype
+int8: dtype
+int32: dtype
+int64: dtype
+long: dtype
+float8_e4m3fn: dtype
+
+class Tensor:
+    shape: Sequence[int]
+    dtype: dtype
+    def __getitem__(self, key: Any) -> Tensor: ...
+    def __setitem__(self, key: Any, value: Any) -> None: ...
+    def to(self, *args: Any, **kwargs: Any) -> Tensor: ...
+    def cpu(self) -> Tensor: ...
+    def detach(self) -> Tensor: ...
+    def clone(self) -> Tensor: ...
+    def flatten(self, start_dim: int = 0, end_dim: int = -1) -> Tensor: ...
+    def view(self, *shape: Any) -> Tensor: ...
+    def squeeze(self, dim: int = ...) -> Tensor: ...
+    def unsqueeze(self, dim: int) -> Tensor: ...
+    def permute(self, *dims: int) -> Tensor: ...
+    def float(self) -> Tensor: ...
+    def numpy(self) -> Any: ...
+    def numel(self) -> int: ...
+    def nelement(self) -> int: ...
+    @property
+    def is_cuda(self) -> bool: ...
+    @property
+    def device(self) -> device: ...
+    def __len__(self) -> int: ...
+    def data_ptr(self) -> int: ...
+    def tolist(self) -> Any: ...
+    def abs(self) -> Tensor: ...
+    def max(self) -> Tensor: ...
+    def mean(self) -> Tensor: ...
+    def sum(self, dim: int = ...) -> Tensor: ...
+    def item(self) -> float: ...
+
+def tensor(data: Any, dtype: dtype | None = None, device: Any = None) -> Tensor: ...
+def zeros(*size: Any, dtype: dtype | None = None, device: Any = None) -> Tensor: ...
+def empty(*size: Any, dtype: dtype | None = None, device: Any = None) -> Tensor: ...
+def from_numpy(ndarray: Any) -> Tensor: ...
+def inference_mode() -> Any: ...
+
+class device:
+    def __init__(self, type: str, index: int = ...) -> None: ...

.cuda_typings/torch/backends/__init__.pyi

@@ -0,0 +1 @@
+from torch.backends import cuda as cuda

.cuda_typings/torch/backends/cuda/__init__.pyi

@@ -0,0 +1 @@
+def is_built() -> bool: ...

.cuda_typings/torch/cuda/__init__.pyi

@@ -0,0 +1,10 @@
+class _DeviceProperties:
+    total_memory: int
+
+def is_available() -> bool: ...
+def get_device_name(device: int) -> str: ...
+def get_device_properties(device: int) -> _DeviceProperties: ...
+def empty_cache() -> None: ...
+def mem_get_info() -> tuple[int, int]: ...
+def synchronize() -> None: ...
+def max_memory_allocated() -> int: ...

.cuda_typings/torch/distributed/__init__.pyi

@@ -0,0 +1,2 @@
+def is_initialized() -> bool: ...
+def destroy_process_group() -> None: ...

.cuda_typings/vllm/__init__.pyi

@@ -0,0 +1 @@
+__version__: str

.cuda_typings/vllm/config.pyi

@@ -0,0 +1,2 @@
+class ModelConfig:
+    max_model_len: int

.cuda_typings/vllm/engine/arg_utils.pyi

@@ -0,0 +1,18 @@
+from dataclasses import dataclass
+
+@dataclass
+class EngineArgs:
+    model: str = ...
+    served_model_name: str | list[str] | None = ...
+    tokenizer: str | None = ...
+    trust_remote_code: bool = ...
+    dtype: str = ...
+    seed: int = ...
+    max_model_len: int | None = ...
+    gpu_memory_utilization: float = ...
+    enforce_eager: bool = ...
+    tensor_parallel_size: int = ...
+    pipeline_parallel_size: int = ...
+    quantization: str | None = ...
+    load_format: str = ...
+    enable_sleep_mode: bool = ...

.cuda_typings/vllm/outputs.pyi

@@ -0,0 +1,17 @@
+class CompletionOutput:
+    index: int
+    text: str
+    token_ids: list[int]
+    cumulative_logprob: float | None
+    logprobs: object | None
+    finish_reason: str | None
+    stop_reason: int | str | None
+
+    def finished(self) -> bool: ...
+
+class RequestOutput:
+    request_id: str
+    prompt: str | None
+    prompt_token_ids: list[int] | None
+    outputs: list[CompletionOutput]
+    finished: bool

.cuda_typings/vllm/sampling_params.pyi

@@ -0,0 +1,11 @@
+class SamplingParams:
+    n: int
+    temperature: float
+    top_p: float
+    top_k: int
+    min_p: float
+    seed: int | None
+    stop: str | list[str] | None
+    max_tokens: int | None
+    logprobs: int | None
+    repetition_penalty: float

.cuda_typings/vllm/tokenizers/__init__.pyi

@@ -0,0 +1,3 @@
+from vllm.tokenizers.protocol import TokenizerLike
+
+__all__ = ["TokenizerLike"]

.cuda_typings/vllm/tokenizers/protocol.pyi

@@ -0,0 +1,15 @@
+from typing import Protocol
+
+class TokenizerLike(Protocol):
+    @property
+    def eos_token_id(self) -> int: ...
+    @property
+    def vocab_size(self) -> int: ...
+    def encode(self, text: str, add_special_tokens: bool = ...) -> list[int]: ...
+    def decode(self, ids: list[int] | int, skip_special_tokens: bool = ...) -> str: ...
+    def apply_chat_template(
+        self,
+        messages: list[dict[str, str]],
+        tools: list[dict[str, object]] | None = ...,
+        **kwargs: object,
+    ) -> str | list[int]: ...

.cuda_typings/vllm/v1/__init__.pyi

@@ -0,0 +1 @@
+

.cuda_typings/vllm/v1/core/__init__.pyi

@@ -0,0 +1 @@
+

.cuda_typings/vllm/v1/core/kv_cache_manager.pyi

@@ -0,0 +1,24 @@
+from collections.abc import Sequence
+
+from vllm.v1.core.kv_cache_utils import BlockPool, KVCacheBlock
+from vllm.v1.kv_cache_interface import KVCacheConfig
+
+class KVCacheBlocks:
+    blocks: tuple[Sequence[KVCacheBlock], ...]
+    def __init__(self, blocks: tuple[Sequence[KVCacheBlock], ...]) -> None: ...
+    def get_block_ids(self) -> tuple[list[int], ...]: ...
+
+class KVCacheManager:
+    block_pool: BlockPool
+    kv_cache_config: KVCacheConfig
+    enable_caching: bool
+    num_kv_cache_groups: int
+    coordinator: object
+    def __init__(self, *args: object, **kwargs: object) -> None: ...
+    def allocate_slots(
+        self, request: object, num_new_tokens: int, *args: object, **kwargs: object
+    ) -> KVCacheBlocks | None: ...
+    def get_computed_blocks(self, request: object) -> tuple[KVCacheBlocks, int]: ...
+    def create_kv_cache_blocks(
+        self, blocks: tuple[list[KVCacheBlock], ...]
+    ) -> KVCacheBlocks: ...

.cuda_typings/vllm/v1/core/kv_cache_utils.pyi

@@ -0,0 +1,16 @@
+class KVCacheBlock:
+    block_id: int
+    ref_cnt: int
+    def __init__(self, block_id: int) -> None: ...
+
+class FreeKVCacheBlockQueue:
+    def append_n(self, blocks: list[KVCacheBlock]) -> None: ...
+    def popleft_n(self, n: int) -> list[KVCacheBlock]: ...
+
+class BlockPool:
+    blocks: list[KVCacheBlock]
+    free_block_queue: FreeKVCacheBlockQueue
+    num_gpu_blocks: int
+    enable_caching: bool
+    def get_num_free_blocks(self) -> int: ...
+    def get_new_blocks(self, num_blocks: int) -> list[KVCacheBlock]: ...

.cuda_typings/vllm/v1/engine/llm_engine.pyi

@@ -0,0 +1,22 @@
+from vllm.config import ModelConfig
+from vllm.engine.arg_utils import EngineArgs
+from vllm.outputs import RequestOutput
+from vllm.sampling_params import SamplingParams
+from vllm.tokenizers import TokenizerLike
+
+class LLMEngine:
+    tokenizer: TokenizerLike | None
+    model_config: ModelConfig
+
+    @classmethod
+    def from_engine_args(cls, engine_args: EngineArgs) -> LLMEngine: ...
+    def add_request(
+        self,
+        request_id: str,
+        prompt: str,
+        params: SamplingParams,
+        arrival_time: float | None = ...,
+    ) -> None: ...
+    def step(self) -> list[RequestOutput]: ...
+    def has_unfinished_requests(self) -> bool: ...
+    def get_tokenizer(self) -> TokenizerLike: ...

.cuda_typings/vllm/v1/kv_cache_interface.pyi

@@ -0,0 +1,23 @@
+from dataclasses import dataclass
+
+@dataclass
+class KVCacheSpec:
+    block_size: int
+    num_kv_heads: int
+    head_size: int
+
+@dataclass
+class KVCacheGroupSpec:
+    layer_names: list[str]
+    kv_cache_spec: KVCacheSpec
+
+@dataclass
+class KVCacheTensorSpec:
+    shared_by: list[str]
+    size: int
+
+@dataclass
+class KVCacheConfig:
+    num_blocks: int
+    kv_cache_groups: list[KVCacheGroupSpec]
+    kv_cache_tensors: list[KVCacheTensorSpec]

.cuda_typings/vllm/v1/request.pyi

@@ -0,0 +1,6 @@
+class Request:
+    request_id: str
+    prompt_token_ids: list[int] | None
+    num_prompt_tokens: int
+    num_computed_tokens: int
+    num_tokens: int

.cuda_typings/vllm/v1/worker/__init__.pyi

@@ -0,0 +1 @@
+

.cuda_typings/vllm/v1/worker/gpu_model_runner.pyi

@@ -0,0 +1,24 @@
+import torch
+
+class _CompilationConfig:
+    static_forward_context: dict[str, object]
+
+class _ModelConfig:
+    hf_config: object
+
+class GPUModelRunner:
+    kv_caches: list[torch.Tensor]
+    compilation_config: _CompilationConfig
+    model_config: _ModelConfig | None
+    def _allocate_kv_cache_tensors(
+        self, kv_cache_config: object
+    ) -> dict[str, torch.Tensor]: ...
+    def initialize_kv_cache_tensors(
+        self, kv_cache_config: object, kernel_block_sizes: list[int]
+    ) -> dict[str, torch.Tensor]: ...
+    def _reshape_kv_cache_tensors(
+        self,
+        kv_cache_config: object,
+        raw_tensors: dict[str, torch.Tensor],
+        kernel_block_sizes: list[int],
+    ) -> dict[str, torch.Tensor]: ...

.cuda_typings/vllm/v1/worker/gpu_worker.pyi

@@ -0,0 +1,6 @@
+from vllm.v1.worker.gpu_model_runner import GPUModelRunner
+
+class Worker:
+    model_runner: GPUModelRunner
+    def determine_available_memory(self) -> int: ...
+    def initialize_from_config(self, kv_cache_config: object) -> None: ...

.cuda_typings/vllm/v1/worker/utils.pyi

@@ -0,0 +1 @@
+def extract_layer_index(layer_name: str, num_attn_module: int) -> int: ...

.envrc

@@ -1,8 +1 @@
 use flake
-
-# creates .venv if doesn't exist and loads its environment
-export VIRTUAL_ENV=".venv"
-if ! [ -d "./$VIRTUAL_ENV" ]; then
-  uv venv
-fi
-layout python

.github/workflows/build-app.yml

@@ -32,6 +32,7 @@ jobs:
       SPARKLE_ED25519_PRIVATE: ${{ secrets.SPARKLE_ED25519_PRIVATE }}
       SPARKLE_S3_BUCKET: ${{ secrets.SPARKLE_S3_BUCKET }}
       SPARKLE_S3_PREFIX: ${{ secrets.SPARKLE_S3_PREFIX }}
+      EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT: ${{ secrets.EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT }}
       AWS_REGION: ${{ secrets.AWS_REGION }}
       EXO_BUILD_NUMBER: ${{ github.run_number }}
       EXO_LIBP2P_NAMESPACE: ${{ github.ref_name }}
@@ -158,7 +159,7 @@ jobs:
           fi
 
       - name: Install Homebrew packages
-        run: brew install just awscli
+        run: brew install just awscli macmon
 
       - name: Install UV
         uses: astral-sh/setup-uv@v6
@@ -238,92 +239,10 @@ jobs:
           # Export keychain path for other steps
           echo "BUILD_KEYCHAIN_PATH=$KEYCHAIN_PATH" >> $GITHUB_ENV
 
-      # ============================================================
-      # Pre-flight credential / profile validation
-      # Runs BEFORE the ~16 min build so auth/expiry failures surface in <1 min.
-      # ============================================================
-
-      - name: Validate Apple notarization credentials
-        env:
-          APPLE_NOTARIZATION_USERNAME: ${{ secrets.APPLE_NOTARIZATION_USERNAME }}
-          APPLE_NOTARIZATION_PASSWORD: ${{ secrets.APPLE_NOTARIZATION_PASSWORD }}
-          APPLE_NOTARIZATION_TEAM: ${{ secrets.APPLE_NOTARIZATION_TEAM }}
-        run: |
-          # All-or-nothing: either all three creds are set, or none are.
-          CRED_COUNT=0
-          for v in "$APPLE_NOTARIZATION_USERNAME" "$APPLE_NOTARIZATION_PASSWORD" "$APPLE_NOTARIZATION_TEAM"; do
-            [[ -n "$v" ]] && CRED_COUNT=$((CRED_COUNT + 1))
-          done
-          if [[ "$CRED_COUNT" -eq 0 ]]; then
-            echo "No notarization credentials configured — skipping notarization for this build."
-            exit 0
-          fi
-          if [[ "$CRED_COUNT" -ne 3 ]]; then
-            echo "ERROR: partial notarization credentials set ($CRED_COUNT/3). Aborting before build."
-            exit 1
-          fi
-          # Cheap, ~5s, auth-only call. Fails instantly with a clear message if
-          # the app-specific password is stale, wrong team-id, etc.
-          echo "Verifying Apple notarization credentials via notarytool history..."
-          if ! xcrun notarytool history \
-            --apple-id "$APPLE_NOTARIZATION_USERNAME" \
-            --password "$APPLE_NOTARIZATION_PASSWORD" \
-            --team-id "$APPLE_NOTARIZATION_TEAM" >/dev/null; then
-            echo "ERROR: notarytool rejected the provided credentials. Fix before rerunning."
-            echo "Common causes: app-specific password expired/revoked, wrong team-id,"
-            echo "Apple ID not on the team, or 2FA not configured for this Apple ID."
-            exit 1
-          fi
-          echo "Apple notarization credentials OK."
-
-      - name: Validate provisioning profile expiry
-        run: |
-          PROFILE="$HOME/Library/Developer/Xcode/UserData/Provisioning Profiles/EXO.provisionprofile"
-          if [[ ! -f "$PROFILE" ]]; then
-            echo "ERROR: provisioning profile not found at $PROFILE"
-            exit 1
-          fi
-          EXPIRY=$(security cms -D -i "$PROFILE" | plutil -extract ExpirationDate raw -o - - 2>/dev/null || true)
-          if [[ -z "$EXPIRY" ]]; then
-            echo "WARNING: could not read ExpirationDate from provisioning profile; skipping expiry check."
-            exit 0
-          fi
-          # Try a couple of known plutil date formats. If none parse, skip the check rather
-          # than risk a false-positive "expired" block on a format we didn't anticipate.
-          EXPIRY_EPOCH=""
-          for fmt in "%Y-%m-%dT%H:%M:%SZ" "%Y-%m-%d %H:%M:%S %z" "%Y-%m-%d %H:%M:%S +0000"; do
-            if parsed=$(date -j -f "$fmt" "$EXPIRY" +%s 2>/dev/null); then
-              EXPIRY_EPOCH="$parsed"
-              break
-            fi
-          done
-          if [[ -z "$EXPIRY_EPOCH" ]]; then
-            echo "WARNING: could not parse ExpirationDate '$EXPIRY'; skipping expiry check."
-            exit 0
-          fi
-          NOW_EPOCH=$(date +%s)
-          if [[ "$EXPIRY_EPOCH" -le "$NOW_EPOCH" ]]; then
-            echo "ERROR: provisioning profile expired on $EXPIRY. Regenerate it before rerunning."
-            exit 1
-          fi
-          DAYS_LEFT=$(( (EXPIRY_EPOCH - NOW_EPOCH) / 86400 ))
-          echo "Provisioning profile valid until $EXPIRY ($DAYS_LEFT days remaining)."
-          if [[ "$DAYS_LEFT" -lt 14 ]]; then
-            echo "WARNING: profile expires in under 14 days — regenerate soon."
-          fi
-
       # ============================================================
       # Build the bundle
       # ============================================================
 
-      - name: Add pinned macmon to PATH
-        run: |
-          MACMON_DIR=$(nix develop --command sh -c 'dirname $(which macmon)')
-          echo "Using macmon from: $MACMON_DIR"
-          echo "$MACMON_DIR" >> $GITHUB_PATH
-          # Remove any Homebrew macmon so PyInstaller can't accidentally pick it up
-          brew uninstall macmon 2>/dev/null || true
-
       - name: Build PyInstaller bundle
         run: uv run pyinstaller packaging/pyinstaller/exo.spec
 
@@ -346,6 +265,7 @@ jobs:
             EXO_BUILD_COMMIT="$GITHUB_SHA" \
             SPARKLE_FEED_URL="$SPARKLE_FEED_URL" \
             SPARKLE_ED25519_PUBLIC="$SPARKLE_ED25519_PUBLIC" \
+            EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT="$EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT" \
             CODE_SIGNING_IDENTITY="$SIGNING_IDENTITY" \
             CODE_SIGN_INJECT_BASE_ENTITLEMENTS=YES
           mkdir -p ../../output
@@ -378,41 +298,11 @@ jobs:
           APPLE_NOTARIZATION_PASSWORD: ${{ secrets.APPLE_NOTARIZATION_PASSWORD }}
           APPLE_NOTARIZATION_TEAM: ${{ secrets.APPLE_NOTARIZATION_TEAM }}
         run: |
-          set -o pipefail
           cd output
           security unlock-keychain -p "$MACOS_CERTIFICATE_PASSWORD" "$BUILD_KEYCHAIN_PATH"
           SIGNING_IDENTITY=$(security find-identity -v -p codesigning "$BUILD_KEYCHAIN_PATH" | awk -F '"' '{print $2}')
-
-          # Fail fast if notarization creds are partial. All-or-nothing.
-          CRED_COUNT=0
-          for v in "$APPLE_NOTARIZATION_USERNAME" "$APPLE_NOTARIZATION_PASSWORD" "$APPLE_NOTARIZATION_TEAM"; do
-            [[ -n "$v" ]] && CRED_COUNT=$((CRED_COUNT + 1))
-          done
-          if [[ "$CRED_COUNT" -ne 0 && "$CRED_COUNT" -ne 3 ]]; then
-            echo "ERROR: partial Apple notarization credentials set ($CRED_COUNT/3). Aborting."
-            exit 1
-          fi
-
           /usr/bin/codesign --deep --force --timestamp --options runtime \
             --sign "$SIGNING_IDENTITY" EXO.app
-
-          # Pre-flight: verify the signed app BEFORE building DMG and submitting to Apple.
-          # If this fails, notarization will fail too — cheap way to fail in seconds, not 15 minutes.
-          echo "===== codesign --verify EXO.app ====="
-          if ! /usr/bin/codesign --verify --deep --strict --verbose=2 EXO.app; then
-            echo "ERROR: EXO.app failed codesign verification. Dumping signing status of every executable:"
-            find EXO.app -type f \( -perm -111 -o -name "*.dylib" -o -name "*.so" -o -name "*.framework" \) -print0 |
-              while IFS= read -r -d '' f; do
-                printf -- '--- %s\n' "$f"
-                /usr/bin/codesign -dv --verbose=2 "$f" 2>&1 | sed 's/^/    /' || true
-              done
-            exit 1
-          fi
-
-          # Gatekeeper assessment. A failure here strongly predicts notarization rejection.
-          echo "===== spctl assessment (predicts notarization outcome) ====="
-          /usr/bin/spctl -a -vvv -t install EXO.app || echo "WARNING: spctl assessment failed — notarization is likely to fail too."
-
           mkdir -p dmg-root
           cp -R EXO.app dmg-root/
           ln -s /Applications dmg-root/Applications
@@ -420,22 +310,12 @@ jobs:
           hdiutil create -volname "EXO" -srcfolder dmg-root -ov -format UDZO "$DMG_NAME"
           /usr/bin/codesign --force --timestamp --options runtime \
             --sign "$SIGNING_IDENTITY" "$DMG_NAME"
-
-          echo "===== codesign --verify DMG ====="
-          if ! /usr/bin/codesign --verify --verbose=2 "$DMG_NAME"; then
-            echo "ERROR: DMG failed codesign verification."
-            exit 1
-          fi
-
           if [[ -n "$APPLE_NOTARIZATION_USERNAME" ]]; then
-            echo "===== notarytool submit ====="
-            # `|| true` so set -e doesn't abort before we can echo output / fetch the log.
-            # We rely on the parsed STATUS below to decide pass/fail.
             SUBMISSION_OUTPUT=$(xcrun notarytool submit "$DMG_NAME" \
               --apple-id "$APPLE_NOTARIZATION_USERNAME" \
               --password "$APPLE_NOTARIZATION_PASSWORD" \
               --team-id "$APPLE_NOTARIZATION_TEAM" \
-              --wait --timeout 15m 2>&1) || true
+              --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}')

.github/workflows/pipeline.yml

@@ -91,6 +91,9 @@ jobs:
             nix build .#metal-toolchain
           fi
 
+          # Build mlx (depends on metal-toolchain)
+          nix build .#mlx
+
       - name: Build all Nix outputs
         run: |
           nix flake show --json | jq -r '

.gitignore

@@ -18,6 +18,7 @@ digest.txt
 app/EXO/build/
 dist/
 
+
 # rust
 target/
 **/*.rs.bk
@@ -37,7 +38,3 @@ bench/**/*.json
 
 # tmp
 tmp/models
-/build/exo
-/.claude/skills
-/.claude
-/.codex

.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

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

@@ -4,7 +4,7 @@
     <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="RuffConfiguration">
-    <option name="enabled" value="true" />
+  <component name="PythonCompatibilityInspectionAdvertiser">
+    <option name="version" value="3" />
   </component>
 </project>

.typings/mflux/callbacks/callback.pyi

@@ -2,10 +2,11 @@
 This type stub file was generated by pyright.
 """
 
+from typing import Protocol
+
 import mlx.core as mx
 import PIL.Image
 import tqdm
-from typing import Protocol
 from mflux.models.common.config.config import Config
 
 class BeforeLoopCallback(Protocol):

.typings/mflux/callbacks/callback_registry.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import TYPE_CHECKING
+
 from mflux.callbacks.callback import (
     AfterLoopCallback,
     BeforeLoopCallback,

.typings/mflux/callbacks/generation_context.pyi

@@ -2,10 +2,11 @@
 This type stub file was generated by pyright.
 """
 
+from typing import TYPE_CHECKING
+
 import mlx.core as mx
 import PIL.Image
 import tqdm
-from typing import TYPE_CHECKING
 from mflux.callbacks.callback_registry import CallbackRegistry
 from mflux.models.common.config.config import Config
 

.typings/mflux/models/common/config/config.pyi

@@ -2,11 +2,12 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from pathlib import Path
 from typing import Any
-from tqdm import tqdm
+
+import mlx.core as mx
 from mflux.models.common.config.model_config import ModelConfig
+from tqdm import tqdm
 
 logger = ...
 

.typings/mflux/models/common/config/model_config.pyi

@@ -2,10 +2,11 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from functools import lru_cache
 from typing import Literal
 
+import mlx.core as mx
+
 class ModelConfig:
     precision: mx.Dtype = ...
     def __init__(

.typings/mflux/models/common/latent_creator/latent_creator.pyi

@@ -2,10 +2,10 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from pathlib import Path
 from typing import TYPE_CHECKING, TypeAlias
-from mlx import nn
+
+import mlx.core as mx
 from mflux.models.common.vae.tiling_config import TilingConfig
 from mflux.models.fibo.latent_creator.fibo_latent_creator import FiboLatentCreator
 from mflux.models.flux.latent_creator.flux_latent_creator import FluxLatentCreator
@@ -13,6 +13,7 @@ from mflux.models.qwen.latent_creator.qwen_latent_creator import QwenLatentCreat
 from mflux.models.z_image.latent_creator.z_image_latent_creator import (
     ZImageLatentCreator,
 )
+from mlx import nn
 
 if TYPE_CHECKING:
     LatentCreatorType: TypeAlias = type[

.typings/mflux/models/common/lora/layer/fused_linear_lora_layer.pyi

@@ -2,8 +2,8 @@
 This type stub file was generated by pyright.
 """
 
-from mlx import nn
 from mflux.models.common.lora.layer.linear_lora_layer import LoRALinear
+from mlx import nn
 
 class FusedLoRALinear(nn.Module):
     def __init__(

.typings/mflux/models/common/lora/mapping/lora_loader.pyi

@@ -2,10 +2,11 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
-import mlx.nn as nn
 from collections.abc import Callable
 from dataclasses import dataclass
+
+import mlx.core as mx
+import mlx.nn as nn
 from mflux.models.common.lora.mapping.lora_mapping import LoRATarget
 
 @dataclass

.typings/mflux/models/common/lora/mapping/lora_mapping.pyi

@@ -2,11 +2,12 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from collections.abc import Callable
 from dataclasses import dataclass
 from typing import List, Protocol
 
+import mlx.core as mx
+
 @dataclass
 class LoRATarget:
     model_path: str

.typings/mflux/models/common/resolution/actions.pyi

@@ -36,4 +36,3 @@ class Rule(NamedTuple):
     name: str
     check: str
     action: QuantizationAction | PathAction | LoraAction | ConfigAction
-    ...

.typings/mflux/models/common/resolution/config_resolution.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import TYPE_CHECKING
+
 from mflux.models.common.config.model_config import ModelConfig
 
 if TYPE_CHECKING: ...

.typings/mflux/models/common/schedulers/base_scheduler.pyi

@@ -2,9 +2,10 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from abc import ABC, abstractmethod
 
+import mlx.core as mx
+
 class BaseScheduler(ABC):
     @property
     @abstractmethod

.typings/mflux/models/common/schedulers/flow_match_euler_discrete_scheduler.pyi

@@ -2,8 +2,9 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from typing import TYPE_CHECKING
+
+import mlx.core as mx
 from mflux.models.common.config.config import Config
 from mflux.models.common.schedulers.base_scheduler import BaseScheduler
 

.typings/mflux/models/common/schedulers/linear_scheduler.pyi

@@ -2,8 +2,9 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from typing import TYPE_CHECKING
+
+import mlx.core as mx
 from mflux.models.common.config.config import Config
 from mflux.models.common.schedulers.base_scheduler import BaseScheduler
 

.typings/mflux/models/common/schedulers/seedvr2_euler_scheduler.pyi

@@ -2,8 +2,9 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from typing import TYPE_CHECKING
+
+import mlx.core as mx
 from mflux.models.common.config.config import Config
 from mflux.models.common.schedulers.base_scheduler import BaseScheduler
 

.typings/mflux/models/common/tokenizer/tokenizer.pyi

@@ -4,9 +4,10 @@ This type stub file was generated by pyright.
 
 from abc import ABC, abstractmethod
 from typing import Protocol, runtime_checkable
+
+from mflux.models.common.tokenizer.tokenizer_output import TokenizerOutput
 from PIL import Image
 from transformers import PreTrainedTokenizer
-from mflux.models.common.tokenizer.tokenizer_output import TokenizerOutput
 
 """
 This type stub file was generated by pyright.

.typings/mflux/models/common/tokenizer/tokenizer_loader.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import TYPE_CHECKING
+
 from mflux.models.common.tokenizer.tokenizer import BaseTokenizer
 from mflux.models.common.weights.loading.weight_definition import TokenizerDefinition
 

.typings/mflux/models/common/tokenizer/tokenizer_output.pyi

@@ -2,9 +2,10 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from dataclasses import dataclass
 
+import mlx.core as mx
+
 """
 This type stub file was generated by pyright.
 """

.typings/mflux/models/common/vae/vae_tiler.pyi

@@ -2,9 +2,10 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from typing import Callable
 
+import mlx.core as mx
+
 class VAETiler:
     @staticmethod
     def encode_image_tiled(

.typings/mflux/models/common/vae/vae_util.pyi

@@ -3,8 +3,8 @@ This type stub file was generated by pyright.
 """
 
 import mlx.core as mx
-from mlx import nn
 from mflux.models.common.vae.tiling_config import TilingConfig
+from mlx import nn
 
 class VAEUtil:
     @staticmethod

.typings/mflux/models/common/weights/loading/weight_applier.pyi

@@ -2,8 +2,9 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.nn as nn
 from typing import TYPE_CHECKING
+
+import mlx.nn as nn
 from mflux.models.common.weights.loading.loaded_weights import LoadedWeights
 from mflux.models.common.weights.loading.weight_definition import (
     ComponentDefinition,

.typings/mflux/models/common/weights/loading/weight_definition.pyi

@@ -2,11 +2,12 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from dataclasses import dataclass
-from typing import Callable, List, TYPE_CHECKING, TypeAlias
-from mflux.models.common.weights.mapping.weight_mapping import WeightTarget
+from typing import TYPE_CHECKING, Callable, List, TypeAlias
+
+import mlx.core as mx
 from mflux.models.common.tokenizer.tokenizer import BaseTokenizer
+from mflux.models.common.weights.mapping.weight_mapping import WeightTarget
 from mflux.models.depth_pro.weights.depth_pro_weight_definition import (
     DepthProWeightDefinition,
 )

.typings/mflux/models/common/weights/loading/weight_loader.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import TYPE_CHECKING
+
 from mflux.models.common.weights.loading.loaded_weights import LoadedWeights
 from mflux.models.common.weights.loading.weight_definition import (
     ComponentDefinition,

.typings/mflux/models/common/weights/mapping/weight_mapper.pyi

@@ -2,8 +2,9 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from typing import Dict, List, Optional
+
+import mlx.core as mx
 from mflux.models.common.weights.mapping.weight_mapping import WeightTarget
 
 class WeightMapper:

.typings/mflux/models/common/weights/mapping/weight_mapping.pyi

@@ -2,10 +2,11 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from dataclasses import dataclass
 from typing import Callable, List, Optional, Protocol
 
+import mlx.core as mx
+
 """
 This type stub file was generated by pyright.
 """

.typings/mflux/models/common/weights/saving/model_saver.pyi

@@ -2,7 +2,8 @@
 This type stub file was generated by pyright.
 """
 
-from typing import Any, TYPE_CHECKING
+from typing import TYPE_CHECKING, Any
+
 from mflux.models.common.weights.loading.weight_definition import WeightDefinitionType
 
 if TYPE_CHECKING: ...

.typings/mflux/models/depth_pro/model/depth_pro.pyi

@@ -2,9 +2,10 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from dataclasses import dataclass
 from pathlib import Path
+
+import mlx.core as mx
 from PIL import Image
 
 @dataclass
@@ -13,7 +14,6 @@ class DepthResult:
     depth_array: mx.array
     min_depth: float
     max_depth: float
-    ...
 
 class DepthPro:
     def __init__(self, quantize: int | None = ...) -> None: ...

.typings/mflux/models/depth_pro/weights/depth_pro_weight_definition.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.loading.weight_definition import (
     ComponentDefinition,
     TokenizerDefinition,

.typings/mflux/models/depth_pro/weights/depth_pro_weight_mapping.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.mapping.weight_mapping import (
     WeightMapping,
     WeightTarget,

.typings/mflux/models/fibo/weights/fibo_weight_definition.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.loading.weight_definition import (
     ComponentDefinition,
     TokenizerDefinition,

.typings/mflux/models/fibo/weights/fibo_weight_mapping.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.mapping.weight_mapping import (
     WeightMapping,
     WeightTarget,

.typings/mflux/models/fibo_vlm/tokenizer/qwen2vl_processor.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import Optional, Union
+
 from PIL import Image
 
 class Qwen2VLProcessor:

.typings/mflux/models/fibo_vlm/weights/fibo_vlm_weight_definition.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.loading.weight_definition import (
     ComponentDefinition,
     TokenizerDefinition,

.typings/mflux/models/fibo_vlm/weights/fibo_vlm_weight_mapping.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.mapping.weight_mapping import (
     WeightMapping,
     WeightTarget,

.typings/mflux/models/flux/model/flux_transformer/joint_attention.pyi

@@ -2,9 +2,10 @@
 This type stub file was generated by pyright.
 """
 
+from typing import Any
+
 import mlx.core as mx
 from mlx import nn
-from typing import Any
 
 class JointAttention(nn.Module):
     num_heads: int

.typings/mflux/models/flux/model/flux_transformer/joint_transformer_block.pyi

@@ -2,13 +2,14 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
-from mlx import nn
 from typing import Any
-from mflux.models.flux.model.flux_transformer.joint_attention import JointAttention
+
+import mlx.core as mx
 from mflux.models.flux.model.flux_transformer.ada_layer_norm_zero import (
     AdaLayerNormZero,
 )
+from mflux.models.flux.model.flux_transformer.joint_attention import JointAttention
+from mlx import nn
 
 class JointTransformerBlock(nn.Module):
     attn: JointAttention

.typings/mflux/models/flux/model/flux_transformer/single_transformer_block.pyi

@@ -2,15 +2,16 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
-from mlx import nn
 from typing import Any
-from mflux.models.flux.model.flux_transformer.single_block_attention import (
-    SingleBlockAttention,
-)
+
+import mlx.core as mx
 from mflux.models.flux.model.flux_transformer.ada_layer_norm_zero_single import (
     AdaLayerNormZeroSingle,
 )
+from mflux.models.flux.model.flux_transformer.single_block_attention import (
+    SingleBlockAttention,
+)
+from mlx import nn
 
 class SingleTransformerBlock(nn.Module):
     attn: SingleBlockAttention

.typings/mflux/models/flux/model/flux_transformer/time_text_embed.pyi

@@ -3,8 +3,8 @@ This type stub file was generated by pyright.
 """
 
 import mlx.core as mx
-from mlx import nn
 from mflux.models.common.config import ModelConfig
+from mlx import nn
 
 class TimeTextEmbed(nn.Module):
     def __init__(self, model_config: ModelConfig) -> None: ...

.typings/mflux/models/flux/model/flux_transformer/transformer.pyi

@@ -3,17 +3,17 @@ This type stub file was generated by pyright.
 """
 
 import mlx.core as mx
-from mlx import nn
 from mflux.models.common.config.config import Config
 from mflux.models.common.config.model_config import ModelConfig
 from mflux.models.flux.model.flux_transformer.embed_nd import EmbedND
-from mflux.models.flux.model.flux_transformer.time_text_embed import TimeTextEmbed
 from mflux.models.flux.model.flux_transformer.joint_transformer_block import (
     JointTransformerBlock,
 )
 from mflux.models.flux.model.flux_transformer.single_transformer_block import (
     SingleTransformerBlock,
 )
+from mflux.models.flux.model.flux_transformer.time_text_embed import TimeTextEmbed
+from mlx import nn
 
 class Transformer(nn.Module):
     transformer_blocks: list[JointTransformerBlock]

.typings/mflux/models/flux/variants/concept_attention/attention_data.pyi

@@ -2,11 +2,12 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
-import PIL.Image
 from dataclasses import dataclass
 from pathlib import Path
 from typing import List
+
+import mlx.core as mx
+import PIL.Image
 from mflux.models.flux.variants.concept_attention.joint_transformer_block_concept import (
     LayerAttentionData,
 )

.typings/mflux/models/flux/variants/concept_attention/joint_transformer_block_concept.pyi

@@ -2,8 +2,9 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from dataclasses import dataclass
+
+import mlx.core as mx
 from mlx import nn
 
 @dataclass
@@ -11,7 +12,6 @@ class LayerAttentionData:
     layer: int
     img_attention: mx.array
     concept_attention: mx.array
-    ...
 
 class JointTransformerBlockConcept(nn.Module):
     def __init__(self, layer) -> None: ...

.typings/mflux/models/flux/variants/concept_attention/transformer_concept.pyi

@@ -3,12 +3,12 @@ This type stub file was generated by pyright.
 """
 
 import mlx.core as mx
-from mlx import nn
 from mflux.models.common.config.config import Config
 from mflux.models.common.config.model_config import ModelConfig
 from mflux.models.flux.variants.concept_attention.attention_data import (
     TimestepAttentionData,
 )
+from mlx import nn
 
 class TransformerConcept(nn.Module):
     def __init__(

.typings/mflux/models/flux/variants/controlnet/transformer_controlnet.pyi

@@ -3,9 +3,9 @@ This type stub file was generated by pyright.
 """
 
 import mlx.core as mx
-from mlx import nn
 from mflux.models.common.config.config import Config
 from mflux.models.common.config.model_config import ModelConfig
+from mlx import nn
 
 class TransformerControlnet(nn.Module):
     def __init__(

.typings/mflux/models/flux/variants/kontext/flux_kontext.pyi

@@ -5,8 +5,6 @@ This type stub file was generated by pyright.
 from pathlib import Path
 from typing import Any
 
-from mlx import nn
-
 from mflux.models.common.config.model_config import ModelConfig
 from mflux.models.flux.model.flux_text_encoder.clip_encoder.clip_encoder import (
     CLIPEncoder,
@@ -15,6 +13,7 @@ from mflux.models.flux.model.flux_text_encoder.t5_encoder.t5_encoder import T5En
 from mflux.models.flux.model.flux_transformer.transformer import Transformer
 from mflux.models.flux.model.flux_vae.vae import VAE
 from mflux.utils.generated_image import GeneratedImage
+from mlx import nn
 
 class Flux1Kontext(nn.Module):
     vae: VAE

.typings/mflux/models/flux/variants/kontext/kontext_util.pyi

@@ -3,7 +3,6 @@ This type stub file was generated by pyright.
 """
 
 import mlx.core as mx
-
 from mflux.models.flux.model.flux_vae.vae import VAE
 
 class KontextUtil:

.typings/mflux/models/flux/variants/txt2img/flux.pyi

@@ -3,8 +3,8 @@ This type stub file was generated by pyright.
 """
 
 from pathlib import Path
-from mlx import nn
 from typing import Any
+
 from mflux.models.common.config.model_config import ModelConfig
 from mflux.models.flux.model.flux_text_encoder.clip_encoder.clip_encoder import (
     CLIPEncoder,
@@ -13,6 +13,7 @@ from mflux.models.flux.model.flux_text_encoder.t5_encoder.t5_encoder import T5En
 from mflux.models.flux.model.flux_transformer.transformer import Transformer
 from mflux.models.flux.model.flux_vae.vae import VAE
 from mflux.utils.generated_image import GeneratedImage
+from mlx import nn
 
 class Flux1(nn.Module):
     vae: VAE

.typings/mflux/models/flux/weights/flux_weight_definition.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.loading.weight_definition import (
     ComponentDefinition,
     TokenizerDefinition,

.typings/mflux/models/flux/weights/flux_weight_mapping.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.mapping.weight_mapping import (
     WeightMapping,
     WeightTarget,

.typings/mflux/models/qwen/model/qwen_transformer/qwen_attention.pyi

@@ -2,9 +2,10 @@
 This type stub file was generated by pyright.
 """
 
+from typing import Any
+
 import mlx.core as mx
 from mlx import nn
-from typing import Any
 
 class QwenAttention(nn.Module):
     _num_heads: int

.typings/mflux/models/qwen/model/qwen_transformer/qwen_transformer.pyi

@@ -2,13 +2,14 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
-from mlx import nn
 from typing import Any
+
+import mlx.core as mx
 from mflux.models.common.config.config import Config
 from mflux.models.qwen.model.qwen_transformer.qwen_transformer_block import (
     QwenTransformerBlock,
 )
+from mlx import nn
 
 class QwenTransformer(nn.Module):
     transformer_blocks: list[QwenTransformerBlock]

.typings/mflux/models/qwen/model/qwen_transformer/qwen_transformer_block.pyi

@@ -2,10 +2,11 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
-from mlx import nn
 from typing import Any
+
+import mlx.core as mx
 from mflux.models.qwen.model.qwen_transformer.qwen_attention import QwenAttention
+from mlx import nn
 
 class QwenTransformerBlock(nn.Module):
     attn: QwenAttention

.typings/mflux/models/qwen/tokenizer/qwen_image_processor.pyi

@@ -2,8 +2,9 @@
 This type stub file was generated by pyright.
 """
 
-import numpy as np
 from typing import Optional, Union
+
+import numpy as np
 from PIL import Image
 
 OPENAI_CLIP_MEAN = ...

.typings/mflux/models/qwen/tokenizer/qwen_vision_language_processor.pyi

@@ -3,8 +3,9 @@ This type stub file was generated by pyright.
 """
 
 from typing import Optional, Union
-from PIL import Image
+
 from mflux.models.qwen.tokenizer.qwen_image_processor import QwenImageProcessor
+from PIL import Image
 
 class QwenVisionLanguageProcessor:
     def __init__(

.typings/mflux/models/qwen/tokenizer/qwen_vision_language_tokenizer.pyi

@@ -2,13 +2,14 @@
 This type stub file was generated by pyright.
 """
 
+from typing import Union
+
 import mlx.core as mx
 import numpy as np
-from typing import Union
-from PIL import Image
 from mflux.models.qwen.tokenizer.qwen_vision_language_processor import (
     QwenVisionLanguageProcessor,
 )
+from PIL import Image
 
 class QwenVisionLanguageTokenizer:
     def __init__(

.typings/mflux/models/qwen/variants/edit/qwen_image_edit.pyi

@@ -2,16 +2,17 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from pathlib import Path
-from mlx import nn
 from typing import Any
+
+import mlx.core as mx
 from mflux.models.common.config import Config
 from mflux.models.common.config.model_config import ModelConfig
 from mflux.models.qwen.model.qwen_text_encoder.qwen_text_encoder import QwenTextEncoder
 from mflux.models.qwen.model.qwen_transformer.qwen_transformer import QwenTransformer
 from mflux.models.qwen.model.qwen_vae.qwen_vae import QwenVAE
 from mflux.utils.generated_image import GeneratedImage
+from mlx import nn
 
 class QwenImageEdit(nn.Module):
     vae: QwenVAE

.typings/mflux/models/qwen/variants/txt2img/qwen_image.pyi

@@ -2,15 +2,16 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
 from pathlib import Path
-from mlx import nn
 from typing import Any
+
+import mlx.core as mx
 from mflux.models.common.config import ModelConfig
 from mflux.models.qwen.model.qwen_text_encoder.qwen_text_encoder import QwenTextEncoder
 from mflux.models.qwen.model.qwen_transformer.qwen_transformer import QwenTransformer
 from mflux.models.qwen.model.qwen_vae.qwen_vae import QwenVAE
 from mflux.utils.generated_image import GeneratedImage
+from mlx import nn
 
 class QwenImage(nn.Module):
     vae: QwenVAE

.typings/mflux/models/qwen/weights/qwen_lora_mapping.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.lora.mapping.lora_mapping import LoRAMapping, LoRATarget
 
 class QwenLoRAMapping(LoRAMapping):

.typings/mflux/models/qwen/weights/qwen_weight_definition.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.loading.weight_definition import (
     ComponentDefinition,
     TokenizerDefinition,

.typings/mflux/models/qwen/weights/qwen_weight_mapping.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.mapping.weight_mapping import (
     WeightMapping,
     WeightTarget,

.typings/mflux/models/seedvr2/weights/seedvr2_weight_definition.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.loading.weight_definition import (
     ComponentDefinition,
     TokenizerDefinition,

.typings/mflux/models/seedvr2/weights/seedvr2_weight_mapping.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.mapping.weight_mapping import (
     WeightMapping,
     WeightTarget,

.typings/mflux/models/z_image/weights/z_image_weight_definition.pyi

@@ -3,6 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from typing import List
+
 from mflux.models.common.weights.loading.weight_definition import (
     ComponentDefinition,
     TokenizerDefinition,

.typings/mflux/utils/box_values.pyi

@@ -10,7 +10,6 @@ class AbsoluteBoxValues:
     right: int
     bottom: int
     left: int
-    ...
 
 class BoxValueError(ValueError): ...
 

.typings/mflux/utils/generated_image.pyi

@@ -2,9 +2,10 @@
 This type stub file was generated by pyright.
 """
 
+from pathlib import Path
+
 import mlx.core as mx
 import PIL.Image
-from pathlib import Path
 from mflux.models.common.config import ModelConfig
 from mflux.models.flux.variants.concept_attention.attention_data import ConceptHeatmap
 

.typings/mflux/utils/image_util.pyi

@@ -2,15 +2,16 @@
 This type stub file was generated by pyright.
 """
 
-import mlx.core as mx
-import PIL.Image
 from pathlib import Path
 from typing import Any
-from PIL._typing import StrOrBytesPath
+
+import mlx.core as mx
+import PIL.Image
 from mflux.models.common.config.config import Config
 from mflux.models.flux.variants.concept_attention.attention_data import ConceptHeatmap
 from mflux.utils.box_values import AbsoluteBoxValues
 from mflux.utils.generated_image import GeneratedImage
+from PIL._typing import StrOrBytesPath
 
 log = ...