Point mlx-lm to davidmcc73 fork with context parallelism support

Store pre-shard head count and distributed group on each attention
layer during sharding, enabling automatic TP→CP switching at runtime
when context length exceeds a threshold.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.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/workflows/pipeline.yml

@@ -26,14 +26,73 @@ jobs:
           name: exo
           authToken: "${{ secrets.CACHIX_AUTH_TOKEN }}"
 
-      - name: Load nix develop environment
-        run: nix run github:nicknovitski/nix-develop/v1
+      - 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: Sync dependencies
-        run: uv sync --all-packages
+      - name: Pull LFS files
+        run: |
+          echo "Pulling Git LFS files..."
+          git lfs pull
+        shell: bash
 
-      - name: Run type checker
-        run: uv run basedpyright --project pyproject.toml
+      - 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:
     name: Build and check (${{ matrix.system }})
@@ -64,63 +123,6 @@ jobs:
           name: exo
           authToken: "${{ secrets.CACHIX_AUTH_TOKEN }}"
 
-      - name: Build Metal packages (macOS only)
-        if: runner.os == 'macOS'
-        run: |
-          # Try to build metal-toolchain first (may succeed via cachix cache hit)
-          if nix build .#metal-toolchain 2>/dev/null; then
-            echo "metal-toolchain built successfully (likely cache hit)"
-          else
-            echo "metal-toolchain build failed, extracting from Xcode..."
-
-            NAR_HASH="sha256-ayR5mXN4sZAddwKEG2OszGRF93k9ZFc7H0yi2xbylQw="
-            NAR_NAME="metal-toolchain-17C48.nar"
-
-            # Use RUNNER_TEMP to avoid /tmp symlink issues on macOS
-            WORK_DIR="${RUNNER_TEMP}/metal-work"
-            mkdir -p "$WORK_DIR"
-
-            # Download the Metal toolchain component
-            xcodebuild -downloadComponent MetalToolchain
-
-            # Find and mount the DMG
-            DMG_PATH=$(find /System/Library/AssetsV2/com_apple_MobileAsset_MetalToolchain -name '*.dmg' 2>/dev/null | head -1)
-            if [ -z "$DMG_PATH" ]; then
-              echo "Error: Could not find Metal toolchain DMG"
-              exit 1
-            fi
-
-            echo "Found DMG at: $DMG_PATH"
-            hdiutil attach "$DMG_PATH" -mountpoint "${WORK_DIR}/metal-dmg"
-
-            # Copy the toolchain
-            cp -R "${WORK_DIR}/metal-dmg/Metal.xctoolchain" "${WORK_DIR}/metal-export"
-            hdiutil detach "${WORK_DIR}/metal-dmg"
-
-            # Create NAR and add to store
-            nix nar pack "${WORK_DIR}/metal-export" > "${WORK_DIR}/${NAR_NAME}"
-            STORE_PATH=$(nix store add --mode flat "${WORK_DIR}/${NAR_NAME}")
-            echo "Added NAR to store: $STORE_PATH"
-
-            # Verify the hash matches
-            ACTUAL_HASH=$(nix hash file "${WORK_DIR}/${NAR_NAME}")
-            if [ "$ACTUAL_HASH" != "$NAR_HASH" ]; then
-              echo "Warning: NAR hash mismatch!"
-              echo "Expected: $NAR_HASH"
-              echo "Actual:   $ACTUAL_HASH"
-              echo "The metal-toolchain.nix may need updating"
-            fi
-
-            # Clean up
-            rm -rf "$WORK_DIR"
-
-            # Retry the build now that NAR is in store
-            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 '
@@ -132,16 +134,3 @@ jobs:
 
       - name: Run nix flake check
         run: nix flake check
-
-      - name: Run pytest (macOS only)
-        if: runner.os == 'macOS'
-        run: |
-          # Build the test environment (requires relaxed sandbox for uv2nix on macOS)
-          TEST_ENV=$(nix build '.#exo-test-env' --option sandbox relaxed --print-out-paths)
-
-          # Run pytest outside sandbox (needs GPU access for MLX)
-          export HOME="$RUNNER_TEMP"
-          export EXO_TESTS=1
-          export EXO_DASHBOARD_DIR="$PWD/dashboard/" 
-          export EXO_RESOURCES_DIR="$PWD/resources" 
-          $TEST_ENV/bin/python -m pytest src -m "not slow" --import-mode=importlib

.gitignore

@@ -28,7 +28,3 @@ target/
 dashboard/build/
 dashboard/node_modules/
 dashboard/.svelte-kit/
-
-# host config snapshots
-hosts_*.json
-.swp

.mlx_typings/mlx_lm/tokenizer_utils.pyi

@@ -108,7 +108,6 @@ class TokenizerWrapper:
     _tokenizer: PreTrainedTokenizerFast
     eos_token_id: int | None
     eos_token: str | None
-    eos_token_ids: list[int] | set[int] | None
     bos_token_id: int | None
     bos_token: str | None
     vocab_size: int
@@ -118,7 +117,7 @@ class TokenizerWrapper:
         self,
         tokenizer: Any,
         detokenizer_class: Any = ...,
-        eos_token_ids: list[int] | set[int] | None = ...,
+        eos_token_ids: list[int] | None = ...,
         chat_template: Any = ...,
         tool_parser: Any = ...,
         tool_call_start: str | None = ...,

README.md

@@ -5,7 +5,7 @@
   <img alt="exo logo" src="/docs/imgs/exo-logo-transparent.png" width="50%" height="50%">
 </picture>
 
-exo: Run frontier AI locally. Maintained by [exo labs](https://x.com/exolabs).
+exo: Run your own AI cluster at home with everyday devices. Maintained by [exo labs](https://x.com/exolabs).
 
 <p align="center">
   <a href="https://discord.gg/TJ4P57arEm" target="_blank" rel="noopener noreferrer"><img src="https://img.shields.io/badge/Discord-Join%20Server-5865F2?logo=discord&logoColor=white" alt="Discord"></a>
@@ -107,10 +107,6 @@ uv run exo
 
 This starts the exo dashboard and API at http://localhost:52415/
 
-
-*Please view the section on RDMA to enable this feature on MacOS >=26.2!*
-
-
 ### Run from Source (Linux)
 
 **Prerequisites:**
@@ -234,7 +230,7 @@ This removes:
 
 RDMA is a new capability added to macOS 26.2. It works on any Mac with Thunderbolt 5 (M4 Pro Mac Mini, M4 Max Mac Studio, M4 Max MacBook Pro, M3 Ultra Mac Studio).
 
-Please refer to the caveats for immediate troubleshooting.
+Note that on Mac Studio, you cannot use the Thunderbolt 5 port next to the Ethernet port.
 
 To enable RDMA on macOS, follow these steps:
 
@@ -251,14 +247,6 @@ To enable RDMA on macOS, follow these steps:
 
 After that, RDMA will be enabled in macOS and exo will take care of the rest.
 
-**Important Caveats**
-
-1. Devices that wish to be part of an RDMA cluster must be connected to all other devices in the cluster.
-2. The cables must support TB5.
-3. On a Mac Studio, you cannot use the Thunderbolt 5 port next to the Ethernet port.
-4. If running from source, please use the script found at `tmp/set_rdma_network_config.sh`, which will disable Thunderbolt Bridge and set dhcp on each RDMA port.
-5. RDMA ports may be unable to discover each other on different versions of MacOS. Please ensure that OS versions match exactly (even beta version numbers) on all devices.
-
 ---
 
 ### Using the API

app/EXO/EXO.xcodeproj/project.pbxproj

@@ -342,8 +342,6 @@
 				SDKROOT = macosx;
 				SWIFT_ACTIVE_COMPILATION_CONDITIONS = "DEBUG $(inherited)";
 				SWIFT_OPTIMIZATION_LEVEL = "-Onone";
-				SWIFT_TREAT_WARNINGS_AS_ERRORS = YES;
-				GCC_TREAT_WARNINGS_AS_ERRORS = YES;
 			};
 			name = Debug;
 		};
@@ -399,8 +397,6 @@
 				MTL_FAST_MATH = YES;
 				SDKROOT = macosx;
 				SWIFT_COMPILATION_MODE = wholemodule;
-				SWIFT_TREAT_WARNINGS_AS_ERRORS = YES;
-				GCC_TREAT_WARNINGS_AS_ERRORS = YES;
 			};
 			name = Release;
 		};

app/EXO/EXO/EXOApp.swift

@@ -225,7 +225,7 @@ private final class ExoUpdaterDelegate: NSObject, SPUUpdaterDelegate {
         }
     }
 
-    nonisolated private func showNotification(title: String, body: String) {
+    private func showNotification(title: String, body: String) {
         let center = UNUserNotificationCenter.current()
         let content = UNMutableNotificationContent()
         content.title = title

app/EXO/EXO/Models/ClusterState.swift

@@ -293,7 +293,7 @@ struct ClusterTask {
     let modelName: String?
     let promptPreview: String?
     let errorMessage: String?
-    let parameters: TextGenerationTaskParameters?
+    let parameters: ChatCompletionTaskParameters?
 
     var sortPriority: Int {
         switch status {
@@ -330,12 +330,12 @@ struct ClusterTaskPayload: Decodable {
     let taskStatus: TaskStatus?
     let instanceId: String?
     let commandId: String?
-    let taskParams: TextGenerationTaskParameters?
+    let taskParams: ChatCompletionTaskParameters?
     let errorType: String?
     let errorMessage: String?
 }
 
-struct TextGenerationTaskParameters: Decodable, Equatable {
+struct ChatCompletionTaskParameters: Decodable, Equatable {
     let model: String?
     let messages: [ChatCompletionMessage]?
     let maxTokens: Int?
@@ -374,7 +374,7 @@ extension ClusterTask {
         guard let id = payload.taskId else { return nil }
         let status = payload.taskStatus ?? .unknown
         switch kindKey {
-        case "TextGeneration":
+        case "ChatCompletion":
             self.init(
                 id: id,
                 status: status,

app/EXO/EXO/Services/NetworkSetupHelper.swift

@@ -18,9 +18,6 @@ enum NetworkSetupHelper {
 
         set -euo pipefail
 
-        # Wait for macOS to finish network setup after boot
-        sleep 20
-
         PREFS="/Library/Preferences/SystemConfiguration/preferences.plist"
 
         # Remove bridge0 interface
@@ -83,7 +80,7 @@ enum NetworkSetupHelper {
                 let alert = NSAlert()
                 alert.messageText = "EXO Network Configuration"
                 alert.informativeText =
-                    "EXO needs to install a system service to configure local networking. This will disable Thunderbolt Bridge (preventing packet storms) and install a Network Location.\n\nYou will be prompted for your password."
+                    "EXO needs to install a system service to automatically disable Thunderbolt Bridge on startup. This prevents network loops when connecting multiple Macs via Thunderbolt.\n\nYou will be prompted for your administrator password."
                 alert.alertStyle = .informational
                 alert.addButton(withTitle: "Install")
                 alert.addButton(withTitle: "Not Now")
@@ -244,11 +241,11 @@ enum NetworkSetupHelper {
         rm -f "$LOG_OUT" "$LOG_ERR"
 
         # Switch back to Automatic network location
-        networksetup -switchtolocation Automatic >/dev/null 2>&1 || true
+        networksetup -switchtolocation Automatic 2>/dev/null || true
 
         # Delete the exo network location if it exists
-        networksetup -listlocations 2>/dev/null | grep -q '^exo$' && {
-          networksetup -deletelocation exo >/dev/null 2>&1 || true
+        networksetup -listlocations | grep -q '^exo$' && {
+          networksetup -deletelocation exo 2>/dev/null || true
         } || true
 
         # Re-enable any Thunderbolt Bridge service if it exists
@@ -258,12 +255,12 @@ enum NetworkSetupHelper {
           tb_devices=$(networksetup -listallhardwareports 2>/dev/null | awk '
             /^Hardware Port:/ { port = tolower(substr($0, 16)) }
             /^Device:/ { if (port ~ /thunderbolt/) print substr($0, 9) }
-          ') || true
+          ')
           [ -z "$tb_devices" ] && return 0
 
           # For each bridge device, check if it contains Thunderbolt interfaces
           for bridge in bridge0 bridge1 bridge2; do
-            members=$(ifconfig "$bridge" 2>/dev/null | awk '/member:/ {print $2}') || true
+            members=$(ifconfig "$bridge" 2>/dev/null | awk '/member:/ {print $2}')
             [ -z "$members" ] && continue
 
             for tb_dev in $tb_devices; do
@@ -272,7 +269,7 @@ enum NetworkSetupHelper {
                 service_name=$(networksetup -listnetworkserviceorder 2>/dev/null | awk -v dev="$bridge" '
                   /^\\([0-9*]/ { gsub(/^\\([0-9*]+\\) /, ""); svc = $0 }
                   /Device:/ && $0 ~ dev { print svc; exit }
-                ') || true
+                ')
                 if [ -n "$service_name" ]; then
                   networksetup -setnetworkserviceenabled "$service_name" on 2>/dev/null || true
                   return 0
@@ -280,9 +277,8 @@ enum NetworkSetupHelper {
               fi
             done
           done
-          return 0
         }
-        find_and_enable_thunderbolt_bridge || true
+        find_and_enable_thunderbolt_bridge
 
         echo "EXO network components removed successfully"
         """

app/EXO/EXO/Services/ThunderboltBridgeService.swift

@@ -127,24 +127,21 @@ final class ThunderboltBridgeService: ObservableObject {
 
         // 2. Request specific network configuration rights
         let rightName = "system.services.systemconfiguration.network"
-        status = rightName.withCString { nameCString in
-            var item = AuthorizationItem(
-                name: nameCString,
-                valueLength: 0,
-                value: nil,
-                flags: 0
-            )
-            return withUnsafeMutablePointer(to: &item) { itemPointer in
-                var rights = AuthorizationRights(count: 1, items: itemPointer)
-                return AuthorizationCopyRights(
-                    authRef,
-                    &rights,
-                    nil,
-                    [.extendRights, .interactionAllowed],
-                    nil
-                )
-            }
-        }
+        var item = AuthorizationItem(
+            name: rightName,
+            valueLength: 0,
+            value: nil,
+            flags: 0
+        )
+        var rights = AuthorizationRights(count: 1, items: &item)
+
+        status = AuthorizationCopyRights(
+            authRef,
+            &rights,
+            nil,
+            [.extendRights, .interactionAllowed],
+            nil
+        )
         guard status == errAuthorizationSuccess else {
             if status == errAuthorizationCanceled {
                 throw ThunderboltBridgeError.authorizationCanceled

app/EXO/EXO/ViewModels/InstanceViewModel.swift

@@ -216,7 +216,7 @@ struct InstanceTaskViewModel: Identifiable, Equatable {
     let promptPreview: String?
     let errorMessage: String?
     let subtitle: String?
-    let parameters: TextGenerationTaskParameters?
+    let parameters: ChatCompletionTaskParameters?
 
     var title: String {
         switch kind {

app/EXO/uninstall-exo.sh

@@ -29,21 +29,21 @@ YELLOW='\033[1;33m'
 NC='\033[0m' # No Color
 
 echo_info() {
-  echo -e "${GREEN}[INFO]${NC} $1"
+    echo -e "${GREEN}[INFO]${NC} $1"
 }
 
 echo_warn() {
-  echo -e "${YELLOW}[WARN]${NC} $1"
+    echo -e "${YELLOW}[WARN]${NC} $1"
 }
 
 echo_error() {
-  echo -e "${RED}[ERROR]${NC} $1"
+    echo -e "${RED}[ERROR]${NC} $1"
 }
 
 # Check if running as root
 if [[ $EUID -ne 0 ]]; then
-  echo_error "This script must be run as root (use sudo)"
-  exit 1
+    echo_error "This script must be run as root (use sudo)"
+    exit 1
 fi
 
 echo ""
@@ -55,64 +55,64 @@ echo ""
 # Unload the LaunchDaemon if running
 echo_info "Stopping network setup daemon..."
 if launchctl list | grep -q "$LABEL"; then
-  launchctl bootout system/"$LABEL" 2>/dev/null || true
-  echo_info "Daemon stopped"
+    launchctl bootout system/"$LABEL" 2>/dev/null || true
+    echo_info "Daemon stopped"
 else
-  echo_warn "Daemon was not running"
+    echo_warn "Daemon was not running"
 fi
 
 # Remove LaunchDaemon plist
-if [[ -f $PLIST_DEST ]]; then
-  rm -f "$PLIST_DEST"
-  echo_info "Removed LaunchDaemon plist"
+if [[ -f "$PLIST_DEST" ]]; then
+    rm -f "$PLIST_DEST"
+    echo_info "Removed LaunchDaemon plist"
 else
-  echo_warn "LaunchDaemon plist not found (already removed?)"
+    echo_warn "LaunchDaemon plist not found (already removed?)"
 fi
 
 # Remove the script and parent directory
-if [[ -f $SCRIPT_DEST ]]; then
-  rm -f "$SCRIPT_DEST"
-  echo_info "Removed network setup script"
+if [[ -f "$SCRIPT_DEST" ]]; then
+    rm -f "$SCRIPT_DEST"
+    echo_info "Removed network setup script"
 else
-  echo_warn "Network setup script not found (already removed?)"
+    echo_warn "Network setup script not found (already removed?)"
 fi
 
 # Remove EXO directory if empty
 if [[ -d "/Library/Application Support/EXO" ]]; then
-  rmdir "/Library/Application Support/EXO" 2>/dev/null &&
-    echo_info "Removed EXO support directory" ||
-    echo_warn "EXO support directory not empty, leaving in place"
+    rmdir "/Library/Application Support/EXO" 2>/dev/null && \
+        echo_info "Removed EXO support directory" || \
+        echo_warn "EXO support directory not empty, leaving in place"
 fi
 
 # Remove log files
-if [[ -f $LOG_OUT ]] || [[ -f $LOG_ERR ]]; then
-  rm -f "$LOG_OUT" "$LOG_ERR"
-  echo_info "Removed log files"
+if [[ -f "$LOG_OUT" ]] || [[ -f "$LOG_ERR" ]]; then
+    rm -f "$LOG_OUT" "$LOG_ERR"
+    echo_info "Removed log files"
 else
-  echo_warn "Log files not found (already removed?)"
+    echo_warn "Log files not found (already removed?)"
 fi
 
 # Switch back to Automatic network location
 echo_info "Restoring network configuration..."
 if networksetup -listlocations | grep -q "^Automatic$"; then
-  networksetup -switchtolocation Automatic 2>/dev/null || true
-  echo_info "Switched to Automatic network location"
+    networksetup -switchtolocation Automatic 2>/dev/null || true
+    echo_info "Switched to Automatic network location"
 else
-  echo_warn "Automatic network location not found"
+    echo_warn "Automatic network location not found"
 fi
 
 # Delete the exo network location if it exists
 if networksetup -listlocations | grep -q "^exo$"; then
-  networksetup -deletelocation exo 2>/dev/null || true
-  echo_info "Deleted 'exo' network location"
+    networksetup -deletelocation exo 2>/dev/null || true
+    echo_info "Deleted 'exo' network location"
 else
-  echo_warn "'exo' network location not found (already removed?)"
+    echo_warn "'exo' network location not found (already removed?)"
 fi
 
 # Re-enable Thunderbolt Bridge if it exists
 if networksetup -listnetworkservices 2>/dev/null | grep -q "Thunderbolt Bridge"; then
-  networksetup -setnetworkserviceenabled "Thunderbolt Bridge" on 2>/dev/null || true
-  echo_info "Re-enabled Thunderbolt Bridge"
+    networksetup -setnetworkserviceenabled "Thunderbolt Bridge" on 2>/dev/null || true
+    echo_info "Re-enabled Thunderbolt Bridge"
 fi
 
 # Note about launch at login registration
@@ -124,14 +124,14 @@ echo_warn "  System Settings → General → Login Items → Remove EXO"
 # Check if EXO.app exists in common locations
 APP_FOUND=false
 for app_path in "/Applications/EXO.app" "$HOME/Applications/EXO.app"; do
-  if [[ -d $app_path ]]; then
-    if [[ $APP_FOUND == false ]]; then
-      echo ""
-      APP_FOUND=true
+    if [[ -d "$app_path" ]]; then
+        if [[ "$APP_FOUND" == false ]]; then
+            echo ""
+            APP_FOUND=true
+        fi
+        echo_warn "EXO.app found at: $app_path"
+        echo_warn "You may want to move it to Trash manually."
     fi
-    echo_warn "EXO.app found at: $app_path"
-    echo_warn "You may want to move it to Trash manually."
-  fi
 done
 
 echo ""
@@ -151,3 +151,4 @@ echo ""
 echo "Manual step required:"
 echo "  Remove EXO from Login Items in System Settings → General → Login Items"
 echo ""
+

bench/eval_config.toml

@@ -0,0 +1,66 @@
+# exo-eval configuration file
+# See bench/exo_eval.py for usage
+
+[eval]
+# Eval framework type: "lm_eval" | "swe_bench" | "custom"
+type = "lm_eval"
+# Require HuggingFace token (default: true)
+# Set to false if using only public datasets
+require_hf_token = true
+
+# Instance/placement configuration
+# Controls how exo sets up the model instance before running evals
+[instance]
+# Placement strategy: "ring" | "jaccl" | "both"
+instance_meta = "jaccl"
+# Sharding strategy: "pipeline" | "tensor" | "both"
+sharding = "tensor"
+# Node constraints
+min_nodes = 2
+max_nodes = 2
+
+# lm_eval configuration (EleutherAI's lm-evaluation-harness)
+[lm_eval]
+# Tasks to run (list of task names)
+# NOTE: Chat completions API only supports generation-based tasks.
+# Loglikelihood tasks (mmlu, hellaswag, arc) require /v1/completions endpoint.
+#
+# Generation-based tasks (work with chat completions):
+#   - mmlu_pro, mmlu_generative, mmlu_flan_cot_fewshot, mmlu_flan_cot_zeroshot
+#   - gsm8k, gsm8k_cot, gsm8k_cot_zeroshot
+#   - truthfulqa (uses generate_until for some subtasks)
+#   - humaneval, mbpp (code generation)
+#
+# Run `lm_eval --tasks list` to see all available tasks
+tasks = ["mmlu_pro"]
+# Number of few-shot examples (5 is standard for mmlu_pro CoT)
+num_fewshot = 5
+# Batch size (use 1 for API models, "auto" doesn't work)
+batch_size = 1
+# Number of concurrent requests (set > 1 to enable parallelism)
+# Higher values enable better batching throughput
+num_concurrent = 64
+# Apply chat template for instruct/chat models (default: true)
+apply_chat_template = true
+# Use fewshot examples as conversation turns (better for chat models)
+fewshot_as_multiturn = true
+# Optional: limit samples per task (omit or comment out for no limit)
+# limit = 100
+# Output path for results
+output_path = "bench/eval_results"
+
+# SWE-bench configuration (placeholder)
+[swe_bench]
+# SWE-bench dataset
+dataset = "princeton-nlp/SWE-bench_Lite"
+# Maximum workers for parallel execution
+max_workers = 8
+# Path for prediction outputs
+predictions_path = "bench/predictions"
+
+# Custom evaluation script configuration
+[custom]
+# Path to custom evaluation script
+script = "path/to/eval_script.py"
+# Arguments to pass to the script
+args = ["--arg1", "value1"]

bench/exo_bench.py

@@ -5,13 +5,10 @@ from __future__ import annotations
 import argparse
 import contextlib
 import http.client
-import itertools
 import json
 import os
-import sys
 import time
 from collections.abc import Callable
-from pathlib import Path
 from statistics import mean
 from typing import Any
 from urllib.parse import urlencode
@@ -19,84 +16,6 @@ from urllib.parse import urlencode
 from loguru import logger
 from transformers import AutoTokenizer
 
-# Monkey-patch for transformers 5.x compatibility
-# Kimi's tokenization_kimi.py imports bytes_to_unicode from the old location
-# which was moved in transformers 5.0.0rc2
-try:
-    import transformers.models.gpt2.tokenization_gpt2 as gpt2_tokenization
-    from transformers.convert_slow_tokenizer import bytes_to_unicode
-
-    if not hasattr(gpt2_tokenization, "bytes_to_unicode"):
-        gpt2_tokenization.bytes_to_unicode = bytes_to_unicode  # type: ignore[attr-defined]
-except ImportError:
-    pass  # transformers < 5.0 or bytes_to_unicode not available
-
-
-def load_tokenizer_for_bench(model_id: str) -> Any:
-    """
-    Load tokenizer for benchmarking, with special handling for Kimi models.
-
-    Kimi uses a custom TikTokenTokenizer that transformers 5.x can't load via AutoTokenizer.
-    This function replicates the logic from utils_mlx.py for bench compatibility.
-    """
-    model_id_lower = model_id.lower()
-
-    if "kimi-k2" in model_id_lower:
-        import importlib.util
-        import types
-
-        from huggingface_hub import snapshot_download
-
-        # Download/get the model path
-        model_path = Path(
-            snapshot_download(
-                model_id,
-                allow_patterns=["*.json", "*.py", "*.tiktoken"],
-            )
-        )
-
-        sys.path.insert(0, str(model_path))
-
-        # Load tool_declaration_ts first (tokenization_kimi imports it with relative import)
-        tool_decl_path = model_path / "tool_declaration_ts.py"
-        if tool_decl_path.exists():
-            spec = importlib.util.spec_from_file_location(
-                "tool_declaration_ts", tool_decl_path
-            )
-            if spec and spec.loader:
-                tool_decl_module = importlib.util.module_from_spec(spec)
-                sys.modules["tool_declaration_ts"] = tool_decl_module
-                spec.loader.exec_module(tool_decl_module)
-
-        # Load tokenization_kimi with patched source (convert relative to absolute import)
-        tok_path = model_path / "tokenization_kimi.py"
-        source = tok_path.read_text()
-        source = source.replace("from .tool_declaration_ts", "from tool_declaration_ts")
-        spec = importlib.util.spec_from_file_location("tokenization_kimi", tok_path)
-        if spec:
-            tok_module = types.ModuleType("tokenization_kimi")
-            tok_module.__file__ = str(tok_path)
-            sys.modules["tokenization_kimi"] = tok_module
-            exec(compile(source, tok_path, "exec"), tok_module.__dict__)  # noqa: S102
-            TikTokenTokenizer = tok_module.TikTokenTokenizer  # noqa: N806
-        else:
-            from tokenization_kimi import TikTokenTokenizer  # type: ignore[import-not-found]  # noqa: I001
-
-        hf_tokenizer: Any = TikTokenTokenizer.from_pretrained(model_path)
-
-        # Patch encode to use internal tiktoken model directly
-        # transformers 5.x has a bug in the encode->pad path for slow tokenizers
-        def _patched_encode(text: str, **kwargs: object) -> list[int]:
-            # Pass allowed_special="all" to handle special tokens like <|im_user|>
-            return list(hf_tokenizer.model.encode(text, allowed_special="all"))
-
-        hf_tokenizer.encode = _patched_encode
-
-        return hf_tokenizer
-
-    # Default: use AutoTokenizer
-    return AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
-
 
 class ExoHttpError(RuntimeError):
     def __init__(self, status: int, reason: str, body_preview: str):
@@ -105,7 +24,7 @@ class ExoHttpError(RuntimeError):
 
 
 class ExoClient:
-    def __init__(self, host: str, port: int, timeout_s: float = 7200.0):
+    def __init__(self, host: str, port: int, timeout_s: float = 600.0):
         self.host = host
         self.port = port
         self.timeout_s = timeout_s
@@ -261,7 +180,14 @@ def parse_int_list(values: list[str]) -> list[int]:
             part = part.strip()
             if part:
                 items.append(int(part))
-    return items
+
+    seen: set[int] = set()
+    out: list[int] = []
+    for x in items:
+        if x not in seen:
+            out.append(x)
+            seen.add(x)
+    return out
 
 
 def resolve_model_short_id(client: ExoClient, model_arg: str) -> tuple[str, str]:
@@ -314,11 +240,7 @@ def run_one_completion(
 
     stats = out.get("generation_stats")
 
-    # Extract preview, handling None content (common for thinking models)
-    choices = out.get("choices") or [{}]
-    message = choices[0].get("message", {}) if choices else {}
-    content = message.get("content") or ""
-    preview = content[:200] if content else ""
+    preview = (out.get("choices") or [{}])[0]["message"]["content"][:200]
 
     return {
         "elapsed_s": elapsed,
@@ -355,29 +277,12 @@ class PromptSizer:
                 f"Target ({target}) is smaller than template overhead ({self.base_tokens})."
             )
 
-        # Estimate tokens per atom using a sample
-        sample_count = 100
-        sample_content = self.atom * sample_count
-        sample_tokens = self.count_fn(sample_content) - self.base_tokens
-        tokens_per_atom = sample_tokens / sample_count
-
-        # Estimate starting point
-        needed_tokens = target - self.base_tokens
-        estimated_atoms = int(needed_tokens / tokens_per_atom)
-
-        # Binary search to find exact atom count
-        low, high = 0, estimated_atoms * 2 + 100
-        while low < high:
-            mid = (low + high) // 2
-            tok = self.count_fn(self.atom * mid)
-            if tok < target:
-                low = mid + 1
-            else:
-                high = mid
-
-        content = self.atom * low
+        content = ""
         tok = self.count_fn(content)
-        logger.info(f"{tok=}")
+
+        while tok < target:
+            content += self.atom
+            tok = self.count_fn(content)
 
         if tok != target:
             raise RuntimeError(
@@ -443,7 +348,7 @@ def main() -> int:
         help="Warmup runs per placement (uses first pp/tg).",
     )
     ap.add_argument(
-        "--timeout", type=float, default=7200.0, help="HTTP timeout (seconds)."
+        "--timeout", type=float, default=600.0, help="HTTP timeout (seconds)."
     )
     ap.add_argument(
         "--json-out",
@@ -453,11 +358,6 @@ def main() -> int:
     ap.add_argument(
         "--dry-run", action="store_true", help="List selected placements and exit."
     )
-    ap.add_argument(
-        "--all-combinations",
-        action="store_true",
-        help="Force all pp×tg combinations (cartesian product) even when lists have equal length.",
-    )
     args = ap.parse_args()
 
     pp_list = parse_int_list(args.pp)
@@ -469,15 +369,6 @@ def main() -> int:
         logger.error("--repeat must be >= 1")
         return 2
 
-    # Log pairing mode
-    use_combinations = args.all_combinations or len(pp_list) != len(tg_list)
-    if use_combinations:
-        logger.info(
-            f"pp/tg mode: combinations (product) - {len(pp_list) * len(tg_list)} pairs"
-        )
-    else:
-        logger.info(f"pp/tg mode: tandem (zip) - {len(pp_list)} pairs")
-
     client = ExoClient(args.host, args.port, timeout_s=args.timeout)
     short_id, full_model_id = resolve_model_short_id(client, args.model)
 
@@ -486,7 +377,10 @@ def main() -> int:
     )
     previews = previews_resp.get("previews") or []
 
-    tokenizer = load_tokenizer_for_bench(full_model_id)
+    tokenizer = AutoTokenizer.from_pretrained(
+        full_model_id,
+        trust_remote_code=True,
+    )
     if tokenizer is None:
         raise RuntimeError("[exo-bench] tokenizer load failed")
 
@@ -592,55 +486,60 @@ def main() -> int:
                 )
                 logger.debug(f"  warmup {i + 1}/{args.warmup} done")
 
-            # If pp and tg lists have same length, run in tandem (zip)
-            # Otherwise (or if --all-combinations), run all combinations (cartesian product)
-            if use_combinations:
-                pp_tg_pairs = list(itertools.product(pp_list, tg_list))
-            else:
-                pp_tg_pairs = list(zip(pp_list, tg_list, strict=True))
-
-            for pp, tg in pp_tg_pairs:
-                runs: list[dict[str, Any]] = []
-                for r in range(args.repeat):
-                    time.sleep(3)
-                    try:
-                        row, actual_pp_tokens = run_one_completion(
-                            client, full_model_id, pp, tg, prompt_sizer
+            for pp in pp_list:
+                # if (
+                #     pp * n_nodes > 2048
+                #     and "ring" in instance_meta.lower()
+                #     and "tensor" in sharding.lower()
+                # ):
+                #     model_card = MODEL_CARDS[short_id]
+                #     if model_card.metadata.storage_size > Memory.from_gb(10):
+                #         logger.info(
+                #             f"Skipping tensor ring as this is too slow for model of size {model_card.metadata.storage_size} on {n_nodes=}"
+                #         )
+                #         continue
+                for tg in tg_list:
+                    runs: list[dict[str, Any]] = []
+                    for r in range(args.repeat):
+                        time.sleep(3)
+                        try:
+                            row, actual_pp_tokens = run_one_completion(
+                                client, full_model_id, pp, tg, prompt_sizer
+                            )
+                        except Exception as e:
+                            logger.error(e)
+                            continue
+                        row.update(
+                            {
+                                "model_short_id": short_id,
+                                "model_id": full_model_id,
+                                "placement_sharding": sharding,
+                                "placement_instance_meta": instance_meta,
+                                "placement_nodes": n_nodes,
+                                "instance_id": instance_id,
+                                "pp_tokens": actual_pp_tokens,
+                                "tg": tg,
+                                "repeat_index": r,
+                            }
                         )
-                    except Exception as e:
-                        logger.error(e)
-                        continue
-                    row.update(
-                        {
-                            "model_short_id": short_id,
-                            "model_id": full_model_id,
-                            "placement_sharding": sharding,
-                            "placement_instance_meta": instance_meta,
-                            "placement_nodes": n_nodes,
-                            "instance_id": instance_id,
-                            "pp_tokens": actual_pp_tokens,
-                            "tg": tg,
-                            "repeat_index": r,
-                        }
-                    )
-                    runs.append(row)
-                    all_rows.append(row)
+                        runs.append(row)
+                        all_rows.append(row)
 
-                if runs:
-                    prompt_tps = mean(x["stats"]["prompt_tps"] for x in runs)
-                    gen_tps = mean(x["stats"]["generation_tps"] for x in runs)
-                    ptok = mean(x["stats"]["prompt_tokens"] for x in runs)
-                    gtok = mean(x["stats"]["generation_tokens"] for x in runs)
-                    peak = mean(
-                        x["stats"]["peak_memory_usage"]["inBytes"] for x in runs
-                    )
+                    if runs:
+                        prompt_tps = mean(x["stats"]["prompt_tps"] for x in runs)
+                        gen_tps = mean(x["stats"]["generation_tps"] for x in runs)
+                        ptok = mean(x["stats"]["prompt_tokens"] for x in runs)
+                        gtok = mean(x["stats"]["generation_tokens"] for x in runs)
+                        peak = mean(
+                            x["stats"]["peak_memory_usage"]["inBytes"] for x in runs
+                        )
 
-                    logger.info(
-                        f"prompt_tps={prompt_tps:.2f} gen_tps={gen_tps:.2f}    "
-                        f"prompt_tokens={ptok} gen_tokens={gtok}    "
-                        f"peak_memory={format_peak_memory(peak)}\n"
-                    )
-                time.sleep(2)
+                        logger.info(
+                            f"prompt_tps={prompt_tps:.2f} gen_tps={gen_tps:.2f}    "
+                            f"prompt_tokens={ptok} gen_tokens={gtok}    "
+                            f"peak_memory={format_peak_memory(peak)}\n"
+                        )
+                    time.sleep(2)
         finally:
             try:
                 client.request_json("DELETE", f"/instance/{instance_id}")

bench/exo_eval.py

@@ -0,0 +1,679 @@
+#!/usr/bin/env python3
+# pyright: reportAny=false, reportUnknownMemberType=false, reportUnknownVariableType=false, reportUnknownArgumentType=false
+"""
+exo-eval: Evaluation harness for exo inference system.
+
+Supports multiple evaluation frameworks via TOML configuration:
+- lm_eval: Language model evaluation using EleutherAI's lm-evaluation-harness
+- swe_bench: SWE-bench evaluation (placeholder for future implementation)
+- custom: Custom evaluation scripts
+
+Usage:
+    uv run python -m bench.exo_eval --config bench/eval_config.toml --model Llama-3.2-1b-Instruct-4bit
+    uv run python -m bench.exo_eval --config bench/eval_config.toml --model Llama-3.2-1b-Instruct-4bit --dry-run
+"""
+
+from __future__ import annotations
+
+import argparse
+import contextlib
+import json
+import os
+import subprocess
+import sys
+import time
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Literal
+
+# Add parent directory to path for direct script execution
+if __name__ == "__main__" and __package__ is None:
+    sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+import tomlkit
+from huggingface_hub import get_token as get_hf_token
+from loguru import logger
+from tomlkit.exceptions import TOMLKitError
+
+from bench.exo_bench import (
+    ExoClient,
+    ExoHttpError,
+    instance_id_from_instance,
+    nodes_used_in_instance,
+    placement_filter,
+    resolve_model_short_id,
+    sharding_filter,
+    wait_for_instance_gone,
+    wait_for_instance_ready,
+)
+
+EvalType = Literal["lm_eval", "swe_bench", "custom"]
+
+
+def load_config(config_path: str) -> dict[str, Any]:
+    """Load and parse TOML configuration file."""
+    path = Path(config_path)
+    if not path.exists():
+        raise FileNotFoundError(f"Config file not found: {config_path}")
+
+    with open(path, encoding="utf-8") as f:
+        return dict(tomlkit.load(f))
+
+
+def get_eval_type(config: dict[str, Any]) -> EvalType:
+    """Extract evaluation type from config."""
+    eval_section = config.get("eval", {})
+    eval_type = eval_section.get("type", "lm_eval")
+    if eval_type not in ("lm_eval", "swe_bench", "custom"):
+        raise ValueError(f"Unknown eval type: {eval_type}")
+    return eval_type
+
+
+def check_hf_token(config: dict[str, Any]) -> bool:
+    """Check if HuggingFace token is available when required.
+
+    Returns True if token is available or not required, False otherwise.
+    """
+    eval_section = config.get("eval", {})
+    require_hf_token = eval_section.get("require_hf_token", True)
+
+    if not require_hf_token:
+        return True
+
+    token = get_hf_token()
+    if token is None:
+        logger.error(
+            "HuggingFace token not found. "
+            "Set HF_TOKEN environment variable or run 'huggingface-cli login'. "
+            "To disable this check, set require_hf_token = false in [eval] config."
+        )
+        return False
+
+    logger.info("HuggingFace token found")
+    return True
+
+
+def select_placement(
+    client: ExoClient,
+    full_model_id: str,
+    config: dict[str, Any],
+) -> dict[str, Any] | None:
+    """Select a placement based on config preferences."""
+    instance_config = config.get("instance", {})
+
+    # If explicit instance is provided, use it directly
+    if "instance" in instance_config:
+        return instance_config["instance"]
+
+    # Otherwise, select from previews based on preferences
+    instance_meta_pref = instance_config.get("instance_meta", "ring")
+    sharding_pref = instance_config.get("sharding", "pipeline")
+    max_nodes = instance_config.get("max_nodes", 4)
+    min_nodes = instance_config.get("min_nodes", 1)
+
+    previews_resp = client.request_json(
+        "GET", "/instance/previews", params={"model_id": full_model_id}
+    )
+    previews = previews_resp.get("previews") or []
+
+    selected: list[dict[str, Any]] = []
+    for p in previews:
+        if p.get("error") is not None:
+            continue
+        if not placement_filter(str(p.get("instance_meta", "")), instance_meta_pref):
+            continue
+        if not sharding_filter(str(p.get("sharding", "")), sharding_pref):
+            continue
+
+        instance = p.get("instance")
+        if not isinstance(instance, dict):
+            continue
+
+        n = nodes_used_in_instance(instance)
+        if min_nodes <= n <= max_nodes:
+            selected.append(p)
+
+    if not selected:
+        return None
+
+    # Sort by preference: exact match on sharding/meta, then by node count (descending)
+    def sort_key(p: dict[str, Any]) -> tuple[int, int, int]:
+        meta_match = (
+            1 if instance_meta_pref in str(p.get("instance_meta", "")).lower() else 0
+        )
+        sharding_match = 1 if sharding_pref in str(p.get("sharding", "")).lower() else 0
+        n_nodes = nodes_used_in_instance(p["instance"])
+        return (meta_match, sharding_match, n_nodes)
+
+    selected.sort(key=sort_key, reverse=True)
+    return selected[0]
+
+
+def setup_instance(
+    client: ExoClient,
+    full_model_id: str,
+    config: dict[str, Any],
+    dry_run: bool,
+) -> tuple[str | None, dict[str, Any] | None]:
+    """Create and wait for an instance to be ready. Returns (instance_id, preview)."""
+    preview = select_placement(client, full_model_id, config)
+
+    if preview is None:
+        logger.error("No valid placement found matching config preferences")
+        return None, None
+
+    instance_data = preview.get("instance")
+    instance: dict[str, Any] = (
+        instance_data if isinstance(instance_data, dict) else preview
+    )
+    instance_id = instance_id_from_instance(instance)
+
+    sharding = str(preview.get("sharding", "unknown"))
+    instance_meta = str(preview.get("instance_meta", "unknown"))
+    n_nodes = nodes_used_in_instance(instance)
+
+    logger.info(f"Selected placement: {sharding} / {instance_meta} / nodes={n_nodes}")
+    logger.info(f"Instance ID: {instance_id}")
+
+    if dry_run:
+        logger.info("[dry-run] Would create instance and wait for ready")
+        return instance_id, preview
+
+    # Create instance
+    client.request_json("POST", "/instance", body={"instance": instance})
+
+    try:
+        wait_for_instance_ready(client, instance_id)
+        logger.info("Instance is ready")
+        time.sleep(1)  # Brief pause after ready
+        return instance_id, preview
+    except (RuntimeError, TimeoutError) as e:
+        logger.error(f"Failed to initialize instance: {e}")
+        with contextlib.suppress(ExoHttpError):
+            client.request_json("DELETE", f"/instance/{instance_id}")
+        return None, None
+
+
+def teardown_instance(client: ExoClient, instance_id: str) -> None:
+    """Delete an instance and wait for it to be gone."""
+    try:
+        client.request_json("DELETE", f"/instance/{instance_id}")
+    except ExoHttpError as e:
+        if e.status != 404:
+            raise
+    except (ConnectionRefusedError, OSError):
+        logger.warning(
+            f"Could not connect to exo to delete instance {instance_id} (server may be down)"
+        )
+        return
+    try:
+        wait_for_instance_gone(client, instance_id)
+    except (ConnectionRefusedError, OSError, TimeoutError):
+        logger.warning("Could not verify instance deletion (server may be down)")
+        return
+    logger.info(f"Instance {instance_id} deleted")
+
+
+def build_lm_eval_args(
+    config: dict[str, Any],
+    base_url: str,
+    model: str,
+    output_path: str | None,
+    limit: int | None,
+    use_completions: bool,
+) -> list[str]:
+    """Build command-line arguments for lm_eval."""
+    lm_eval_config = config.get("lm_eval", {})
+
+    # Choose model type based on whether tasks need completions API
+    if use_completions:
+        model_type = "local-completions"
+        endpoint_url = f"{base_url}/v1/completions"
+    else:
+        model_type = "local-chat-completions"
+        endpoint_url = f"{base_url}/v1/chat/completions"
+
+    # Build model_args string with num_concurrent and timeout
+    model_args_parts = [f"model={model}", f"base_url={endpoint_url}"]
+    num_concurrent = lm_eval_config.get("num_concurrent")
+    if num_concurrent is not None and num_concurrent > 1:
+        model_args_parts.append(f"num_concurrent={num_concurrent}")
+    # Use a very long timeout (1 week) to handle large request queues
+    timeout = lm_eval_config.get("timeout", 604800)
+    model_args_parts.append(f"timeout={timeout}")
+    model_args = ",".join(model_args_parts)
+
+    args = [
+        sys.executable,
+        "-m",
+        "bench.lm_eval_patched",
+        "--model",
+        model_type,
+        "--model_args",
+        model_args,
+        "--verbosity",
+        "WARNING",
+    ]
+
+    # Tasks
+    tasks = lm_eval_config.get("tasks", ["mmlu"])
+    tasks_str = ",".join(tasks) if isinstance(tasks, list) else str(tasks)
+    args.extend(["--tasks", tasks_str])
+
+    # Few-shot
+    num_fewshot = lm_eval_config.get("num_fewshot")
+    if num_fewshot is not None:
+        args.extend(["--num_fewshot", str(num_fewshot)])
+
+    # Batch size (default to 1 for API models, "auto" doesn't work)
+    batch_size = lm_eval_config.get("batch_size", 1)
+    args.extend(["--batch_size", str(batch_size)])
+
+    # Apply chat template for instruct/chat models (default: true)
+    # Only applies to chat completions, but doesn't hurt to include
+    apply_chat_template = lm_eval_config.get("apply_chat_template", True)
+    if apply_chat_template and not use_completions:
+        args.append("--apply_chat_template")
+
+    # Fewshot as multiturn (optional, works with chat template)
+    fewshot_as_multiturn = lm_eval_config.get("fewshot_as_multiturn", False)
+    if fewshot_as_multiturn and not use_completions:
+        args.append("--fewshot_as_multiturn")
+
+    # Limit (command line overrides config)
+    effective_limit = limit if limit is not None else lm_eval_config.get("limit")
+    if effective_limit is not None:
+        args.extend(["--limit", str(effective_limit)])
+
+    # Output path
+    effective_output = output_path or lm_eval_config.get("output_path")
+    if effective_output:
+        args.extend(["--output_path", effective_output])
+        # Log model responses for post-hoc analysis when output is saved
+        args.append("--log_samples")
+
+    return args
+
+
+def run_lm_eval(
+    config: dict[str, Any],
+    host: str,
+    port: int,
+    model: str,
+    output_path: str | None,
+    limit: int | None,
+    dry_run: bool,
+) -> int:
+    """Run lm_eval evaluation."""
+    lm_eval_config = config.get("lm_eval", {})
+    tasks = lm_eval_config.get("tasks", ["mmlu"])
+    if isinstance(tasks, str):
+        tasks = [tasks]
+
+    exo_base_url = f"http://{host}:{port}"
+
+    # Build args - use native completions or chat completions endpoint directly
+    args = build_lm_eval_args(
+        config, exo_base_url, model, output_path, limit, use_completions=False
+    )
+    logger.info(f"lm_eval command: {' '.join(args)}")
+
+    if dry_run:
+        logger.info("[dry-run] Would execute the above command")
+        return 0
+
+    try:
+        result = subprocess.run(args, check=False)
+
+        # Print token usage summary from exo
+        try:
+            import httpx
+
+            usage_resp = httpx.get(f"{exo_base_url}/v1/usage", timeout=5)
+            if usage_resp.status_code == 200:
+                usage = usage_resp.json()
+                logger.info("--- Token Usage (Total) ---")
+                logger.info(f"  Requests:          {usage.get('total_requests', 0)}")
+                logger.info(
+                    f"  Prompt tokens:     {usage.get('total_prompt_tokens', 0)}"
+                )
+                logger.info(
+                    f"  Completion tokens: {usage.get('total_completion_tokens', 0)}"
+                )
+                logger.info(
+                    f"  Reasoning tokens:  {usage.get('total_reasoning_tokens', 0)}"
+                )
+                logger.info(f"  Total tokens:      {usage.get('total_tokens', 0)}")
+                by_model = usage.get("by_model", {})
+                if by_model:
+                    for model_name, counters in by_model.items():
+                        logger.info(f"--- Token Usage ({model_name}) ---")
+                        logger.info(
+                            f"  Requests:          {counters.get('requests', 0)}"
+                        )
+                        logger.info(
+                            f"  Prompt tokens:     {counters.get('prompt_tokens', 0)}"
+                        )
+                        logger.info(
+                            f"  Completion tokens: {counters.get('completion_tokens', 0)}"
+                        )
+                        logger.info(
+                            f"  Reasoning tokens:  {counters.get('reasoning_tokens', 0)}"
+                        )
+        except Exception:
+            pass  # Usage endpoint not available
+
+        return result.returncode
+    except FileNotFoundError:
+        logger.error("lm_eval not found. Install with: uv sync --extra eval")
+        return 1
+
+
+def run_swe_bench(
+    config: dict[str, Any],
+    host: str,
+    port: int,
+    model: str,
+    output_path: str | None,
+    dry_run: bool,
+) -> int:
+    """Run SWE-bench evaluation (placeholder)."""
+    swe_config = config.get("swe_bench", {})
+
+    dataset = swe_config.get("dataset", "princeton-nlp/SWE-bench_Lite")
+    max_workers = swe_config.get("max_workers", 8)
+    predictions_path = output_path or swe_config.get(
+        "predictions_path", "bench/predictions"
+    )
+
+    logger.info("SWE-bench evaluation configuration:")
+    logger.info(f"  Dataset: {dataset}")
+    logger.info(f"  Model: {model}")
+    logger.info(f"  API endpoint: http://{host}:{port}/v1")
+    logger.info(f"  Max workers: {max_workers}")
+    logger.info(f"  Predictions path: {predictions_path}")
+
+    if dry_run:
+        logger.info("[dry-run] SWE-bench evaluation would be executed")
+        return 0
+
+    logger.warning(
+        "SWE-bench integration is a placeholder. "
+        "Implement swebench inference and evaluation logic as needed."
+    )
+    return 0
+
+
+def run_custom_eval(
+    config: dict[str, Any],
+    host: str,
+    port: int,
+    model: str,
+    output_path: str | None,
+    dry_run: bool,
+) -> int:
+    """Run custom evaluation script."""
+    custom_config = config.get("custom", {})
+
+    script = custom_config.get("script")
+    if not script:
+        logger.error("No script specified in [custom] config section")
+        return 1
+
+    script_path = Path(script)
+    if not script_path.exists():
+        logger.error(f"Custom script not found: {script}")
+        return 1
+
+    script_args = custom_config.get("args", [])
+    if not isinstance(script_args, list):
+        script_args = [str(script_args)]
+
+    # Build environment with exo connection info
+    env = os.environ.copy()
+    env["EXO_HOST"] = host
+    env["EXO_PORT"] = str(port)
+    env["EXO_MODEL"] = model
+    if output_path:
+        env["EXO_OUTPUT_PATH"] = output_path
+
+    cmd = [sys.executable, str(script_path), *script_args]
+    logger.info(f"Custom eval command: {' '.join(cmd)}")
+
+    if dry_run:
+        logger.info("[dry-run] Would execute the above command")
+        return 0
+
+    result = subprocess.run(cmd, env=env, check=False)
+    return result.returncode
+
+
+def write_results_metadata(
+    output_path: str,
+    config: dict[str, Any],
+    host: str,
+    port: int,
+    model: str,
+    eval_type: EvalType,
+    return_code: int,
+    preview: dict[str, Any] | None,
+) -> None:
+    """Write evaluation metadata to a JSON file."""
+    metadata: dict[str, Any] = {
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "eval_type": eval_type,
+        "model": model,
+        "api_endpoint": f"http://{host}:{port}/v1",
+        "config": config,
+        "return_code": return_code,
+    }
+
+    if preview:
+        metadata["placement"] = {
+            "sharding": preview.get("sharding"),
+            "instance_meta": preview.get("instance_meta"),
+            "instance_id": instance_id_from_instance(preview["instance"])
+            if "instance" in preview
+            else None,
+        }
+
+    output_dir = Path(output_path)
+    output_dir.mkdir(parents=True, exist_ok=True)
+    metadata_path = output_dir / "eval_metadata.json"
+
+    with open(metadata_path, "w", encoding="utf-8") as f:
+        json.dump(metadata, f, indent=2, ensure_ascii=False, default=str)
+
+    logger.info(f"Wrote evaluation metadata to: {metadata_path}")
+
+
+def main() -> int:
+    """Main entry point for exo-eval."""
+    ap = argparse.ArgumentParser(
+        prog="exo-eval",
+        description="Evaluation harness for exo inference system.",
+    )
+    ap.add_argument(
+        "--config",
+        required=True,
+        help="Path to TOML configuration file",
+    )
+    ap.add_argument(
+        "--host",
+        default=os.environ.get("EXO_HOST", "localhost"),
+        help="exo API host (default: localhost or EXO_HOST env var)",
+    )
+    ap.add_argument(
+        "--port",
+        type=int,
+        default=int(os.environ.get("EXO_PORT", "52415")),
+        help="exo API port (default: 52415 or EXO_PORT env var)",
+    )
+    ap.add_argument(
+        "--model",
+        required=True,
+        help="Model name/ID to evaluate",
+    )
+    ap.add_argument(
+        "--output",
+        default=None,
+        help="Output path for results (overrides config)",
+    )
+    ap.add_argument(
+        "--limit",
+        type=int,
+        default=None,
+        help="Limit samples per task (overrides config, lm_eval only)",
+    )
+    ap.add_argument(
+        "--timeout",
+        type=float,
+        default=604800.0,
+        help="HTTP timeout in seconds (default: 604800 = 1 week)",
+    )
+    ap.add_argument(
+        "--skip-instance-setup",
+        action="store_true",
+        help="Skip instance creation (assume instance already running)",
+    )
+    ap.add_argument(
+        "--pipeline",
+        type=int,
+        default=None,
+        metavar="N",
+        help="Use pipeline sharding with exactly N nodes (overrides config)",
+    )
+    ap.add_argument(
+        "--instance-meta",
+        choices=["ring", "jaccl", "both"],
+        default=None,
+        help="Instance meta preference (overrides config)",
+    )
+    ap.add_argument(
+        "--dry-run",
+        action="store_true",
+        help="Print commands without executing",
+    )
+    args = ap.parse_args()
+
+    logger.info(f"exo-eval starting with config: {args.config}")
+
+    try:
+        config = load_config(args.config)
+    except FileNotFoundError as e:
+        logger.error(str(e))
+        return 1
+    except TOMLKitError as e:
+        logger.error(f"Failed to parse config: {e}")
+        return 1
+
+    eval_type = get_eval_type(config)
+    logger.info(f"Evaluation type: {eval_type}")
+    logger.info(f"Model: {args.model}")
+    logger.info(f"API endpoint: http://{args.host}:{args.port}/v1")
+
+    # Apply CLI overrides to instance config
+    if args.pipeline is not None or args.instance_meta is not None:
+        instance_config = config.setdefault("instance", {})
+        if args.pipeline is not None:
+            instance_config["sharding"] = "pipeline"
+            instance_config["min_nodes"] = args.pipeline
+            instance_config["max_nodes"] = args.pipeline
+            logger.info(f"CLI override: pipeline={args.pipeline} nodes")
+            # Limit concurrency for pipeline to avoid GPU timeouts
+            if args.pipeline >= 2:
+                lm_eval_config = config.setdefault("lm_eval", {})
+                lm_eval_config["num_concurrent"] = 4
+                logger.info("CLI override: num_concurrent=4 (pipeline>=2)")
+        if args.instance_meta is not None:
+            instance_config["instance_meta"] = args.instance_meta
+            logger.info(f"CLI override: instance_meta={args.instance_meta}")
+
+    # Check HuggingFace token if required
+    if not check_hf_token(config):
+        return 1
+
+    # Setup instance and resolve model
+    instance_id: str | None = None
+    preview: dict[str, Any] | None = None
+    client: ExoClient | None = None
+
+    if args.skip_instance_setup:
+        # Use model name as-is when skipping instance setup
+        full_model_id = args.model
+        logger.info(f"Using model: {full_model_id} (instance setup skipped)")
+    else:
+        client = ExoClient(args.host, args.port, timeout_s=args.timeout)
+
+        # Resolve model
+        try:
+            short_id, full_model_id = resolve_model_short_id(client, args.model)
+            logger.info(f"Resolved model: {short_id} -> {full_model_id}")
+        except Exception as e:
+            logger.error(f"Failed to resolve model: {e}")
+            return 1
+
+        instance_id, preview = setup_instance(
+            client, full_model_id, config, args.dry_run
+        )
+        if instance_id is None and not args.dry_run:
+            return 1
+
+    try:
+        # Run evaluation
+        if eval_type == "lm_eval":
+            return_code = run_lm_eval(
+                config,
+                args.host,
+                args.port,
+                full_model_id,
+                args.output,
+                args.limit,
+                args.dry_run,
+            )
+        elif eval_type == "swe_bench":
+            return_code = run_swe_bench(
+                config,
+                args.host,
+                args.port,
+                full_model_id,
+                args.output,
+                args.dry_run,
+            )
+        elif eval_type == "custom":
+            return_code = run_custom_eval(
+                config,
+                args.host,
+                args.port,
+                full_model_id,
+                args.output,
+                args.dry_run,
+            )
+        else:
+            logger.error(f"Unknown eval type: {eval_type}")
+            return 1
+
+        # Write metadata if output path specified and not dry-run
+        output_path = args.output or config.get(eval_type, {}).get("output_path")
+        if output_path and not args.dry_run:
+            write_results_metadata(
+                output_path,
+                config,
+                args.host,
+                args.port,
+                full_model_id,
+                eval_type,
+                return_code,
+                preview,
+            )
+
+        return return_code
+
+    finally:
+        # Teardown instance
+        if instance_id and client and not args.skip_instance_setup and not args.dry_run:
+            teardown_instance(client, instance_id)
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

bench/lm_eval_patched.py

@@ -0,0 +1,145 @@
+"""Patched lm_eval runner that fixes bugs in the upstream library.
+
+Fixes:
+- UnboundLocalError on `outputs` in TemplateAPI.amodel_call when API returns error
+- Prevents eval crash on transient API failures (returns None instead of raising)
+- Compatibility with transformers 5.x (missing AutoModelForVision2Seq)
+- sock_read timeout causing connection drops with large request queues
+
+Usage: python -m bench.lm_eval_patched [lm_eval args...]
+"""
+
+# ruff: noqa: I001, E402
+# pyright: reportMissingTypeStubs=false, reportUnknownVariableType=false
+# pyright: reportUnknownMemberType=false, reportAny=false, reportUnknownArgumentType=false
+# pyright: reportPrivateUsage=false, reportUnknownLambdaType=false
+
+# MUST patch transformers BEFORE any lm_eval imports
+# AutoModelForVision2Seq/AutoModelForImageTextToText were removed in transformers 5.0
+# Patch the lazy module's __getattr__ to return stubs for missing classes
+from transformers.utils import import_utils
+
+_original_getattr = import_utils._LazyModule.__getattr__
+
+
+def _patched_getattr(self: object, name: str) -> object:
+    if name in ("AutoModelForVision2Seq", "AutoModelForImageTextToText"):
+        return type(name, (), {})  # Return a stub class
+    return _original_getattr(self, name)  # type: ignore
+
+
+import_utils._LazyModule.__getattr__ = _patched_getattr
+
+import functools
+from typing import Any
+
+
+def _patch_amodel_call() -> None:
+    """Monkey-patch TemplateAPI.amodel_call to handle the unbound `outputs` variable bug."""
+    from lm_eval.models.api_models import TemplateAPI
+
+    original: Any = TemplateAPI.amodel_call
+
+    @functools.wraps(original)
+    async def patched_amodel_call(self: Any, *args: Any, **kwargs: Any) -> Any:
+        try:
+            return await original(self, *args, **kwargs)
+        except (UnboundLocalError, Exception):
+            # Return one empty-string result per request in the batch so the
+            # reorderer doesn't assert on missing coverage.
+            messages = kwargs.get("messages") or (args[2] if len(args) > 2 else [])
+            return [""] * max(len(messages), 1)
+
+    TemplateAPI.amodel_call = patched_amodel_call
+
+
+def _patch_client_timeout() -> None:
+    """Patch TemplateAPI.get_batched_requests to disable sock_read timeout.
+
+    By default, aiohttp's ClientTimeout can have a sock_read timeout that causes
+    connections to drop if no data is received for a while. With large request
+    queues, requests may wait a long time before processing starts, causing
+    spurious connection drops and retries that pile up requests.
+    """
+    from aiohttp import ClientSession, ClientTimeout, TCPConnector
+
+    from lm_eval.models.api_models import TemplateAPI
+
+    original_get_batched: Any = TemplateAPI.get_batched_requests
+
+    @functools.wraps(original_get_batched)
+    async def patched_get_batched_requests(self: Any, *args: Any, **kwargs: Any) -> Any:
+        # Override the timeout to explicitly disable sock_read timeout
+        # This prevents connection drops when requests are queued for a long time
+        original_timeout = getattr(self, "timeout", 604800)
+        conn = TCPConnector(limit=self._concurrent, ssl=self.verify_certificate)
+        timeout = ClientTimeout(
+            total=original_timeout, sock_read=None, sock_connect=None
+        )
+
+        async with ClientSession(connector=conn, timeout=timeout) as session:
+            # Call the internal async logic with our session
+            return await _run_batched_requests_with_session(
+                self, session, *args, **kwargs
+            )
+
+    async def _run_batched_requests_with_session(
+        self: Any,
+        session: ClientSession,
+        requests: Any,
+        cache_keys: Any = None,
+        ctxlens: Any = None,
+        **kwargs: Any,
+    ) -> Any:
+        import asyncio
+        import copy
+        import logging
+
+        from tqdm.asyncio import tqdm_asyncio
+        from tenacity import retry, stop_after_attempt, wait_exponential
+        from lm_eval.models.utils import chunks
+
+        eval_logger = logging.getLogger("lm_eval.models.api_models")
+        ctxlens = ctxlens if ctxlens else [None] * len(requests)
+        sem = asyncio.Semaphore(self._concurrent)
+
+        retry_: Any = retry(
+            stop=stop_after_attempt(self.max_retries),
+            wait=wait_exponential(multiplier=0.5, min=1, max=10),
+            reraise=True,
+            before_sleep=lambda retry_state: eval_logger.info(
+                f"Retry attempt {retry_state.attempt_number}"
+            ),
+        )(self.amodel_call)
+
+        tasks = [
+            asyncio.create_task(
+                retry_(
+                    session=session,
+                    sem=sem,
+                    messages=message,
+                    cache_keys=cache_key,
+                    ctxlens=ctxlen,
+                    gen_kwargs=copy.deepcopy(kwargs.get("gen_kwargs")),
+                    **{k: v for k, v in kwargs.items() if k != "gen_kwargs"},
+                )
+            )
+            for message, cache_key, ctxlen in zip(
+                chunks(requests, n=self._batch_size),
+                chunks(cache_keys, n=self._batch_size),
+                chunks(ctxlens, n=self._batch_size),
+                strict=True,
+            )
+        ]
+
+        return await tqdm_asyncio.gather(*tasks, desc="Requesting API")
+
+    TemplateAPI.get_batched_requests = patched_get_batched_requests
+
+
+if __name__ == "__main__":
+    _patch_amodel_call()
+    _patch_client_timeout()
+    from lm_eval.__main__ import cli_evaluate
+
+    cli_evaluate()

bench/stats_dashboard.html

@@ -0,0 +1,290 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>exo Usage Stats</title>
+<style>
+  * { margin: 0; padding: 0; box-sizing: border-box; }
+  body {
+    font-family: -apple-system, BlinkMacSystemFont, 'SF Mono', 'Menlo', monospace;
+    background: #1a1a2e;
+    color: #e0e0e0;
+    padding: 24px;
+    min-height: 100vh;
+  }
+  .header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-bottom: 24px;
+    padding-bottom: 16px;
+    border-bottom: 1px solid #333;
+  }
+  .header h1 {
+    font-size: 20px;
+    font-weight: 600;
+    color: #fff;
+  }
+  .status {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    font-size: 13px;
+    color: #888;
+  }
+  .status-dot {
+    width: 8px;
+    height: 8px;
+    border-radius: 50%;
+    background: #666;
+  }
+  .status-dot.connected { background: #4caf50; }
+  .status-dot.error { background: #f44336; }
+  .config {
+    margin-bottom: 24px;
+    display: flex;
+    align-items: center;
+    gap: 8px;
+  }
+  .config label {
+    font-size: 12px;
+    color: #888;
+  }
+  .config input {
+    background: #252540;
+    border: 1px solid #444;
+    border-radius: 4px;
+    color: #e0e0e0;
+    padding: 4px 8px;
+    font-size: 13px;
+    font-family: inherit;
+    width: 280px;
+  }
+  .section {
+    background: #252540;
+    border-radius: 8px;
+    padding: 20px;
+    margin-bottom: 16px;
+  }
+  .section h2 {
+    font-size: 14px;
+    font-weight: 600;
+    color: #aaa;
+    text-transform: uppercase;
+    letter-spacing: 0.5px;
+    margin-bottom: 16px;
+  }
+  .stat-grid {
+    display: grid;
+    grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
+    gap: 16px;
+  }
+  .stat-card {
+    background: #1a1a2e;
+    border-radius: 6px;
+    padding: 16px;
+  }
+  .stat-label {
+    font-size: 11px;
+    color: #888;
+    text-transform: uppercase;
+    letter-spacing: 0.5px;
+    margin-bottom: 4px;
+  }
+  .stat-value {
+    font-size: 28px;
+    font-weight: 700;
+    color: #fff;
+  }
+  .stat-rate {
+    font-size: 12px;
+    color: #4caf50;
+    margin-top: 4px;
+  }
+  table {
+    width: 100%;
+    border-collapse: collapse;
+    font-size: 13px;
+  }
+  th {
+    text-align: left;
+    padding: 8px 12px;
+    color: #888;
+    font-weight: 500;
+    border-bottom: 1px solid #333;
+    font-size: 11px;
+    text-transform: uppercase;
+    letter-spacing: 0.5px;
+  }
+  td {
+    padding: 8px 12px;
+    border-bottom: 1px solid #2a2a45;
+  }
+  td.num {
+    text-align: right;
+    font-variant-numeric: tabular-nums;
+  }
+  .model-name {
+    color: #7c9eff;
+    max-width: 300px;
+    overflow: hidden;
+    text-overflow: ellipsis;
+    white-space: nowrap;
+  }
+  .empty-state {
+    color: #666;
+    font-style: italic;
+    padding: 16px 0;
+  }
+</style>
+</head>
+<body>
+  <div class="header">
+    <h1>exo Usage Stats</h1>
+    <div class="status">
+      <div class="status-dot" id="statusDot"></div>
+      <span id="statusText">connecting...</span>
+    </div>
+  </div>
+
+  <div class="config">
+    <label for="baseUrl">Base URL:</label>
+    <input type="text" id="baseUrl" value="http://mac8-1:52415">
+  </div>
+
+  <div class="section">
+    <h2>Totals</h2>
+    <div class="stat-grid">
+      <div class="stat-card">
+        <div class="stat-label">Requests</div>
+        <div class="stat-value" id="totalRequests">0</div>
+      </div>
+      <div class="stat-card">
+        <div class="stat-label">Prompt Tokens</div>
+        <div class="stat-value" id="totalPrompt">0</div>
+        <div class="stat-rate" id="promptRate"></div>
+      </div>
+      <div class="stat-card">
+        <div class="stat-label">Completion Tokens</div>
+        <div class="stat-value" id="totalCompletion">0</div>
+        <div class="stat-rate" id="completionRate"></div>
+      </div>
+      <div class="stat-card">
+        <div class="stat-label">Reasoning Tokens</div>
+        <div class="stat-value" id="totalReasoning">0</div>
+      </div>
+      <div class="stat-card">
+        <div class="stat-label">Total Tokens</div>
+        <div class="stat-value" id="totalTokens">0</div>
+        <div class="stat-rate" id="totalRate"></div>
+      </div>
+    </div>
+  </div>
+
+  <div class="section">
+    <h2>Per-Model Breakdown</h2>
+    <div id="modelTable">
+      <div class="empty-state">No data yet</div>
+    </div>
+  </div>
+
+<script>
+
+  function fmt(n) {
+    return n.toLocaleString();
+  }
+
+  // Track first non-zero timestamp for overall average rate
+  let firstSeenTime = null;
+  let firstSeenTokens = { prompt: 0, completion: 0, total: 0 };
+
+  function setRate(id, currentTokens, tokenType) {
+    const el = document.getElementById(id);
+    if (firstSeenTime === null || currentTokens <= firstSeenTokens[tokenType]) {
+      el.textContent = '';
+      return;
+    }
+    const elapsed = (performance.now() / 1000) - firstSeenTime;
+    if (elapsed <= 0) { el.textContent = ''; return; }
+    const delta = currentTokens - firstSeenTokens[tokenType];
+    const avg = delta / elapsed;
+    el.textContent = fmt(Math.round(avg)) + ' tok/s avg';
+  }
+
+  function renderModelTable(byModel) {
+    const container = document.getElementById('modelTable');
+    const models = Object.entries(byModel);
+    if (models.length === 0) {
+      container.innerHTML = '<div class="empty-state">No data yet</div>';
+      return;
+    }
+    let html = '<table><thead><tr>';
+    html += '<th>Model</th><th style="text-align:right">Requests</th>';
+    html += '<th style="text-align:right">Prompt</th>';
+    html += '<th style="text-align:right">Completion</th>';
+    html += '<th style="text-align:right">Reasoning</th>';
+    html += '<th style="text-align:right">Total</th>';
+    html += '</tr></thead><tbody>';
+    for (const [name, counters] of models) {
+      const total = (counters.prompt_tokens || 0) + (counters.completion_tokens || 0);
+      html += '<tr>';
+      html += `<td class="model-name" title="${name}">${name}</td>`;
+      html += `<td class="num">${fmt(counters.requests || 0)}</td>`;
+      html += `<td class="num">${fmt(counters.prompt_tokens || 0)}</td>`;
+      html += `<td class="num">${fmt(counters.completion_tokens || 0)}</td>`;
+      html += `<td class="num">${fmt(counters.reasoning_tokens || 0)}</td>`;
+      html += `<td class="num">${fmt(total)}</td>`;
+      html += '</tr>';
+    }
+    html += '</tbody></table>';
+    container.innerHTML = html;
+  }
+
+  async function poll() {
+    const baseUrl = document.getElementById('baseUrl').value.replace(/\/+$/, '');
+    const dot = document.getElementById('statusDot');
+    const text = document.getElementById('statusText');
+
+    try {
+      const resp = await fetch(baseUrl + '/v1/usage');
+      if (!resp.ok) throw new Error(`HTTP ${resp.status}`);
+      const data = await resp.json();
+
+      dot.className = 'status-dot connected';
+      text.textContent = 'connected';
+
+
+      document.getElementById('totalRequests').textContent = fmt(data.total_requests || 0);
+      document.getElementById('totalPrompt').textContent = fmt(data.total_prompt_tokens || 0);
+      document.getElementById('totalCompletion').textContent = fmt(data.total_completion_tokens || 0);
+      document.getElementById('totalReasoning').textContent = fmt(data.total_reasoning_tokens || 0);
+      document.getElementById('totalTokens').textContent = fmt(data.total_tokens || 0);
+
+      // Record first non-zero reading as baseline
+      if (firstSeenTime === null && (data.total_tokens || 0) > 0) {
+        firstSeenTime = performance.now() / 1000;
+        firstSeenTokens = {
+          prompt: data.total_prompt_tokens || 0,
+          completion: data.total_completion_tokens || 0,
+          total: data.total_tokens || 0,
+        };
+      }
+
+      setRate('promptRate', data.total_prompt_tokens || 0, 'prompt');
+      setRate('completionRate', data.total_completion_tokens || 0, 'completion');
+      setRate('totalRate', data.total_tokens || 0, 'total');
+
+      renderModelTable(data.by_model || {});
+
+    } catch (e) {
+      dot.className = 'status-dot error';
+      text.textContent = e.message || 'error';
+    }
+  }
+
+  poll();
+  setInterval(poll, 1000);
+</script>
+</body>
+</html>

dashboard/package-lock.json

@@ -865,6 +865,7 @@
 			"integrity": "sha512-oH8tXw7EZnie8FdOWYrF7Yn4IKrqTFHhXvl8YxXxbKwTMcD/5NNCryUSEXRk2ZR4ojnub0P8rNrsVGHXWqIDtA==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@standard-schema/spec": "^1.0.0",
 				"@sveltejs/acorn-typescript": "^1.0.5",
@@ -904,6 +905,7 @@
 			"integrity": "sha512-Y1Cs7hhTc+a5E9Va/xwKlAJoariQyHY+5zBgCZg4PFWNYQ1nMN9sjK1zhw1gK69DuqVP++sht/1GZg1aRwmAXQ==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@sveltejs/vite-plugin-svelte-inspector": "^4.0.1",
 				"debug": "^4.4.1",
@@ -1520,6 +1522,7 @@
 			"integrity": "sha512-LCCV0HdSZZZb34qifBsyWlUmok6W7ouER+oQIGBScS8EsZsQbrtFTUrDX4hOl+CS6p7cnNC4td+qrSVGSCTUfQ==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"undici-types": "~6.21.0"
 			}
@@ -1529,6 +1532,7 @@
 			"resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz",
 			"integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
 			"license": "MIT",
+			"peer": true,
 			"bin": {
 				"acorn": "bin/acorn"
 			},
@@ -1941,6 +1945,7 @@
 			"integrity": "sha512-fmTRWbNMmsmWq6xJV8D19U/gw/bwrHfNXxrIN+HfZgnzqTHp9jOmKMhsTUjXOJnZOdZY9Q28y4yebKzqDKlxlQ==",
 			"dev": true,
 			"license": "ISC",
+			"peer": true,
 			"engines": {
 				"node": ">=12"
 			}
@@ -2648,6 +2653,7 @@
 			"integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"engines": {
 				"node": ">=12"
 			},
@@ -2690,6 +2696,7 @@
 			"integrity": "sha512-UOnG6LftzbdaHZcKoPFtOcCKztrQ57WkHDeRD9t/PTQtmT0NHSeWWepj6pS0z/N7+08BHFDQVUrfmfMRcZwbMg==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"bin": {
 				"prettier": "bin/prettier.cjs"
 			},
@@ -2862,6 +2869,7 @@
 			"resolved": "https://registry.npmjs.org/svelte/-/svelte-5.45.3.tgz",
 			"integrity": "sha512-ngKXNhNvwPzF43QqEhDOue7TQTrG09em1sd4HBxVF0Wr2gopAmdEWan+rgbdgK4fhBtSOTJO8bYU4chUG7VXZQ==",
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"@jridgewell/remapping": "^2.3.4",
 				"@jridgewell/sourcemap-codec": "^1.5.0",
@@ -3006,6 +3014,7 @@
 			"integrity": "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==",
 			"dev": true,
 			"license": "Apache-2.0",
+			"peer": true,
 			"bin": {
 				"tsc": "bin/tsc",
 				"tsserver": "bin/tsserver"
@@ -3027,6 +3036,7 @@
 			"integrity": "sha512-+Oxm7q9hDoLMyJOYfUYBuHQo+dkAloi33apOPP56pzj+vsdJDzr+j1NISE5pyaAuKL4A3UD34qd0lx5+kfKp2g==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"esbuild": "^0.25.0",
 				"fdir": "^6.4.4",

dashboard/src/lib/components/FamilyLogos.svelte

@@ -1,73 +0,0 @@
-<script lang="ts">
-  type FamilyLogoProps = {
-    family: string;
-    class?: string;
-  };
-
-  let { family, class: className = "" }: FamilyLogoProps = $props();
-</script>
-
-{#if family === "favorites"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12 2l3.09 6.26L22 9.27l-5 4.87 1.18 6.88L12 17.77l-6.18 3.25L7 14.14 2 9.27l6.91-1.01L12 2z"
-    />
-  </svg>
-{:else if family === "llama" || family === "meta"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M6.915 4.03c-1.968 0-3.683 1.28-4.871 3.113C.704 9.208 0 11.883 0 14.449c0 .706.07 1.369.21 1.973a6.624 6.624 0 0 0 .265.86 5.297 5.297 0 0 0 .371.761c.696 1.159 1.818 1.927 3.593 1.927 1.497 0 2.633-.671 3.965-2.444.76-1.012 1.144-1.626 2.663-4.32l.756-1.339.186-.325c.061.1.121.196.183.3l2.152 3.595c.724 1.21 1.665 2.556 2.47 3.314 1.046.987 1.992 1.22 3.06 1.22 1.075 0 1.876-.355 2.455-.843a3.743 3.743 0 0 0 .81-.973c.542-.939.861-2.127.861-3.745 0-2.72-.681-5.357-2.084-7.45-1.282-1.912-2.957-2.93-4.716-2.93-1.047 0-2.088.467-3.053 1.308-.652.57-1.257 1.29-1.82 2.05-.69-.875-1.335-1.547-1.958-2.056-1.182-.966-2.315-1.303-3.454-1.303zm10.16 2.053c1.147 0 2.188.758 2.992 1.999 1.132 1.748 1.647 4.195 1.647 6.4 0 1.548-.368 2.9-1.839 2.9-.58 0-1.027-.23-1.664-1.004-.496-.601-1.343-1.878-2.832-4.358l-.617-1.028a44.908 44.908 0 0 0-1.255-1.98c.07-.109.141-.224.211-.327 1.12-1.667 2.118-2.602 3.358-2.602zm-10.201.553c1.265 0 2.058.791 2.675 1.446.307.327.737.871 1.234 1.579l-1.02 1.566c-.757 1.163-1.882 3.017-2.837 4.338-1.191 1.649-1.81 1.817-2.486 1.817-.524 0-1.038-.237-1.383-.794-.263-.426-.464-1.13-.464-2.046 0-2.221.63-4.535 1.66-6.088.454-.687.964-1.226 1.533-1.533a2.264 2.264 0 0 1 1.088-.285z"
-    />
-  </svg>
-{:else if family === "qwen"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12.604 1.34c.393.69.784 1.382 1.174 2.075a.18.18 0 00.157.091h5.552c.174 0 .322.11.446.327l1.454 2.57c.19.337.24.478.024.837-.26.43-.513.864-.76 1.3l-.367.658c-.106.196-.223.28-.04.512l2.652 4.637c.172.301.111.494-.043.77-.437.785-.882 1.564-1.335 2.34-.159.272-.352.375-.68.37-.777-.016-1.552-.01-2.327.016a.099.099 0 00-.081.05 575.097 575.097 0 01-2.705 4.74c-.169.293-.38.363-.725.364-.997.003-2.002.004-3.017.002a.537.537 0 01-.465-.271l-1.335-2.323a.09.09 0 00-.083-.049H4.982c-.285.03-.553-.001-.805-.092l-1.603-2.77a.543.543 0 01-.002-.54l1.207-2.12a.198.198 0 000-.197 550.951 550.951 0 01-1.875-3.272l-.79-1.395c-.16-.31-.173-.496.095-.965.465-.813.927-1.625 1.387-2.436.132-.234.304-.334.584-.335a338.3 338.3 0 012.589-.001.124.124 0 00.107-.063l2.806-4.895a.488.488 0 01.422-.246c.524-.001 1.053 0 1.583-.006L11.704 1c.341-.003.724.032.9.34zm-3.432.403a.06.06 0 00-.052.03L6.254 6.788a.157.157 0 01-.135.078H3.253c-.056 0-.07.025-.041.074l5.81 10.156c.025.042.013.062-.034.063l-2.795.015a.218.218 0 00-.2.116l-1.32 2.31c-.044.078-.021.118.068.118l5.716.008c.046 0 .08.02.104.061l1.403 2.454c.046.081.092.082.139 0l5.006-8.76.783-1.382a.055.055 0 01.096 0l1.424 2.53a.122.122 0 00.107.062l2.763-.02a.04.04 0 00.035-.02.041.041 0 000-.04l-2.9-5.086a.108.108 0 010-.113l.293-.507 1.12-1.977c.024-.041.012-.062-.035-.062H9.2c-.059 0-.073-.026-.043-.077l1.434-2.505a.107.107 0 000-.114L9.225 1.774a.06.06 0 00-.053-.031zm6.29 8.02c.046 0 .058.02.034.06l-.832 1.465-2.613 4.585a.056.056 0 01-.05.029.058.058 0 01-.05-.029L8.498 9.841c-.02-.034-.01-.052.028-.054l.216-.012 6.722-.012z"
-    />
-  </svg>
-{:else if family === "deepseek"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M23.748 4.482c-.254-.124-.364.113-.512.234-.051.039-.094.09-.137.136-.372.397-.806.657-1.373.626-.829-.046-1.537.214-2.163.848-.133-.782-.575-1.248-1.247-1.548-.352-.156-.708-.311-.955-.65-.172-.241-.219-.51-.305-.774-.055-.16-.11-.323-.293-.35-.2-.031-.278.136-.356.276-.313.572-.434 1.202-.422 1.84.027 1.436.633 2.58 1.838 3.393.137.093.172.187.129.323-.082.28-.18.552-.266.833-.055.179-.137.217-.329.14a5.526 5.526 0 01-1.736-1.18c-.857-.828-1.631-1.742-2.597-2.458a11.365 11.365 0 00-.689-.471c-.985-.957.13-1.743.388-1.836.27-.098.093-.432-.779-.428-.872.004-1.67.295-2.687.684a3.055 3.055 0 01-.465.137 9.597 9.597 0 00-2.883-.102c-1.885.21-3.39 1.102-4.497 2.623C.082 8.606-.231 10.684.152 12.85c.403 2.284 1.569 4.175 3.36 5.653 1.858 1.533 3.997 2.284 6.438 2.14 1.482-.085 3.133-.284 4.994-1.86.47.234.962.327 1.78.397.63.059 1.236-.03 1.705-.128.735-.156.684-.837.419-.961-2.155-1.004-1.682-.595-2.113-.926 1.096-1.296 2.746-2.642 3.392-7.003.05-.347.007-.565 0-.845-.004-.17.035-.237.23-.256a4.173 4.173 0 001.545-.475c1.396-.763 1.96-2.015 2.093-3.517.02-.23-.004-.467-.247-.588zM11.581 18c-2.089-1.642-3.102-2.183-3.52-2.16-.392.024-.321.471-.235.763.09.288.207.486.371.739.114.167.192.416-.113.603-.673.416-1.842-.14-1.897-.167-1.361-.802-2.5-1.86-3.301-3.307-.774-1.393-1.224-2.887-1.298-4.482-.02-.386.093-.522.477-.592a4.696 4.696 0 011.529-.039c2.132.312 3.946 1.265 5.468 2.774.868.86 1.525 1.887 2.202 2.891.72 1.066 1.494 2.082 2.48 2.914.348.292.625.514.891.677-.802.09-2.14.11-3.054-.614zm1-6.44a.306.306 0 01.415-.287.302.302 0 01.2.288.306.306 0 01-.31.307.303.303 0 01-.304-.308zm3.11 1.596c-.2.081-.399.151-.59.16a1.245 1.245 0 01-.798-.254c-.274-.23-.47-.358-.552-.758a1.73 1.73 0 01.016-.588c.07-.327-.008-.537-.239-.727-.187-.156-.426-.199-.688-.199a.559.559 0 01-.254-.078c-.11-.054-.2-.19-.114-.358.028-.054.16-.186.192-.21.356-.202.767-.136 1.146.016.352.144.618.408 1.001.782.391.451.462.576.685.914.176.265.336.537.445.848.067.195-.019.354-.25.452z"
-    />
-  </svg>
-{:else if family === "openai" || family === "gpt-oss"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M22.2819 9.8211a5.9847 5.9847 0 0 0-.5157-4.9108 6.0462 6.0462 0 0 0-6.5098-2.9A6.0651 6.0651 0 0 0 4.9807 4.1818a5.9847 5.9847 0 0 0-3.9977 2.9 6.0462 6.0462 0 0 0 .7427 7.0966 5.98 5.98 0 0 0 .511 4.9107 6.051 6.051 0 0 0 6.5146 2.9001A5.9847 5.9847 0 0 0 13.2599 24a6.0557 6.0557 0 0 0 5.7718-4.2058 5.9894 5.9894 0 0 0 3.9977-2.9001 6.0557 6.0557 0 0 0-.7475-7.0729zm-9.022 12.6081a4.4755 4.4755 0 0 1-2.8764-1.0408l.1419-.0804 4.7783-2.7582a.7948.7948 0 0 0 .3927-.6813v-6.7369l2.02 1.1686a.071.071 0 0 1 .038.052v5.5826a4.504 4.504 0 0 1-4.4945 4.4944zm-9.6607-4.1254a4.4708 4.4708 0 0 1-.5346-3.0137l.142.0852 4.783 2.7582a.7712.7712 0 0 0 .7806 0l5.8428-3.3685v2.3324a.0804.0804 0 0 1-.0332.0615L9.74 19.9502a4.4992 4.4992 0 0 1-6.1408-1.6464zM2.3408 7.8956a4.485 4.485 0 0 1 2.3655-1.9728V11.6a.7664.7664 0 0 0 .3879.6765l5.8144 3.3543-2.0201 1.1685a.0757.0757 0 0 1-.071 0l-4.8303-2.7865A4.504 4.504 0 0 1 2.3408 7.872zm16.5963 3.8558L13.1038 8.364 15.1192 7.2a.0757.0757 0 0 1 .071 0l4.8303 2.7913a4.4944 4.4944 0 0 1-.6765 8.1042v-5.6772a.79.79 0 0 0-.407-.667zm2.0107-3.0231l-.142-.0852-4.7735-2.7818a.7759.7759 0 0 0-.7854 0L9.409 9.2297V6.8974a.0662.0662 0 0 1 .0284-.0615l4.8303-2.7866a4.4992 4.4992 0 0 1 6.6802 4.66zM8.3065 12.863l-2.02-1.1638a.0804.0804 0 0 1-.038-.0567V6.0742a4.4992 4.4992 0 0 1 7.3757-3.4537l-.142.0805L8.704 5.459a.7948.7948 0 0 0-.3927.6813zm1.0976-2.3654l2.602-1.4998 2.6069 1.4998v2.9994l-2.5974 1.4997-2.6067-1.4997Z"
-    />
-  </svg>
-{:else if family === "glm"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M11.991 23.503a.24.24 0 00-.244.248.24.24 0 00.244.249.24.24 0 00.245-.249.24.24 0 00-.22-.247l-.025-.001zM9.671 5.365a1.697 1.697 0 011.099 2.132l-.071.172-.016.04-.018.054c-.07.16-.104.32-.104.498-.035.71.47 1.279 1.186 1.314h.366c1.309.053 2.338 1.173 2.286 2.523-.052 1.332-1.152 2.38-2.478 2.327h-.174c-.715.018-1.274.64-1.239 1.368 0 .124.018.23.053.337.209.373.54.658.96.8.75.23 1.517-.125 1.9-.782l.018-.035c.402-.64 1.17-.96 1.92-.711.854.284 1.378 1.226 1.099 2.167a1.661 1.661 0 01-2.077 1.102 1.711 1.711 0 01-.907-.711l-.017-.035c-.2-.323-.463-.58-.851-.711l-.056-.018a1.646 1.646 0 00-1.954.746 1.66 1.66 0 01-1.065.764 1.677 1.677 0 01-1.989-1.279c-.209-.906.332-1.83 1.257-2.043a1.51 1.51 0 01.296-.035h.018c.68-.071 1.151-.622 1.116-1.333a1.307 1.307 0 00-.227-.693 2.515 2.515 0 01-.366-1.403 2.39 2.39 0 01.366-1.208c.14-.195.21-.444.227-.693.018-.71-.506-1.261-1.186-1.332l-.07-.018a1.43 1.43 0 01-.299-.07l-.05-.019a1.7 1.7 0 01-1.047-2.114 1.68 1.68 0 012.094-1.101zm-5.575 10.11c.26-.264.639-.367.994-.27.355.096.633.379.728.74.095.362-.007.748-.267 1.013-.402.41-1.053.41-1.455 0a1.062 1.062 0 010-1.482zm14.845-.294c.359-.09.738.024.992.297.254.274.344.665.237 1.025-.107.36-.396.634-.756.718-.551.128-1.1-.22-1.23-.781a1.05 1.05 0 01.757-1.26zm-.064-4.39c.314.32.49.753.49 1.206 0 .452-.176.886-.49 1.206-.315.32-.74.5-1.185.5-.444 0-.87-.18-1.184-.5a1.727 1.727 0 010-2.412 1.654 1.654 0 012.369 0zm-11.243.163c.364.484.447 1.128.218 1.691a1.665 1.665 0 01-2.188.923c-.855-.36-1.26-1.358-.907-2.228a1.68 1.68 0 011.33-1.038c.593-.08 1.183.169 1.547.652zm11.545-4.221c.368 0 .708.2.892.524.184.324.184.724 0 1.048a1.026 1.026 0 01-.892.524c-.568 0-1.03-.47-1.03-1.048 0-.579.462-1.048 1.03-1.048zm-14.358 0c.368 0 .707.2.891.524.184.324.184.724 0 1.048a1.026 1.026 0 01-.891.524c-.569 0-1.03-.47-1.03-1.048 0-.579.461-1.048 1.03-1.048zm10.031-1.475c.925 0 1.675.764 1.675 1.706s-.75 1.705-1.675 1.705-1.674-.763-1.674-1.705c0-.942.75-1.706 1.674-1.706zm-2.626-.684c.362-.082.653-.356.761-.718a1.062 1.062 0 00-.238-1.028 1.017 1.017 0 00-.996-.294c-.547.14-.881.7-.752 1.257.13.558.675.907 1.225.783zm0 16.876c.359-.087.644-.36.75-.72a1.062 1.062 0 00-.237-1.019 1.018 1.018 0 00-.985-.301 1.037 1.037 0 00-.762.717c-.108.361-.017.754.239 1.028.245.263.606.377.953.305l.043-.01zM17.19 3.5a.631.631 0 00.628-.64c0-.355-.279-.64-.628-.64a.631.631 0 00-.628.64c0 .355.28.64.628.64zm-10.38 0a.631.631 0 00.628-.64c0-.355-.28-.64-.628-.64a.631.631 0 00-.628.64c0 .355.279.64.628.64zm-5.182 7.852a.631.631 0 00-.628.64c0 .354.28.639.628.639a.63.63 0 00.627-.606l.001-.034a.62.62 0 00-.628-.64zm5.182 9.13a.631.631 0 00-.628.64c0 .355.279.64.628.64a.631.631 0 00.628-.64c0-.355-.28-.64-.628-.64zm10.38.018a.631.631 0 00-.628.64c0 .355.28.64.628.64a.631.631 0 00.628-.64c0-.355-.279-.64-.628-.64zm5.182-9.148a.631.631 0 00-.628.64c0 .354.279.639.628.639a.631.631 0 00.628-.64c0-.355-.28-.64-.628-.64zm-.384-4.992a.24.24 0 00.244-.249.24.24 0 00-.244-.249.24.24 0 00-.244.249c0 .142.122.249.244.249zM11.991.497a.24.24 0 00.245-.248A.24.24 0 0011.99 0a.24.24 0 00-.244.249c0 .133.108.236.223.247l.021.001zM2.011 6.36a.24.24 0 00.245-.249.24.24 0 00-.244-.249.24.24 0 00-.244.249.24.24 0 00.244.249zm0 11.263a.24.24 0 00-.243.248.24.24 0 00.244.249.24.24 0 00.244-.249.252.252 0 00-.244-.248zm19.995-.018a.24.24 0 00-.245.248.24.24 0 00.245.25.24.24 0 00.244-.25.252.252 0 00-.244-.248z"
-    />
-  </svg>
-{:else if family === "minimax"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M16.278 2c1.156 0 2.093.927 2.093 2.07v12.501a.74.74 0 00.744.709.74.74 0 00.743-.709V9.099a2.06 2.06 0 012.071-2.049A2.06 2.06 0 0124 9.1v6.561a.649.649 0 01-.652.645.649.649 0 01-.653-.645V9.1a.762.762 0 00-.766-.758.762.762 0 00-.766.758v7.472a2.037 2.037 0 01-2.048 2.026 2.037 2.037 0 01-2.048-2.026v-12.5a.785.785 0 00-.788-.753.785.785 0 00-.789.752l-.001 15.904A2.037 2.037 0 0113.441 22a2.037 2.037 0 01-2.048-2.026V18.04c0-.356.292-.645.652-.645.36 0 .652.289.652.645v1.934c0 .263.142.506.372.638.23.131.514.131.744 0a.734.734 0 00.372-.638V4.07c0-1.143.937-2.07 2.093-2.07zm-5.674 0c1.156 0 2.093.927 2.093 2.07v11.523a.648.648 0 01-.652.645.648.648 0 01-.652-.645V4.07a.785.785 0 00-.789-.78.785.785 0 00-.789.78v14.013a2.06 2.06 0 01-2.07 2.048 2.06 2.06 0 01-2.071-2.048V9.1a.762.762 0 00-.766-.758.762.762 0 00-.766.758v3.8a2.06 2.06 0 01-2.071 2.049A2.06 2.06 0 010 12.9v-1.378c0-.357.292-.646.652-.646.36 0 .653.29.653.646V12.9c0 .418.343.757.766.757s.766-.339.766-.757V9.099a2.06 2.06 0 012.07-2.048 2.06 2.06 0 012.071 2.048v8.984c0 .419.343.758.767.758.423 0 .766-.339.766-.758V4.07c0-1.143.937-2.07 2.093-2.07z"
-    />
-  </svg>
-{:else if family === "kimi"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M19.738 5.776c.163-.209.306-.4.457-.585.07-.087.064-.153-.004-.244-.655-.861-.717-1.817-.34-2.787.283-.73.909-1.072 1.674-1.145.477-.045.945.004 1.379.236.57.305.902.77 1.01 1.412.086.512.07 1.012-.075 1.508-.257.878-.888 1.333-1.753 1.448-.718.096-1.446.108-2.17.157-.056.004-.113 0-.178 0z"
-    />
-    <path
-      d="M17.962 1.844h-4.326l-3.425 7.81H5.369V1.878H1.5V22h3.87v-8.477h6.824a3.025 3.025 0 002.743-1.75V22h3.87v-8.477a3.87 3.87 0 00-3.588-3.86v-.01h-2.125a3.94 3.94 0 002.323-2.12l2.545-5.689z"
-    />
-  </svg>
-{:else if family === "huggingface"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12.025 1.13c-5.77 0-10.449 4.647-10.449 10.378 0 1.112.178 2.181.503 3.185.064-.222.203-.444.416-.577a.96.96 0 0 1 .524-.15c.293 0 .584.124.84.284.278.173.48.408.71.694.226.282.458.611.684.951v-.014c.017-.324.106-.622.264-.874s.403-.487.762-.543c.3-.047.596.06.787.203s.31.313.4.467c.15.257.212.468.233.542.01.026.653 1.552 1.657 2.54.616.605 1.01 1.223 1.082 1.912.055.537-.096 1.059-.38 1.572.637.121 1.294.187 1.967.187.657 0 1.298-.063 1.921-.178-.287-.517-.44-1.041-.384-1.581.07-.69.465-1.307 1.081-1.913 1.004-.987 1.647-2.513 1.657-2.539.021-.074.083-.285.233-.542.09-.154.208-.323.4-.467a1.08 1.08 0 0 1 .787-.203c.359.056.604.29.762.543s.247.55.265.874v.015c.225-.34.457-.67.683-.952.23-.286.432-.52.71-.694.257-.16.547-.284.84-.285a.97.97 0 0 1 .524.151c.228.143.373.388.43.625l.006.04a10.3 10.3 0 0 0 .534-3.273c0-5.731-4.678-10.378-10.449-10.378M8.327 6.583a1.5 1.5 0 0 1 .713.174 1.487 1.487 0 0 1 .617 2.013c-.183.343-.762-.214-1.102-.094-.38.134-.532.914-.917.71a1.487 1.487 0 0 1 .69-2.803m7.486 0a1.487 1.487 0 0 1 .689 2.803c-.385.204-.536-.576-.916-.71-.34-.12-.92.437-1.103.094a1.487 1.487 0 0 1 .617-2.013 1.5 1.5 0 0 1 .713-.174m-10.68 1.55a.96.96 0 1 1 0 1.921.96.96 0 0 1 0-1.92m13.838 0a.96.96 0 1 1 0 1.92.96.96 0 0 1 0-1.92M8.489 11.458c.588.01 1.965 1.157 3.572 1.164 1.607-.007 2.984-1.155 3.572-1.164.196-.003.305.12.305.454 0 .886-.424 2.328-1.563 3.202-.22-.756-1.396-1.366-1.63-1.32q-.011.001-.02.006l-.044.026-.01.008-.03.024q-.018.017-.035.036l-.032.04a1 1 0 0 0-.058.09l-.014.025q-.049.088-.11.19a1 1 0 0 1-.083.116 1.2 1.2 0 0 1-.173.18q-.035.029-.075.058a1.3 1.3 0 0 1-.251-.243 1 1 0 0 1-.076-.107c-.124-.193-.177-.363-.337-.444-.034-.016-.104-.008-.2.022q-.094.03-.216.087-.06.028-.125.063l-.13.074q-.067.04-.136.086a3 3 0 0 0-.135.096 3 3 0 0 0-.26.219 2 2 0 0 0-.12.121 2 2 0 0 0-.106.128l-.002.002a2 2 0 0 0-.09.132l-.001.001a1.2 1.2 0 0 0-.105.212q-.013.036-.024.073c-1.139-.875-1.563-2.317-1.563-3.203 0-.334.109-.457.305-.454m.836 10.354c.824-1.19.766-2.082-.365-3.194-1.13-1.112-1.789-2.738-1.789-2.738s-.246-.945-.806-.858-.97 1.499.202 2.362c1.173.864-.233 1.45-.685.64-.45-.812-1.683-2.896-2.322-3.295s-1.089-.175-.938.647 2.822 2.813 2.562 3.244-1.176-.506-1.176-.506-2.866-2.567-3.49-1.898.473 1.23 2.037 2.16c1.564.932 1.686 1.178 1.464 1.53s-3.675-2.511-4-1.297c-.323 1.214 3.524 1.567 3.287 2.405-.238.839-2.71-1.587-3.216-.642-.506.946 3.49 2.056 3.522 2.064 1.29.33 4.568 1.028 5.713-.624m5.349 0c-.824-1.19-.766-2.082.365-3.194 1.13-1.112 1.789-2.738 1.789-2.738s.246-.945.806-.858.97 1.499-.202 2.362c-1.173.864.233 1.45.685.64.451-.812 1.683-2.896 2.322-3.295s1.089-.175.938.647-2.822 2.813-2.562 3.244 1.176-.506 1.176-.506 2.866-2.567 3.49-1.898-.473 1.23-2.037 2.16c-1.564.932-1.686 1.178-1.464 1.53s3.675-2.511 4-1.297c.323 1.214-3.524 1.567-3.287 2.405.238.839 2.71-1.587 3.216-.642.506.946-3.49 2.056-3.522 2.064-1.29.33-4.568 1.028-5.713-.624"
-    />
-  </svg>
-{:else}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm-2 15l-5-5 1.41-1.41L10 14.17l7.59-7.59L19 8l-9 9z"
-    />
-  </svg>
-{/if}

dashboard/src/lib/components/FamilySidebar.svelte

@@ -1,142 +0,0 @@
-<script lang="ts">
-  import FamilyLogos from "./FamilyLogos.svelte";
-
-  type FamilySidebarProps = {
-    families: string[];
-    selectedFamily: string | null;
-    hasFavorites: boolean;
-    onSelect: (family: string | null) => void;
-  };
-
-  let { families, selectedFamily, hasFavorites, onSelect }: FamilySidebarProps =
-    $props();
-
-  // Family display names
-  const familyNames: Record<string, string> = {
-    favorites: "Favorites",
-    huggingface: "Hub",
-    llama: "Meta",
-    qwen: "Qwen",
-    deepseek: "DeepSeek",
-    "gpt-oss": "OpenAI",
-    glm: "GLM",
-    minimax: "MiniMax",
-    kimi: "Kimi",
-  };
-
-  function getFamilyName(family: string): string {
-    return (
-      familyNames[family] || family.charAt(0).toUpperCase() + family.slice(1)
-    );
-  }
-</script>
-
-<div
-  class="flex flex-col gap-1 py-2 px-1 border-r border-exo-yellow/10 bg-exo-medium-gray/30 min-w-[64px]"
->
-  <!-- All models (no filter) -->
-  <button
-    type="button"
-    onclick={() => onSelect(null)}
-    class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
-    null
-      ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
-      : 'hover:bg-white/5 border-l-2 border-transparent'}"
-    title="All models"
-  >
-    <svg
-      class="w-5 h-5 {selectedFamily === null
-        ? 'text-exo-yellow'
-        : 'text-white/50 group-hover:text-white/70'}"
-      viewBox="0 0 24 24"
-      fill="currentColor"
-    >
-      <path
-        d="M4 8h4V4H4v4zm6 12h4v-4h-4v4zm-6 0h4v-4H4v4zm0-6h4v-4H4v4zm6 0h4v-4h-4v4zm6-10v4h4V4h-4zm-6 4h4V4h-4v4zm6 6h4v-4h-4v4zm0 6h4v-4h-4v4z"
-      />
-    </svg>
-    <span
-      class="text-[9px] font-mono mt-0.5 {selectedFamily === null
-        ? 'text-exo-yellow'
-        : 'text-white/40 group-hover:text-white/60'}">All</span
-    >
-  </button>
-
-  <!-- Favorites (only show if has favorites) -->
-  {#if hasFavorites}
-    <button
-      type="button"
-      onclick={() => onSelect("favorites")}
-      class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
-      'favorites'
-        ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
-        : 'hover:bg-white/5 border-l-2 border-transparent'}"
-      title="Show favorited models"
-    >
-      <FamilyLogos
-        family="favorites"
-        class={selectedFamily === "favorites"
-          ? "text-amber-400"
-          : "text-white/50 group-hover:text-amber-400/70"}
-      />
-      <span
-        class="text-[9px] font-mono mt-0.5 {selectedFamily === 'favorites'
-          ? 'text-amber-400'
-          : 'text-white/40 group-hover:text-white/60'}">Faves</span
-      >
-    </button>
-  {/if}
-
-  <!-- HuggingFace Hub -->
-  <button
-    type="button"
-    onclick={() => onSelect("huggingface")}
-    class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
-    'huggingface'
-      ? 'bg-orange-500/20 border-l-2 border-orange-400'
-      : 'hover:bg-white/5 border-l-2 border-transparent'}"
-    title="Browse and add models from Hugging Face"
-  >
-    <FamilyLogos
-      family="huggingface"
-      class={selectedFamily === "huggingface"
-        ? "text-orange-400"
-        : "text-white/50 group-hover:text-orange-400/70"}
-    />
-    <span
-      class="text-[9px] font-mono mt-0.5 {selectedFamily === 'huggingface'
-        ? 'text-orange-400'
-        : 'text-white/40 group-hover:text-white/60'}">Hub</span
-    >
-  </button>
-
-  <div class="h-px bg-exo-yellow/10 my-1"></div>
-
-  <!-- Model families -->
-  {#each families as family}
-    <button
-      type="button"
-      onclick={() => onSelect(family)}
-      class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
-      family
-        ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
-        : 'hover:bg-white/5 border-l-2 border-transparent'}"
-      title={getFamilyName(family)}
-    >
-      <FamilyLogos
-        {family}
-        class={selectedFamily === family
-          ? "text-exo-yellow"
-          : "text-white/50 group-hover:text-white/70"}
-      />
-      <span
-        class="text-[9px] font-mono mt-0.5 truncate max-w-full {selectedFamily ===
-        family
-          ? 'text-exo-yellow'
-          : 'text-white/40 group-hover:text-white/60'}"
-      >
-        {getFamilyName(family)}
-      </span>
-    </button>
-  {/each}
-</div>

dashboard/src/lib/components/HuggingFaceResultItem.svelte

@@ -1,127 +0,0 @@
-<script lang="ts">
-  interface HuggingFaceModel {
-    id: string;
-    author: string;
-    downloads: number;
-    likes: number;
-    last_modified: string;
-    tags: string[];
-  }
-
-  type HuggingFaceResultItemProps = {
-    model: HuggingFaceModel;
-    isAdded: boolean;
-    isAdding: boolean;
-    onAdd: () => void;
-    onSelect: () => void;
-  };
-
-  let {
-    model,
-    isAdded,
-    isAdding,
-    onAdd,
-    onSelect,
-  }: HuggingFaceResultItemProps = $props();
-
-  function formatNumber(num: number): string {
-    if (num >= 1000000) {
-      return `${(num / 1000000).toFixed(1)}M`;
-    } else if (num >= 1000) {
-      return `${(num / 1000).toFixed(1)}k`;
-    }
-    return num.toString();
-  }
-
-  // Extract model name from full ID (e.g., "mlx-community/Llama-3.2-1B" -> "Llama-3.2-1B")
-  const modelName = $derived(model.id.split("/").pop() || model.id);
-</script>
-
-<div
-  class="flex items-center justify-between gap-3 px-3 py-2.5 hover:bg-white/5 transition-colors border-b border-white/5 last:border-b-0"
->
-  <div class="flex-1 min-w-0">
-    <div class="flex items-center gap-2">
-      <span class="text-sm font-mono text-white truncate" title={model.id}
-        >{modelName}</span
-      >
-      {#if isAdded}
-        <span
-          class="px-1.5 py-0.5 text-[10px] font-mono bg-green-500/20 text-green-400 rounded"
-          >Added</span
-        >
-      {/if}
-    </div>
-    <div class="flex items-center gap-3 mt-0.5 text-xs text-white/40">
-      <span class="truncate">{model.author}</span>
-      <span
-        class="flex items-center gap-1 shrink-0"
-        title="Downloads in the last 30 days"
-      >
-        <svg
-          class="w-3 h-3"
-          fill="none"
-          stroke="currentColor"
-          viewBox="0 0 24 24"
-        >
-          <path
-            stroke-linecap="round"
-            stroke-linejoin="round"
-            stroke-width="2"
-            d="M4 16v1a3 3 0 003 3h10a3 3 0 003-3v-1m-4-4l-4 4m0 0l-4-4m4 4V4"
-          />
-        </svg>
-        {formatNumber(model.downloads)}
-      </span>
-      <span
-        class="flex items-center gap-1 shrink-0"
-        title="Community likes on Hugging Face"
-      >
-        <svg
-          class="w-3 h-3"
-          fill="none"
-          stroke="currentColor"
-          viewBox="0 0 24 24"
-        >
-          <path
-            stroke-linecap="round"
-            stroke-linejoin="round"
-            stroke-width="2"
-            d="M4.318 6.318a4.5 4.5 0 000 6.364L12 20.364l7.682-7.682a4.5 4.5 0 00-6.364-6.364L12 7.636l-1.318-1.318a4.5 4.5 0 00-6.364 0z"
-          />
-        </svg>
-        {formatNumber(model.likes)}
-      </span>
-    </div>
-  </div>
-
-  <div class="flex items-center gap-2 shrink-0">
-    {#if isAdded}
-      <button
-        type="button"
-        onclick={onSelect}
-        class="px-3 py-1.5 text-xs font-mono tracking-wider uppercase bg-exo-yellow/10 text-exo-yellow border border-exo-yellow/30 hover:bg-exo-yellow/20 transition-colors rounded cursor-pointer"
-      >
-        Select
-      </button>
-    {:else}
-      <button
-        type="button"
-        onclick={onAdd}
-        disabled={isAdding}
-        class="px-3 py-1.5 text-xs font-mono tracking-wider uppercase bg-orange-500/10 text-orange-400 border border-orange-400/30 hover:bg-orange-500/20 transition-colors rounded cursor-pointer disabled:opacity-50 disabled:cursor-not-allowed"
-      >
-        {#if isAdding}
-          <span class="flex items-center gap-1.5">
-            <span
-              class="w-3 h-3 border-2 border-orange-400 border-t-transparent rounded-full animate-spin"
-            ></span>
-            Adding...
-          </span>
-        {:else}
-          + Add
-        {/if}
-      </button>
-    {/if}
-  </div>
-</div>

dashboard/src/lib/components/ModelFilterPopover.svelte

@@ -1,182 +0,0 @@
-<script lang="ts">
-  import { fly } from "svelte/transition";
-  import { cubicOut } from "svelte/easing";
-
-  interface FilterState {
-    capabilities: string[];
-    sizeRange: { min: number; max: number } | null;
-  }
-
-  type ModelFilterPopoverProps = {
-    filters: FilterState;
-    onChange: (filters: FilterState) => void;
-    onClear: () => void;
-    onClose: () => void;
-  };
-
-  let { filters, onChange, onClear, onClose }: ModelFilterPopoverProps =
-    $props();
-
-  // Available capabilities
-  const availableCapabilities = [
-    { id: "text", label: "Text" },
-    { id: "thinking", label: "Thinking" },
-    { id: "code", label: "Code" },
-    { id: "vision", label: "Vision" },
-  ];
-
-  // Size ranges
-  const sizeRanges = [
-    { label: "< 10GB", min: 0, max: 10 },
-    { label: "10-50GB", min: 10, max: 50 },
-    { label: "50-200GB", min: 50, max: 200 },
-    { label: "> 200GB", min: 200, max: 10000 },
-  ];
-
-  function toggleCapability(cap: string) {
-    const next = filters.capabilities.includes(cap)
-      ? filters.capabilities.filter((c) => c !== cap)
-      : [...filters.capabilities, cap];
-    onChange({ ...filters, capabilities: next });
-  }
-
-  function selectSizeRange(range: { min: number; max: number } | null) {
-    // Toggle off if same range is clicked
-    if (
-      filters.sizeRange &&
-      range &&
-      filters.sizeRange.min === range.min &&
-      filters.sizeRange.max === range.max
-    ) {
-      onChange({ ...filters, sizeRange: null });
-    } else {
-      onChange({ ...filters, sizeRange: range });
-    }
-  }
-
-  function handleClickOutside(e: MouseEvent) {
-    const target = e.target as HTMLElement;
-    if (
-      !target.closest(".filter-popover") &&
-      !target.closest(".filter-toggle")
-    ) {
-      onClose();
-    }
-  }
-</script>
-
-<svelte:window onclick={handleClickOutside} />
-
-<!-- svelte-ignore a11y_no_static_element_interactions -->
-<div
-  class="filter-popover absolute right-0 top-full mt-2 w-64 bg-exo-dark-gray border border-exo-yellow/10 rounded-lg shadow-xl z-10"
-  transition:fly={{ y: -10, duration: 200, easing: cubicOut }}
-  onclick={(e) => e.stopPropagation()}
-  role="dialog"
-  aria-label="Filter options"
->
-  <div class="p-3 space-y-4">
-    <!-- Capabilities -->
-    <div>
-      <h4 class="text-xs font-mono text-white/50 mb-2">Capabilities</h4>
-      <div class="flex flex-wrap gap-1.5">
-        {#each availableCapabilities as cap}
-          {@const isSelected = filters.capabilities.includes(cap.id)}
-          <button
-            type="button"
-            class="px-2 py-1 text-xs font-mono rounded transition-colors {isSelected
-              ? 'bg-exo-yellow/20 text-exo-yellow border border-exo-yellow/30'
-              : 'bg-white/5 text-white/60 hover:bg-white/10 border border-transparent'}"
-            onclick={() => toggleCapability(cap.id)}
-          >
-            {#if cap.id === "text"}
-              <svg
-                class="w-3.5 h-3.5 inline-block"
-                viewBox="0 0 24 24"
-                fill="none"
-                stroke="currentColor"
-                stroke-width="1.5"
-                ><path
-                  d="M21 15a2 2 0 0 1-2 2H7l-4 4V5a2 2 0 0 1 2-2h14a2 2 0 0 1 2 2z"
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                /></svg
-              >
-            {:else if cap.id === "thinking"}
-              <svg
-                class="w-3.5 h-3.5 inline-block"
-                viewBox="0 0 24 24"
-                fill="none"
-                stroke="currentColor"
-                stroke-width="1.5"
-                ><path
-                  d="M12 2a7 7 0 0 0-7 7c0 2.38 1.19 4.47 3 5.74V17a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1v-2.26c1.81-1.27 3-3.36 3-5.74a7 7 0 0 0-7-7zM9 20h6M10 22h4"
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                /></svg
-              >
-            {:else if cap.id === "code"}
-              <svg
-                class="w-3.5 h-3.5 inline-block"
-                viewBox="0 0 24 24"
-                fill="none"
-                stroke="currentColor"
-                stroke-width="1.5"
-                ><path
-                  d="M16 18l6-6-6-6M8 6l-6 6 6 6"
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                /></svg
-              >
-            {:else if cap.id === "vision"}
-              <svg
-                class="w-3.5 h-3.5 inline-block"
-                viewBox="0 0 24 24"
-                fill="none"
-                stroke="currentColor"
-                stroke-width="1.5"
-                ><path
-                  d="M1 12s4-8 11-8 11 8 11 8-4 8-11 8-11-8-11-8z"
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                /><circle cx="12" cy="12" r="3" /></svg
-              >
-            {/if}
-            <span class="ml-1">{cap.label}</span>
-          </button>
-        {/each}
-      </div>
-    </div>
-
-    <!-- Size range -->
-    <div>
-      <h4 class="text-xs font-mono text-white/50 mb-2">Model Size</h4>
-      <div class="flex flex-wrap gap-1.5">
-        {#each sizeRanges as range}
-          {@const isSelected =
-            filters.sizeRange &&
-            filters.sizeRange.min === range.min &&
-            filters.sizeRange.max === range.max}
-          <button
-            type="button"
-            class="px-2 py-1 text-xs font-mono rounded transition-colors {isSelected
-              ? 'bg-exo-yellow/20 text-exo-yellow border border-exo-yellow/30'
-              : 'bg-white/5 text-white/60 hover:bg-white/10 border border-transparent'}"
-            onclick={() => selectSizeRange(range)}
-          >
-            {range.label}
-          </button>
-        {/each}
-      </div>
-    </div>
-
-    <!-- Clear button -->
-    <button
-      type="button"
-      class="w-full py-1.5 text-xs font-mono text-white/50 hover:text-white/70 hover:bg-white/5 rounded transition-colors"
-      onclick={onClear}
-    >
-      Clear all filters
-    </button>
-  </div>
-</div>

dashboard/src/lib/components/ModelPickerGroup.svelte

@@ -1,324 +0,0 @@
-<script lang="ts">
-  interface ModelInfo {
-    id: string;
-    name?: string;
-    storage_size_megabytes?: number;
-    base_model?: string;
-    quantization?: string;
-    supports_tensor?: boolean;
-    capabilities?: string[];
-    family?: string;
-    is_custom?: boolean;
-  }
-
-  interface ModelGroup {
-    id: string;
-    name: string;
-    capabilities: string[];
-    family: string;
-    variants: ModelInfo[];
-    smallestVariant: ModelInfo;
-    hasMultipleVariants: boolean;
-  }
-
-  type ModelPickerGroupProps = {
-    group: ModelGroup;
-    isExpanded: boolean;
-    isFavorite: boolean;
-    selectedModelId: string | null;
-    canModelFit: (id: string) => boolean;
-    onToggleExpand: () => void;
-    onSelectModel: (modelId: string) => void;
-    onToggleFavorite: (baseModelId: string) => void;
-    onShowInfo: (group: ModelGroup) => void;
-  };
-
-  let {
-    group,
-    isExpanded,
-    isFavorite,
-    selectedModelId,
-    canModelFit,
-    onToggleExpand,
-    onSelectModel,
-    onToggleFavorite,
-    onShowInfo,
-  }: ModelPickerGroupProps = $props();
-
-  // Format storage size
-  function formatSize(mb: number | undefined): string {
-    if (!mb) return "";
-    if (mb >= 1024) {
-      return `${(mb / 1024).toFixed(0)}GB`;
-    }
-    return `${mb}MB`;
-  }
-
-  // Check if any variant can fit
-  const anyVariantFits = $derived(
-    group.variants.some((v) => canModelFit(v.id)),
-  );
-
-  // Check if this group's model is currently selected (for single-variant groups)
-  const isMainSelected = $derived(
-    !group.hasMultipleVariants &&
-      group.variants.some((v) => v.id === selectedModelId),
-  );
-</script>
-
-<div
-  class="border-b border-white/5 last:border-b-0 {!anyVariantFits
-    ? 'opacity-50'
-    : ''}"
->
-  <!-- Main row -->
-  <div
-    class="flex items-center gap-2 px-3 py-2.5 transition-colors {anyVariantFits
-      ? 'hover:bg-white/5 cursor-pointer'
-      : 'cursor-not-allowed'} {isMainSelected
-      ? 'bg-exo-yellow/10 border-l-2 border-exo-yellow'
-      : 'border-l-2 border-transparent'}"
-    onclick={() => {
-      if (group.hasMultipleVariants) {
-        onToggleExpand();
-      } else {
-        const modelId = group.variants[0]?.id;
-        if (modelId && canModelFit(modelId)) {
-          onSelectModel(modelId);
-        }
-      }
-    }}
-    role="button"
-    tabindex="0"
-    onkeydown={(e) => {
-      if (e.key === "Enter" || e.key === " ") {
-        e.preventDefault();
-        if (group.hasMultipleVariants) {
-          onToggleExpand();
-        } else {
-          const modelId = group.variants[0]?.id;
-          if (modelId && canModelFit(modelId)) {
-            onSelectModel(modelId);
-          }
-        }
-      }
-    }}
-  >
-    <!-- Expand/collapse chevron (for groups with variants) -->
-    {#if group.hasMultipleVariants}
-      <svg
-        class="w-4 h-4 text-white/40 transition-transform duration-200 flex-shrink-0 {isExpanded
-          ? 'rotate-90'
-          : ''}"
-        viewBox="0 0 24 24"
-        fill="currentColor"
-      >
-        <path d="M8.59 16.59L13.17 12 8.59 7.41 10 6l6 6-6 6-1.41-1.41z" />
-      </svg>
-    {:else}
-      <div class="w-4 flex-shrink-0"></div>
-    {/if}
-
-    <!-- Model name -->
-    <div class="flex-1 min-w-0">
-      <div class="flex items-center gap-2">
-        <span class="font-mono text-sm text-white truncate">
-          {group.name}
-        </span>
-        <!-- Capability icons -->
-        {#each group.capabilities.filter((c) => c !== "text") as cap}
-          {#if cap === "thinking"}
-            <svg
-              class="w-3.5 h-3.5 text-white/40 flex-shrink-0"
-              viewBox="0 0 24 24"
-              fill="none"
-              stroke="currentColor"
-              stroke-width="1.5"
-              title="Supports Thinking"
-            >
-              <path
-                d="M12 2a7 7 0 0 0-7 7c0 2.38 1.19 4.47 3 5.74V17a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1v-2.26c1.81-1.27 3-3.36 3-5.74a7 7 0 0 0-7-7zM9 20h6M10 22h4"
-                stroke-linecap="round"
-                stroke-linejoin="round"
-              />
-            </svg>
-          {:else if cap === "code"}
-            <svg
-              class="w-3.5 h-3.5 text-white/40 flex-shrink-0"
-              viewBox="0 0 24 24"
-              fill="none"
-              stroke="currentColor"
-              stroke-width="1.5"
-              title="Supports code generation"
-            >
-              <path
-                d="M16 18l6-6-6-6M8 6l-6 6 6 6"
-                stroke-linecap="round"
-                stroke-linejoin="round"
-              />
-            </svg>
-          {:else if cap === "vision"}
-            <svg
-              class="w-3.5 h-3.5 text-white/40 flex-shrink-0"
-              viewBox="0 0 24 24"
-              fill="none"
-              stroke="currentColor"
-              stroke-width="1.5"
-              title="Supports image input"
-            >
-              <path
-                d="M1 12s4-8 11-8 11 8 11 8-4 8-11 8-11-8-11-8z"
-                stroke-linecap="round"
-                stroke-linejoin="round"
-              />
-              <circle cx="12" cy="12" r="3" />
-            </svg>
-          {:else if cap === "image_gen"}
-            <svg
-              class="w-3.5 h-3.5 text-white/40 flex-shrink-0"
-              viewBox="0 0 24 24"
-              fill="none"
-              stroke="currentColor"
-              stroke-width="1.5"
-              title="Supports image generation"
-            >
-              <rect x="3" y="3" width="18" height="18" rx="2" ry="2" />
-              <circle cx="8.5" cy="8.5" r="1.5" />
-              <path d="M21 15l-5-5L5 21" />
-            </svg>
-          {/if}
-        {/each}
-      </div>
-    </div>
-
-    <!-- Size indicator (smallest variant) -->
-    {#if !group.hasMultipleVariants && group.smallestVariant?.storage_size_megabytes}
-      <span class="text-xs font-mono text-white/30 flex-shrink-0">
-        {formatSize(group.smallestVariant.storage_size_megabytes)}
-      </span>
-    {/if}
-
-    <!-- Variant count -->
-    {#if group.hasMultipleVariants}
-      <span class="text-xs font-mono text-white/30 flex-shrink-0">
-        {group.variants.length} variants
-      </span>
-    {/if}
-
-    <!-- Check mark if selected (single-variant) -->
-    {#if isMainSelected}
-      <svg
-        class="w-4 h-4 text-exo-yellow flex-shrink-0"
-        viewBox="0 0 24 24"
-        fill="currentColor"
-      >
-        <path d="M9 16.17L4.83 12l-1.42 1.41L9 19 21 7l-1.41-1.41L9 16.17z" />
-      </svg>
-    {/if}
-
-    <!-- Favorite star -->
-    <button
-      type="button"
-      class="p-1 rounded hover:bg-white/10 transition-colors flex-shrink-0"
-      onclick={(e) => {
-        e.stopPropagation();
-        onToggleFavorite(group.id);
-      }}
-      title={isFavorite ? "Remove from favorites" : "Add to favorites"}
-    >
-      {#if isFavorite}
-        <svg
-          class="w-4 h-4 text-amber-400"
-          viewBox="0 0 24 24"
-          fill="currentColor"
-        >
-          <path
-            d="M12 2l3.09 6.26L22 9.27l-5 4.87 1.18 6.88L12 17.77l-6.18 3.25L7 14.14 2 9.27l6.91-1.01L12 2z"
-          />
-        </svg>
-      {:else}
-        <svg
-          class="w-4 h-4 text-white/30 hover:text-white/50"
-          viewBox="0 0 24 24"
-          fill="none"
-          stroke="currentColor"
-          stroke-width="2"
-        >
-          <path
-            d="M12 2l3.09 6.26L22 9.27l-5 4.87 1.18 6.88L12 17.77l-6.18 3.25L7 14.14 2 9.27l6.91-1.01L12 2z"
-          />
-        </svg>
-      {/if}
-    </button>
-
-    <!-- Info button -->
-    <button
-      type="button"
-      class="p-1 rounded hover:bg-white/10 transition-colors flex-shrink-0"
-      onclick={(e) => {
-        e.stopPropagation();
-        onShowInfo(group);
-      }}
-      title="View model details"
-    >
-      <svg
-        class="w-4 h-4 text-white/30 hover:text-white/50"
-        viewBox="0 0 24 24"
-        fill="currentColor"
-      >
-        <path
-          d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm1 15h-2v-6h2v6zm0-8h-2V7h2v2z"
-        />
-      </svg>
-    </button>
-  </div>
-
-  <!-- Expanded variants -->
-  {#if isExpanded && group.hasMultipleVariants}
-    <div class="bg-black/20 border-t border-white/5">
-      {#each group.variants as variant}
-        {@const modelCanFit = canModelFit(variant.id)}
-        {@const isSelected = selectedModelId === variant.id}
-        <button
-          type="button"
-          class="w-full flex items-center gap-3 px-3 py-2 pl-10 hover:bg-white/5 transition-colors text-left {!modelCanFit
-            ? 'opacity-50 cursor-not-allowed'
-            : 'cursor-pointer'} {isSelected
-            ? 'bg-exo-yellow/10 border-l-2 border-exo-yellow'
-            : 'border-l-2 border-transparent'}"
-          disabled={!modelCanFit}
-          onclick={() => {
-            if (modelCanFit) {
-              onSelectModel(variant.id);
-            }
-          }}
-        >
-          <!-- Quantization badge -->
-          <span
-            class="text-xs font-mono px-1.5 py-0.5 rounded bg-white/10 text-white/70 flex-shrink-0"
-          >
-            {variant.quantization || "default"}
-          </span>
-
-          <!-- Size -->
-          <span class="text-xs font-mono text-white/40 flex-1">
-            {formatSize(variant.storage_size_megabytes)}
-          </span>
-
-          <!-- Check mark if selected -->
-          {#if isSelected}
-            <svg
-              class="w-4 h-4 text-exo-yellow"
-              viewBox="0 0 24 24"
-              fill="currentColor"
-            >
-              <path
-                d="M9 16.17L4.83 12l-1.42 1.41L9 19 21 7l-1.41-1.41L9 16.17z"
-              />
-            </svg>
-          {/if}
-        </button>
-      {/each}
-    </div>
-  {/if}
-</div>

dashboard/src/lib/components/ModelPickerModal.svelte

@@ -1,748 +0,0 @@
-<script lang="ts">
-  import { fade, fly } from "svelte/transition";
-  import { cubicOut } from "svelte/easing";
-  import FamilySidebar from "./FamilySidebar.svelte";
-  import ModelPickerGroup from "./ModelPickerGroup.svelte";
-  import ModelFilterPopover from "./ModelFilterPopover.svelte";
-  import HuggingFaceResultItem from "./HuggingFaceResultItem.svelte";
-
-  interface ModelInfo {
-    id: string;
-    name?: string;
-    storage_size_megabytes?: number;
-    base_model?: string;
-    quantization?: string;
-    supports_tensor?: boolean;
-    capabilities?: string[];
-    family?: string;
-    is_custom?: boolean;
-    tasks?: string[];
-    hugging_face_id?: string;
-  }
-
-  interface ModelGroup {
-    id: string;
-    name: string;
-    capabilities: string[];
-    family: string;
-    variants: ModelInfo[];
-    smallestVariant: ModelInfo;
-    hasMultipleVariants: boolean;
-  }
-
-  interface FilterState {
-    capabilities: string[];
-    sizeRange: { min: number; max: number } | null;
-  }
-
-  interface HuggingFaceModel {
-    id: string;
-    author: string;
-    downloads: number;
-    likes: number;
-    last_modified: string;
-    tags: string[];
-  }
-
-  type ModelPickerModalProps = {
-    isOpen: boolean;
-    models: ModelInfo[];
-    selectedModelId: string | null;
-    favorites: Set<string>;
-    existingModelIds: Set<string>;
-    canModelFit: (modelId: string) => boolean;
-    onSelect: (modelId: string) => void;
-    onClose: () => void;
-    onToggleFavorite: (baseModelId: string) => void;
-    onAddModel: (modelId: string) => Promise<void>;
-    onDeleteModel: (modelId: string) => Promise<void>;
-    totalMemoryGB: number;
-    usedMemoryGB: number;
-  };
-
-  let {
-    isOpen,
-    models,
-    selectedModelId,
-    favorites,
-    existingModelIds,
-    canModelFit,
-    onSelect,
-    onClose,
-    onToggleFavorite,
-    onAddModel,
-    onDeleteModel,
-    totalMemoryGB,
-    usedMemoryGB,
-  }: ModelPickerModalProps = $props();
-
-  // Local state
-  let searchQuery = $state("");
-  let selectedFamily = $state<string | null>(null);
-  let expandedGroups = $state<Set<string>>(new Set());
-  let showFilters = $state(false);
-  let filters = $state<FilterState>({ capabilities: [], sizeRange: null });
-  let infoGroup = $state<ModelGroup | null>(null);
-
-  // HuggingFace Hub state
-  let hfSearchQuery = $state("");
-  let hfSearchResults = $state<HuggingFaceModel[]>([]);
-  let hfTrendingModels = $state<HuggingFaceModel[]>([]);
-  let hfIsSearching = $state(false);
-  let hfIsLoadingTrending = $state(false);
-  let addingModelId = $state<string | null>(null);
-  let hfSearchDebounceTimer: ReturnType<typeof setTimeout> | null = null;
-  let manualModelId = $state("");
-  let addModelError = $state<string | null>(null);
-
-  // Reset state when modal opens
-  $effect(() => {
-    if (isOpen) {
-      searchQuery = "";
-      selectedFamily = null;
-      expandedGroups = new Set();
-      showFilters = false;
-      hfSearchQuery = "";
-      hfSearchResults = [];
-      manualModelId = "";
-      addModelError = null;
-    }
-  });
-
-  // Fetch trending models when HuggingFace is selected
-  $effect(() => {
-    if (
-      selectedFamily === "huggingface" &&
-      hfTrendingModels.length === 0 &&
-      !hfIsLoadingTrending
-    ) {
-      fetchTrendingModels();
-    }
-  });
-
-  async function fetchTrendingModels() {
-    hfIsLoadingTrending = true;
-    try {
-      const response = await fetch("/models/search?query=&limit=20");
-      if (response.ok) {
-        hfTrendingModels = await response.json();
-      }
-    } catch (error) {
-      console.error("Failed to fetch trending models:", error);
-    } finally {
-      hfIsLoadingTrending = false;
-    }
-  }
-
-  async function searchHuggingFace(query: string) {
-    if (query.length < 2) {
-      hfSearchResults = [];
-      return;
-    }
-
-    hfIsSearching = true;
-    try {
-      const response = await fetch(
-        `/models/search?query=${encodeURIComponent(query)}&limit=20`,
-      );
-      if (response.ok) {
-        hfSearchResults = await response.json();
-      } else {
-        hfSearchResults = [];
-      }
-    } catch (error) {
-      console.error("Failed to search models:", error);
-      hfSearchResults = [];
-    } finally {
-      hfIsSearching = false;
-    }
-  }
-
-  function handleHfSearchInput(query: string) {
-    hfSearchQuery = query;
-    addModelError = null;
-
-    if (hfSearchDebounceTimer) {
-      clearTimeout(hfSearchDebounceTimer);
-    }
-
-    if (query.length >= 2) {
-      hfSearchDebounceTimer = setTimeout(() => {
-        searchHuggingFace(query);
-      }, 300);
-    } else {
-      hfSearchResults = [];
-    }
-  }
-
-  async function handleAddModel(modelId: string) {
-    addingModelId = modelId;
-    addModelError = null;
-    try {
-      await onAddModel(modelId);
-    } catch (error) {
-      addModelError =
-        error instanceof Error ? error.message : "Failed to add model";
-    } finally {
-      addingModelId = null;
-    }
-  }
-
-  async function handleAddManualModel() {
-    if (!manualModelId.trim()) return;
-    await handleAddModel(manualModelId.trim());
-    if (!addModelError) {
-      manualModelId = "";
-    }
-  }
-
-  function handleSelectHfModel(modelId: string) {
-    onSelect(modelId);
-    onClose();
-  }
-
-  // Models to display in HuggingFace view
-  const hfDisplayModels = $derived.by((): HuggingFaceModel[] => {
-    if (hfSearchQuery.length >= 2) {
-      return hfSearchResults;
-    }
-    return hfTrendingModels;
-  });
-
-  // Group models by base_model
-  const groupedModels = $derived.by((): ModelGroup[] => {
-    const groups = new Map<string, ModelGroup>();
-
-    for (const model of models) {
-      const groupId = model.base_model || model.id;
-      const groupName = model.base_model || model.name || model.id;
-
-      if (!groups.has(groupId)) {
-        groups.set(groupId, {
-          id: groupId,
-          name: groupName,
-          capabilities: model.capabilities || ["text"],
-          family: model.family || "",
-          variants: [],
-          smallestVariant: model,
-          hasMultipleVariants: false,
-        });
-      }
-
-      const group = groups.get(groupId)!;
-      group.variants.push(model);
-
-      // Track smallest variant
-      if (
-        (model.storage_size_megabytes || 0) <
-        (group.smallestVariant.storage_size_megabytes || Infinity)
-      ) {
-        group.smallestVariant = model;
-      }
-
-      // Update capabilities if not set
-      if (
-        group.capabilities.length <= 1 &&
-        model.capabilities &&
-        model.capabilities.length > 1
-      ) {
-        group.capabilities = model.capabilities;
-      }
-      if (!group.family && model.family) {
-        group.family = model.family;
-      }
-    }
-
-    // Sort variants within each group by size
-    for (const group of groups.values()) {
-      group.variants.sort(
-        (a, b) =>
-          (a.storage_size_megabytes || 0) - (b.storage_size_megabytes || 0),
-      );
-      group.hasMultipleVariants = group.variants.length > 1;
-    }
-
-    // Convert to array and sort by smallest variant size (biggest first)
-    return Array.from(groups.values()).sort((a, b) => {
-      return (
-        (b.smallestVariant.storage_size_megabytes || 0) -
-        (a.smallestVariant.storage_size_megabytes || 0)
-      );
-    });
-  });
-
-  // Get unique families
-  const uniqueFamilies = $derived.by((): string[] => {
-    const families = new Set<string>();
-    for (const group of groupedModels) {
-      if (group.family) {
-        families.add(group.family);
-      }
-    }
-    const familyOrder = [
-      "kimi",
-      "qwen",
-      "glm",
-      "minimax",
-      "deepseek",
-      "gpt-oss",
-      "llama",
-    ];
-    return Array.from(families).sort((a, b) => {
-      const aIdx = familyOrder.indexOf(a);
-      const bIdx = familyOrder.indexOf(b);
-      if (aIdx === -1 && bIdx === -1) return a.localeCompare(b);
-      if (aIdx === -1) return 1;
-      if (bIdx === -1) return -1;
-      return aIdx - bIdx;
-    });
-  });
-
-  // Filter models based on search, family, and filters
-  const filteredGroups = $derived.by((): ModelGroup[] => {
-    let result: ModelGroup[] = [...groupedModels];
-
-    // Filter by family
-    if (selectedFamily === "favorites") {
-      result = result.filter((g) => favorites.has(g.id));
-    } else if (selectedFamily && selectedFamily !== "huggingface") {
-      result = result.filter((g) => g.family === selectedFamily);
-    }
-
-    // Filter by search query
-    if (searchQuery.trim()) {
-      const query = searchQuery.toLowerCase().trim();
-      result = result.filter(
-        (g) =>
-          g.name.toLowerCase().includes(query) ||
-          g.variants.some(
-            (v) =>
-              v.id.toLowerCase().includes(query) ||
-              (v.name || "").toLowerCase().includes(query),
-          ),
-      );
-    }
-
-    // Filter by capabilities
-    if (filters.capabilities.length > 0) {
-      result = result.filter((g) =>
-        filters.capabilities.every((cap) => g.capabilities.includes(cap)),
-      );
-    }
-
-    // Filter by size range
-    if (filters.sizeRange) {
-      const { min, max } = filters.sizeRange;
-      result = result.filter((g) => {
-        const sizeGB = (g.smallestVariant.storage_size_megabytes || 0) / 1024;
-        return sizeGB >= min && sizeGB <= max;
-      });
-    }
-
-    // Sort: models that fit first, then by size (largest first)
-    result.sort((a, b) => {
-      const aFits = a.variants.some((v) => canModelFit(v.id));
-      const bFits = b.variants.some((v) => canModelFit(v.id));
-
-      if (aFits && !bFits) return -1;
-      if (!aFits && bFits) return 1;
-
-      return (
-        (b.smallestVariant.storage_size_megabytes || 0) -
-        (a.smallestVariant.storage_size_megabytes || 0)
-      );
-    });
-
-    return result;
-  });
-
-  // Check if any favorites exist
-  const hasFavorites = $derived(favorites.size > 0);
-
-  function toggleGroupExpanded(groupId: string) {
-    const next = new Set(expandedGroups);
-    if (next.has(groupId)) {
-      next.delete(groupId);
-    } else {
-      next.add(groupId);
-    }
-    expandedGroups = next;
-  }
-
-  function handleSelect(modelId: string) {
-    onSelect(modelId);
-    onClose();
-  }
-
-  function handleKeydown(e: KeyboardEvent) {
-    if (e.key === "Escape") {
-      onClose();
-    }
-  }
-
-  function handleFiltersChange(newFilters: FilterState) {
-    filters = newFilters;
-  }
-
-  function clearFilters() {
-    filters = { capabilities: [], sizeRange: null };
-  }
-
-  const hasActiveFilters = $derived(
-    filters.capabilities.length > 0 || filters.sizeRange !== null,
-  );
-</script>
-
-<svelte:window onkeydown={handleKeydown} />
-
-{#if isOpen}
-  <!-- Backdrop -->
-  <div
-    class="fixed inset-0 z-50 bg-black/80 backdrop-blur-sm"
-    transition:fade={{ duration: 200 }}
-    onclick={onClose}
-    role="presentation"
-  ></div>
-
-  <!-- Modal -->
-  <div
-    class="fixed z-50 top-1/2 left-1/2 -translate-x-1/2 -translate-y-1/2 w-[min(90vw,600px)] h-[min(80vh,700px)] bg-exo-dark-gray border border-exo-yellow/10 rounded-lg shadow-2xl overflow-hidden flex flex-col"
-    transition:fly={{ y: 20, duration: 300, easing: cubicOut }}
-    role="dialog"
-    aria-modal="true"
-    aria-label="Select a model"
-  >
-    <!-- Header with search -->
-    <div
-      class="flex items-center gap-2 p-3 border-b border-exo-yellow/10 bg-exo-medium-gray/30"
-    >
-      {#if selectedFamily === "huggingface"}
-        <!-- HuggingFace search -->
-        <svg
-          class="w-5 h-5 text-orange-400/60 flex-shrink-0"
-          viewBox="0 0 24 24"
-          fill="none"
-          stroke="currentColor"
-          stroke-width="2"
-        >
-          <circle cx="11" cy="11" r="8" />
-          <path d="M21 21l-4.35-4.35" />
-        </svg>
-        <input
-          type="search"
-          class="flex-1 bg-transparent border-none outline-none text-sm font-mono text-white placeholder-white/40"
-          placeholder="Search mlx-community models..."
-          value={hfSearchQuery}
-          oninput={(e) => handleHfSearchInput(e.currentTarget.value)}
-        />
-        {#if hfIsSearching}
-          <div class="flex-shrink-0">
-            <span
-              class="w-4 h-4 border-2 border-orange-400 border-t-transparent rounded-full animate-spin block"
-            ></span>
-          </div>
-        {/if}
-      {:else}
-        <!-- Normal model search -->
-        <svg
-          class="w-5 h-5 text-white/40 flex-shrink-0"
-          viewBox="0 0 24 24"
-          fill="none"
-          stroke="currentColor"
-          stroke-width="2"
-        >
-          <circle cx="11" cy="11" r="8" />
-          <path d="M21 21l-4.35-4.35" />
-        </svg>
-        <input
-          type="search"
-          class="flex-1 bg-transparent border-none outline-none text-sm font-mono text-white placeholder-white/40"
-          placeholder="Search models..."
-          bind:value={searchQuery}
-        />
-        <!-- Cluster memory -->
-        <span
-          class="text-xs font-mono flex-shrink-0"
-          title="Cluster memory usage"
-          ><span class="text-exo-yellow">{Math.round(usedMemoryGB)}GB</span
-          ><span class="text-white/40">/{Math.round(totalMemoryGB)}GB</span
-          ></span
-        >
-        <!-- Filter button -->
-        <div class="relative filter-toggle">
-          <button
-            type="button"
-            class="p-1.5 rounded hover:bg-white/10 transition-colors {hasActiveFilters
-              ? 'text-exo-yellow'
-              : 'text-white/50'}"
-            onclick={() => (showFilters = !showFilters)}
-            title="Filter by capability or size"
-          >
-            <svg class="w-5 h-5" viewBox="0 0 24 24" fill="currentColor">
-              <path d="M10 18h4v-2h-4v2zM3 6v2h18V6H3zm3 7h12v-2H6v2z" />
-            </svg>
-          </button>
-          {#if showFilters}
-            <ModelFilterPopover
-              {filters}
-              onChange={handleFiltersChange}
-              onClear={clearFilters}
-              onClose={() => (showFilters = false)}
-            />
-          {/if}
-        </div>
-      {/if}
-      <!-- Close button -->
-      <button
-        type="button"
-        class="p-1.5 rounded hover:bg-white/10 transition-colors text-white/50 hover:text-white/70"
-        onclick={onClose}
-        title="Close model picker"
-      >
-        <svg class="w-5 h-5" viewBox="0 0 24 24" fill="currentColor">
-          <path
-            d="M19 6.41L17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41z"
-          />
-        </svg>
-      </button>
-    </div>
-
-    <!-- Body -->
-    <div class="flex flex-1 overflow-hidden">
-      <!-- Family sidebar -->
-      <FamilySidebar
-        families={uniqueFamilies}
-        {selectedFamily}
-        {hasFavorites}
-        onSelect={(family) => (selectedFamily = family)}
-      />
-
-      <!-- Model list -->
-      <div class="flex-1 overflow-y-auto flex flex-col">
-        {#if selectedFamily === "huggingface"}
-          <!-- HuggingFace Hub view -->
-          <div class="flex-1 flex flex-col min-h-0">
-            <!-- Section header -->
-            <div
-              class="sticky top-0 z-10 px-3 py-2 bg-exo-dark-gray/95 border-b border-exo-yellow/10"
-            >
-              <span class="text-xs font-mono text-white/40">
-                {#if hfSearchQuery.length >= 2}
-                  Search results for "{hfSearchQuery}"
-                {:else}
-                  Trending on mlx-community
-                {/if}
-              </span>
-            </div>
-
-            <!-- Results list -->
-            <div class="flex-1 overflow-y-auto">
-              {#if hfIsLoadingTrending && hfTrendingModels.length === 0}
-                <div
-                  class="flex items-center justify-center py-12 text-white/40"
-                >
-                  <span
-                    class="w-5 h-5 border-2 border-orange-400 border-t-transparent rounded-full animate-spin mr-2"
-                  ></span>
-                  <span class="font-mono text-sm"
-                    >Loading trending models...</span
-                  >
-                </div>
-              {:else if hfDisplayModels.length === 0}
-                <div
-                  class="flex flex-col items-center justify-center py-12 text-white/40"
-                >
-                  <svg
-                    class="w-10 h-10 mb-2"
-                    viewBox="0 0 24 24"
-                    fill="currentColor"
-                  >
-                    <path
-                      d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm-2 13.5c-.83 0-1.5-.67-1.5-1.5s.67-1.5 1.5-1.5 1.5.67 1.5 1.5-.67 1.5-1.5 1.5zm4 0c-.83 0-1.5-.67-1.5-1.5s.67-1.5 1.5-1.5 1.5.67 1.5 1.5-.67 1.5-1.5 1.5zm2-4.5H8c0-2.21 1.79-4 4-4s4 1.79 4 4z"
-                    />
-                  </svg>
-                  <p class="font-mono text-sm">No models found</p>
-                  {#if hfSearchQuery}
-                    <p class="font-mono text-xs mt-1">
-                      Try a different search term
-                    </p>
-                  {/if}
-                </div>
-              {:else}
-                {#each hfDisplayModels as model}
-                  <HuggingFaceResultItem
-                    {model}
-                    isAdded={existingModelIds.has(model.id)}
-                    isAdding={addingModelId === model.id}
-                    onAdd={() => handleAddModel(model.id)}
-                    onSelect={() => handleSelectHfModel(model.id)}
-                  />
-                {/each}
-              {/if}
-            </div>
-
-            <!-- Manual input footer -->
-            <div
-              class="sticky bottom-0 border-t border-exo-yellow/10 bg-exo-dark-gray p-3"
-            >
-              {#if addModelError}
-                <div
-                  class="bg-red-500/10 border border-red-500/30 rounded px-3 py-2 mb-2"
-                >
-                  <p class="text-red-400 text-xs font-mono break-words">
-                    {addModelError}
-                  </p>
-                </div>
-              {/if}
-              <div class="flex gap-2">
-                <input
-                  type="text"
-                  class="flex-1 bg-exo-black/60 border border-exo-yellow/30 rounded px-3 py-1.5 text-xs font-mono text-white placeholder-white/30 focus:outline-none focus:border-exo-yellow/50"
-                  placeholder="Or paste model ID directly..."
-                  bind:value={manualModelId}
-                  onkeydown={(e) => {
-                    if (e.key === "Enter") handleAddManualModel();
-                  }}
-                />
-                <button
-                  type="button"
-                  onclick={handleAddManualModel}
-                  disabled={!manualModelId.trim() || addingModelId !== null}
-                  class="px-3 py-1.5 text-xs font-mono tracking-wider uppercase bg-orange-500/10 text-orange-400 border border-orange-400/30 hover:bg-orange-500/20 transition-colors rounded disabled:opacity-50 disabled:cursor-not-allowed"
-                >
-                  Add
-                </button>
-              </div>
-            </div>
-          </div>
-        {:else if filteredGroups.length === 0}
-          <div
-            class="flex flex-col items-center justify-center h-full text-white/40 p-8"
-          >
-            <svg class="w-12 h-12 mb-3" viewBox="0 0 24 24" fill="currentColor">
-              <path
-                d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm-2 15l-5-5 1.41-1.41L10 14.17l7.59-7.59L19 8l-9 9z"
-              />
-            </svg>
-            <p class="font-mono text-sm">No models found</p>
-            {#if hasActiveFilters || searchQuery}
-              <button
-                type="button"
-                class="mt-2 text-xs text-exo-yellow hover:underline"
-                onclick={() => {
-                  searchQuery = "";
-                  clearFilters();
-                }}
-              >
-                Clear filters
-              </button>
-            {/if}
-          </div>
-        {:else}
-          {#each filteredGroups as group}
-            <ModelPickerGroup
-              {group}
-              isExpanded={expandedGroups.has(group.id)}
-              isFavorite={favorites.has(group.id)}
-              {selectedModelId}
-              {canModelFit}
-              onToggleExpand={() => toggleGroupExpanded(group.id)}
-              onSelectModel={handleSelect}
-              {onToggleFavorite}
-              onShowInfo={(g) => (infoGroup = g)}
-            />
-          {/each}
-        {/if}
-      </div>
-    </div>
-
-    <!-- Footer with active filters indicator -->
-    {#if hasActiveFilters}
-      <div
-        class="flex items-center gap-2 px-3 py-2 border-t border-exo-yellow/10 bg-exo-medium-gray/20 text-xs font-mono text-white/50"
-      >
-        <span>Filters:</span>
-        {#each filters.capabilities as cap}
-          <span class="px-1.5 py-0.5 bg-exo-yellow/20 text-exo-yellow rounded"
-            >{cap}</span
-          >
-        {/each}
-        {#if filters.sizeRange}
-          <span class="px-1.5 py-0.5 bg-exo-yellow/20 text-exo-yellow rounded">
-            {filters.sizeRange.min}GB - {filters.sizeRange.max}GB
-          </span>
-        {/if}
-        <button
-          type="button"
-          class="ml-auto text-white/40 hover:text-white/60"
-          onclick={clearFilters}
-        >
-          Clear all
-        </button>
-      </div>
-    {/if}
-  </div>
-
-  <!-- Info modal -->
-  {#if infoGroup}
-    <div
-      class="fixed inset-0 z-[60] bg-black/60"
-      transition:fade={{ duration: 150 }}
-      onclick={() => (infoGroup = null)}
-      role="presentation"
-    ></div>
-    <div
-      class="fixed z-[60] top-1/2 left-1/2 -translate-x-1/2 -translate-y-1/2 w-[min(80vw,400px)] bg-exo-dark-gray border border-exo-yellow/10 rounded-lg shadow-2xl p-4"
-      transition:fly={{ y: 10, duration: 200, easing: cubicOut }}
-      role="dialog"
-      aria-modal="true"
-    >
-      <div class="flex items-start justify-between mb-3">
-        <h3 class="font-mono text-lg text-white">{infoGroup.name}</h3>
-        <button
-          type="button"
-          class="p-1 rounded hover:bg-white/10 transition-colors text-white/50"
-          onclick={() => (infoGroup = null)}
-          title="Close model details"
-          aria-label="Close info dialog"
-        >
-          <svg class="w-4 h-4" viewBox="0 0 24 24" fill="currentColor">
-            <path
-              d="M19 6.41L17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41z"
-            />
-          </svg>
-        </button>
-      </div>
-      <div class="space-y-2 text-xs font-mono">
-        <div class="flex items-center gap-2">
-          <span class="text-white/40">Family:</span>
-          <span class="text-white/70">{infoGroup.family || "Unknown"}</span>
-        </div>
-        <div class="flex items-center gap-2">
-          <span class="text-white/40">Capabilities:</span>
-          <span class="text-white/70">{infoGroup.capabilities.join(", ")}</span>
-        </div>
-        <div class="flex items-center gap-2">
-          <span class="text-white/40">Variants:</span>
-          <span class="text-white/70">{infoGroup.variants.length}</span>
-        </div>
-        {#if infoGroup.variants.length > 0}
-          <div class="mt-3 pt-3 border-t border-exo-yellow/10">
-            <span class="text-white/40">Available quantizations:</span>
-            <div class="flex flex-wrap gap-1 mt-1">
-              {#each infoGroup.variants as variant}
-                <span
-                  class="px-1.5 py-0.5 bg-white/10 text-white/60 rounded text-[10px]"
-                >
-                  {variant.quantization || "default"} ({Math.round(
-                    (variant.storage_size_megabytes || 0) / 1024,
-                  )}GB)
-                </span>
-              {/each}
-            </div>
-          </div>
-        {/if}
-      </div>
-    </div>
-  {/if}
-{/if}

dashboard/src/lib/components/index.ts

@@ -6,9 +6,3 @@ export { default as ChatSidebar } from "./ChatSidebar.svelte";
 export { default as ModelCard } from "./ModelCard.svelte";
 export { default as MarkdownContent } from "./MarkdownContent.svelte";
 export { default as ImageParamsPanel } from "./ImageParamsPanel.svelte";
-export { default as FamilyLogos } from "./FamilyLogos.svelte";
-export { default as FamilySidebar } from "./FamilySidebar.svelte";
-export { default as HuggingFaceResultItem } from "./HuggingFaceResultItem.svelte";
-export { default as ModelFilterPopover } from "./ModelFilterPopover.svelte";
-export { default as ModelPickerGroup } from "./ModelPickerGroup.svelte";
-export { default as ModelPickerModal } from "./ModelPickerModal.svelte";

dashboard/src/lib/stores/app.svelte.ts

@@ -173,41 +173,6 @@ export interface PlacementPreviewResponse {
   previews: PlacementPreview[];
 }
 
-interface ImageApiResponse {
-  created: number;
-  data: Array<{ b64_json?: string; url?: string }>;
-}
-
-// Trace API response types
-export interface TraceCategoryStats {
-  totalUs: number;
-  count: number;
-  minUs: number;
-  maxUs: number;
-  avgUs: number;
-}
-
-export interface TraceRankStats {
-  byCategory: Record<string, TraceCategoryStats>;
-}
-
-export interface TraceStatsResponse {
-  taskId: string;
-  totalWallTimeUs: number;
-  byCategory: Record<string, TraceCategoryStats>;
-  byRank: Record<number, TraceRankStats>;
-}
-
-export interface TraceListItem {
-  taskId: string;
-  createdAt: string;
-  fileSize: number;
-}
-
-export interface TraceListResponse {
-  traces: TraceListItem[];
-}
-
 interface RawStateResponse {
   topology?: RawTopology;
   instances?: Record<
@@ -2130,137 +2095,107 @@ class AppStore {
         throw new Error(`API error: ${response.status} - ${errorText}`);
       }
 
-      // Streaming requires both stream=true AND partialImages > 0
-      const isStreaming = params.stream && params.partialImages > 0;
-
-      if (!isStreaming) {
-        // Non-streaming: parse JSON response directly
-        const jsonResponse = (await response.json()) as ImageApiResponse;
-        const format = params.outputFormat || "png";
-        const mimeType = `image/${format}`;
-
-        const attachments: MessageAttachment[] = jsonResponse.data
-          .filter((img) => img.b64_json)
-          .map((img, index) => ({
-            type: "generated-image" as const,
-            name: `generated-image-${index + 1}.${format}`,
-            preview: `data:${mimeType};base64,${img.b64_json}`,
-            mimeType,
-          }));
-
-        this.updateConversationMessage(
-          targetConversationId,
-          assistantMessage.id,
-          (msg) => {
-            msg.content = "";
-            msg.attachments = attachments;
-          },
-        );
-        this.syncActiveMessagesIfNeeded(targetConversationId);
-      } else {
-        // Streaming mode: use SSE parser
-        const reader = response.body?.getReader();
-        if (!reader) {
-          throw new Error("No response body");
-        }
-
-        interface ImageGenerationChunk {
-          data?: { b64_json?: string };
-          format?: string;
-          type?: "partial" | "final";
-          image_index?: number;
-          partial_index?: number;
-          total_partials?: number;
-        }
-
-        const numImages = params.numImages;
-
-        await this.parseSSEStream<ImageGenerationChunk>(
-          reader,
-          targetConversationId,
-          (parsed) => {
-            const imageData = parsed.data?.b64_json;
-
-            if (imageData) {
-              const format = parsed.format || "png";
-              const mimeType = `image/${format}`;
-              const imageIndex = parsed.image_index ?? 0;
-
-              if (parsed.type === "partial") {
-                // Update with partial image and progress
-                const partialNum = (parsed.partial_index ?? 0) + 1;
-                const totalPartials = parsed.total_partials ?? 3;
-                const progressText =
-                  numImages > 1
-                    ? `Generating image ${imageIndex + 1}/${numImages}... ${partialNum}/${totalPartials}`
-                    : `Generating... ${partialNum}/${totalPartials}`;
-
-                const partialAttachment: MessageAttachment = {
-                  type: "generated-image",
-                  name: `generated-image.${format}`,
-                  preview: `data:${mimeType};base64,${imageData}`,
-                  mimeType,
-                };
-
-                this.updateConversationMessage(
-                  targetConversationId,
-                  assistantMessage.id,
-                  (msg) => {
-                    msg.content = progressText;
-                    if (imageIndex === 0) {
-                      // First image - safe to replace attachments with partial preview
-                      msg.attachments = [partialAttachment];
-                    } else {
-                      // Subsequent images - keep existing finals, show partial at current position
-                      const existingAttachments = msg.attachments || [];
-                      // Keep only the completed final images (up to current imageIndex)
-                      const finals = existingAttachments.slice(0, imageIndex);
-                      msg.attachments = [...finals, partialAttachment];
-                    }
-                  },
-                );
-              } else if (parsed.type === "final") {
-                // Final image - replace partial at this position
-                const newAttachment: MessageAttachment = {
-                  type: "generated-image",
-                  name: `generated-image-${imageIndex + 1}.${format}`,
-                  preview: `data:${mimeType};base64,${imageData}`,
-                  mimeType,
-                };
-
-                this.updateConversationMessage(
-                  targetConversationId,
-                  assistantMessage.id,
-                  (msg) => {
-                    if (imageIndex === 0) {
-                      // First final image - replace any partial preview
-                      msg.attachments = [newAttachment];
-                    } else {
-                      // Subsequent images - keep previous finals, replace partial at current position
-                      const existingAttachments = msg.attachments || [];
-                      // Slice keeps indices 0 to imageIndex-1 (the previous final images)
-                      const previousFinals = existingAttachments.slice(
-                        0,
-                        imageIndex,
-                      );
-                      msg.attachments = [...previousFinals, newAttachment];
-                    }
-
-                    // Update progress message for multiple images
-                    if (numImages > 1 && imageIndex < numImages - 1) {
-                      msg.content = `Generating image ${imageIndex + 2}/${numImages}...`;
-                    } else {
-                      msg.content = "";
-                    }
-                  },
-                );
-              }
-
-              this.syncActiveMessagesIfNeeded(targetConversationId);
-            }
-          },
-        );
+      const reader = response.body?.getReader();
+      if (!reader) {
+        throw new Error("No response body");
       }
+
+      interface ImageGenerationChunk {
+        data?: { b64_json?: string };
+        format?: string;
+        type?: "partial" | "final";
+        image_index?: number;
+        partial_index?: number;
+        total_partials?: number;
+      }
+
+      const numImages = params.numImages;
+
+      await this.parseSSEStream<ImageGenerationChunk>(
+        reader,
+        targetConversationId,
+        (parsed) => {
+          const imageData = parsed.data?.b64_json;
+
+          if (imageData) {
+            const format = parsed.format || "png";
+            const mimeType = `image/${format}`;
+            const imageIndex = parsed.image_index ?? 0;
+
+            if (parsed.type === "partial") {
+              // Update with partial image and progress
+              const partialNum = (parsed.partial_index ?? 0) + 1;
+              const totalPartials = parsed.total_partials ?? 3;
+              const progressText =
+                numImages > 1
+                  ? `Generating image ${imageIndex + 1}/${numImages}... ${partialNum}/${totalPartials}`
+                  : `Generating... ${partialNum}/${totalPartials}`;
+
+              const partialAttachment: MessageAttachment = {
+                type: "generated-image",
+                name: `generated-image.${format}`,
+                preview: `data:${mimeType};base64,${imageData}`,
+                mimeType,
+              };
+
+              this.updateConversationMessage(
+                targetConversationId,
+                assistantMessage.id,
+                (msg) => {
+                  msg.content = progressText;
+                  if (imageIndex === 0) {
+                    // First image - safe to replace attachments with partial preview
+                    msg.attachments = [partialAttachment];
+                  } else {
+                    // Subsequent images - keep existing finals, show partial at current position
+                    const existingAttachments = msg.attachments || [];
+                    // Keep only the completed final images (up to current imageIndex)
+                    const finals = existingAttachments.slice(0, imageIndex);
+                    msg.attachments = [...finals, partialAttachment];
+                  }
+                },
+              );
+            } else if (parsed.type === "final") {
+              // Final image - replace partial at this position
+              const newAttachment: MessageAttachment = {
+                type: "generated-image",
+                name: `generated-image-${imageIndex + 1}.${format}`,
+                preview: `data:${mimeType};base64,${imageData}`,
+                mimeType,
+              };
+
+              this.updateConversationMessage(
+                targetConversationId,
+                assistantMessage.id,
+                (msg) => {
+                  if (imageIndex === 0) {
+                    // First final image - replace any partial preview
+                    msg.attachments = [newAttachment];
+                  } else {
+                    // Subsequent images - keep previous finals, replace partial at current position
+                    const existingAttachments = msg.attachments || [];
+                    // Slice keeps indices 0 to imageIndex-1 (the previous final images)
+                    const previousFinals = existingAttachments.slice(
+                      0,
+                      imageIndex,
+                    );
+                    msg.attachments = [...previousFinals, newAttachment];
+                  }
+
+                  // Update progress message for multiple images
+                  if (numImages > 1 && imageIndex < numImages - 1) {
+                    msg.content = `Generating image ${imageIndex + 2}/${numImages}...`;
+                  } else {
+                    msg.content = "";
+                  }
+                },
+              );
+            }
+
+            this.syncActiveMessagesIfNeeded(targetConversationId);
+          }
+        },
+      );
     } catch (error) {
       console.error("Error generating image:", error);
       this.handleStreamingError(
@@ -2408,98 +2343,69 @@ class AppStore {
         throw new Error(`API error: ${apiResponse.status} - ${errorText}`);
       }
 
-      // Streaming requires both stream=true AND partialImages > 0
-      const isStreaming = params.stream && params.partialImages > 0;
-
-      if (!isStreaming) {
-        // Non-streaming: parse JSON response directly
-        const jsonResponse = (await apiResponse.json()) as ImageApiResponse;
-        const format = params.outputFormat || "png";
-        const mimeType = `image/${format}`;
-        const attachments: MessageAttachment[] = jsonResponse.data
-          .filter((img) => img.b64_json)
-          .map((img) => ({
-            type: "generated-image" as const,
-            name: `edited-image.${format}`,
-            preview: `data:${mimeType};base64,${img.b64_json}`,
-            mimeType,
-          }));
-
-        this.updateConversationMessage(
-          targetConversationId,
-          assistantMessage.id,
-          (msg) => {
-            msg.content = "";
-            msg.attachments = attachments;
-          },
-        );
-        this.syncActiveMessagesIfNeeded(targetConversationId);
-      } else {
-        // Streaming mode: use SSE parser
-        const reader = apiResponse.body?.getReader();
-        if (!reader) {
-          throw new Error("No response body");
-        }
-
-        interface ImageEditChunk {
-          data?: { b64_json?: string };
-          format?: string;
-          type?: "partial" | "final";
-          partial_index?: number;
-          total_partials?: number;
-        }
-
-        await this.parseSSEStream<ImageEditChunk>(
-          reader,
-          targetConversationId,
-          (parsed) => {
-            const imageData = parsed.data?.b64_json;
-
-            if (imageData) {
-              const format = parsed.format || "png";
-              const mimeType = `image/${format}`;
-              if (parsed.type === "partial") {
-                // Update with partial image and progress
-                const partialNum = (parsed.partial_index ?? 0) + 1;
-                const totalPartials = parsed.total_partials ?? 3;
-                this.updateConversationMessage(
-                  targetConversationId,
-                  assistantMessage.id,
-                  (msg) => {
-                    msg.content = `Editing... ${partialNum}/${totalPartials}`;
-                    msg.attachments = [
-                      {
-                        type: "generated-image",
-                        name: `edited-image.${format}`,
-                        preview: `data:${mimeType};base64,${imageData}`,
-                        mimeType,
-                      },
-                    ];
-                  },
-                );
-              } else if (parsed.type === "final") {
-                // Final image
-                this.updateConversationMessage(
-                  targetConversationId,
-                  assistantMessage.id,
-                  (msg) => {
-                    msg.content = "";
-                    msg.attachments = [
-                      {
-                        type: "generated-image",
-                        name: `edited-image.${format}`,
-                        preview: `data:${mimeType};base64,${imageData}`,
-                        mimeType,
-                      },
-                    ];
-                  },
-                );
-              }
-              this.syncActiveMessagesIfNeeded(targetConversationId);
-            }
-          },
-        );
+      const reader = apiResponse.body?.getReader();
+      if (!reader) {
+        throw new Error("No response body");
       }
+
+      interface ImageEditChunk {
+        data?: { b64_json?: string };
+        format?: string;
+        type?: "partial" | "final";
+        partial_index?: number;
+        total_partials?: number;
+      }
+
+      await this.parseSSEStream<ImageEditChunk>(
+        reader,
+        targetConversationId,
+        (parsed) => {
+          const imageData = parsed.data?.b64_json;
+
+          if (imageData) {
+            const format = parsed.format || "png";
+            const mimeType = `image/${format}`;
+            if (parsed.type === "partial") {
+              // Update with partial image and progress
+              const partialNum = (parsed.partial_index ?? 0) + 1;
+              const totalPartials = parsed.total_partials ?? 3;
+              this.updateConversationMessage(
+                targetConversationId,
+                assistantMessage.id,
+                (msg) => {
+                  msg.content = `Editing... ${partialNum}/${totalPartials}`;
+                  msg.attachments = [
+                    {
+                      type: "generated-image",
+                      name: `edited-image.${format}`,
+                      preview: `data:${mimeType};base64,${imageData}`,
+                      mimeType,
+                    },
+                  ];
+                },
+              );
+            } else if (parsed.type === "final") {
+              // Final image
+              this.updateConversationMessage(
+                targetConversationId,
+                assistantMessage.id,
+                (msg) => {
+                  msg.content = "";
+                  msg.attachments = [
+                    {
+                      type: "generated-image",
+                      name: `edited-image.${format}`,
+                      preview: `data:${mimeType};base64,${imageData}`,
+                      mimeType,
+                    },
+                  ];
+                },
+              );
+            }
+            this.syncActiveMessagesIfNeeded(targetConversationId);
+          }
+        },
+      );
     } catch (error) {
       console.error("Error editing image:", error);
       this.handleStreamingError(
@@ -2585,49 +2491,6 @@ class AppStore {
       throw error;
     }
   }
-
-  /**
-   * List all available traces
-   */
-  async listTraces(): Promise<TraceListResponse> {
-    const response = await fetch("/v1/traces");
-    if (!response.ok) {
-      throw new Error(`Failed to list traces: ${response.status}`);
-    }
-    return (await response.json()) as TraceListResponse;
-  }
-
-  /**
-   * Check if a trace exists for a given task ID
-   */
-  async checkTraceExists(taskId: string): Promise<boolean> {
-    try {
-      const response = await fetch(`/v1/traces/${encodeURIComponent(taskId)}`);
-      return response.ok;
-    } catch {
-      return false;
-    }
-  }
-
-  /**
-   * Get computed statistics for a task's trace
-   */
-  async fetchTraceStats(taskId: string): Promise<TraceStatsResponse> {
-    const response = await fetch(
-      `/v1/traces/${encodeURIComponent(taskId)}/stats`,
-    );
-    if (!response.ok) {
-      throw new Error(`Failed to fetch trace stats: ${response.status}`);
-    }
-    return (await response.json()) as TraceStatsResponse;
-  }
-
-  /**
-   * Get the URL for the raw trace file (for Perfetto)
-   */
-  getTraceRawUrl(taskId: string): string {
-    return `/v1/traces/${encodeURIComponent(taskId)}/raw`;
-  }
 }
 
 export const appStore = new AppStore();
@@ -2739,12 +2602,3 @@ export const startDownload = (nodeId: string, shardMetadata: object) =>
   appStore.startDownload(nodeId, shardMetadata);
 export const deleteDownload = (nodeId: string, modelId: string) =>
   appStore.deleteDownload(nodeId, modelId);
-
-// Trace actions
-export const listTraces = () => appStore.listTraces();
-export const checkTraceExists = (taskId: string) =>
-  appStore.checkTraceExists(taskId);
-export const fetchTraceStats = (taskId: string) =>
-  appStore.fetchTraceStats(taskId);
-export const getTraceRawUrl = (taskId: string) =>
-  appStore.getTraceRawUrl(taskId);

dashboard/src/lib/stores/favorites.svelte.ts

@@ -1,97 +0,0 @@
-/**
- * FavoritesStore - Manages favorite models with localStorage persistence
- */
-
-import { browser } from "$app/environment";
-
-const FAVORITES_KEY = "exo-favorite-models";
-
-class FavoritesStore {
-  favorites = $state<Set<string>>(new Set());
-
-  constructor() {
-    if (browser) {
-      this.loadFromStorage();
-    }
-  }
-
-  private loadFromStorage() {
-    try {
-      const stored = localStorage.getItem(FAVORITES_KEY);
-      if (stored) {
-        const parsed = JSON.parse(stored) as string[];
-        this.favorites = new Set(parsed);
-      }
-    } catch (error) {
-      console.error("Failed to load favorites:", error);
-    }
-  }
-
-  private saveToStorage() {
-    try {
-      const array = Array.from(this.favorites);
-      localStorage.setItem(FAVORITES_KEY, JSON.stringify(array));
-    } catch (error) {
-      console.error("Failed to save favorites:", error);
-    }
-  }
-
-  add(baseModelId: string) {
-    const next = new Set(this.favorites);
-    next.add(baseModelId);
-    this.favorites = next;
-    this.saveToStorage();
-  }
-
-  remove(baseModelId: string) {
-    const next = new Set(this.favorites);
-    next.delete(baseModelId);
-    this.favorites = next;
-    this.saveToStorage();
-  }
-
-  toggle(baseModelId: string) {
-    if (this.favorites.has(baseModelId)) {
-      this.remove(baseModelId);
-    } else {
-      this.add(baseModelId);
-    }
-  }
-
-  isFavorite(baseModelId: string): boolean {
-    return this.favorites.has(baseModelId);
-  }
-
-  getAll(): string[] {
-    return Array.from(this.favorites);
-  }
-
-  getSet(): Set<string> {
-    return new Set(this.favorites);
-  }
-
-  hasAny(): boolean {
-    return this.favorites.size > 0;
-  }
-
-  clearAll() {
-    this.favorites = new Set();
-    this.saveToStorage();
-  }
-}
-
-export const favoritesStore = new FavoritesStore();
-
-export const favorites = () => favoritesStore.favorites;
-export const hasFavorites = () => favoritesStore.hasAny();
-export const isFavorite = (baseModelId: string) =>
-  favoritesStore.isFavorite(baseModelId);
-export const toggleFavorite = (baseModelId: string) =>
-  favoritesStore.toggle(baseModelId);
-export const addFavorite = (baseModelId: string) =>
-  favoritesStore.add(baseModelId);
-export const removeFavorite = (baseModelId: string) =>
-  favoritesStore.remove(baseModelId);
-export const getFavorites = () => favoritesStore.getAll();
-export const getFavoritesSet = () => favoritesStore.getSet();
-export const clearFavorites = () => favoritesStore.clearAll();

dashboard/src/routes/+page.svelte

@@ -5,13 +5,7 @@
     ChatMessages,
     ChatSidebar,
     ModelCard,
-    ModelPickerModal,
   } from "$lib/components";
-  import {
-    favorites,
-    toggleFavorite,
-    getFavoritesSet,
-  } from "$lib/stores/favorites.svelte";
   import {
     hasStartedChat,
     isTopologyMinimized,
@@ -106,11 +100,6 @@
       storage_size_megabytes?: number;
       tasks?: string[];
       hugging_face_id?: string;
-      is_custom?: boolean;
-      family?: string;
-      quantization?: string;
-      base_model?: string;
-      capabilities?: string[];
     }>
   >([]);
 
@@ -222,11 +211,9 @@
   let launchingModelId = $state<string | null>(null);
   let instanceDownloadExpandedNodes = $state<Set<string>>(new Set());
 
-  // Model picker modal state
-  let isModelPickerOpen = $state(false);
-
-  // Favorites state (reactive)
-  const favoritesSet = $derived(getFavoritesSet());
+  // Custom dropdown state
+  let isModelDropdownOpen = $state(false);
+  let modelDropdownSearch = $state("");
 
   // Slider dragging state
   let isDraggingSlider = $state(false);
@@ -543,47 +530,6 @@
     }
   }
 
-  async function addModelFromPicker(modelId: string) {
-    const response = await fetch("/models/add", {
-      method: "POST",
-      headers: { "Content-Type": "application/json" },
-      body: JSON.stringify({ model_id: modelId }),
-    });
-
-    if (!response.ok) {
-      let message = `Failed to add model (${response.status}: ${response.statusText})`;
-      try {
-        const err = await response.json();
-        if (err.detail) message = err.detail;
-      } catch {
-        // use default message
-      }
-      throw new Error(message);
-    }
-
-    await fetchModels();
-  }
-
-  async function deleteCustomModel(modelId: string) {
-    try {
-      const response = await fetch(
-        `/models/custom/${encodeURIComponent(modelId)}`,
-        { method: "DELETE" },
-      );
-      if (response.ok) {
-        await fetchModels();
-      }
-    } catch {
-      console.error("Failed to delete custom model");
-    }
-  }
-
-  function handleModelPickerSelect(modelId: string) {
-    selectPreviewModel(modelId);
-    saveLaunchDefaults();
-    isModelPickerOpen = false;
-  }
-
   async function launchInstance(
     modelId: string,
     specificPreview?: PlacementPreview | null,
@@ -2414,12 +2360,14 @@
               >
             </div>
 
-            <!-- Model Picker Button -->
-            <div class="flex-shrink-0 mb-3">
+            <!-- Model Dropdown (Custom) -->
+            <div class="flex-shrink-0 mb-3 relative">
               <button
                 type="button"
-                onclick={() => (isModelPickerOpen = true)}
-                class="w-full bg-exo-medium-gray/50 border border-exo-yellow/30 rounded pl-3 pr-8 py-2.5 text-sm font-mono text-left tracking-wide cursor-pointer transition-all duration-200 hover:border-exo-yellow/50 focus:outline-none focus:border-exo-yellow/70 relative"
+                onclick={() => (isModelDropdownOpen = !isModelDropdownOpen)}
+                class="w-full bg-exo-medium-gray/50 border border-exo-yellow/30 rounded pl-3 pr-8 py-2.5 text-sm font-mono text-left tracking-wide cursor-pointer transition-all duration-200 hover:border-exo-yellow/50 focus:outline-none focus:border-exo-yellow/70 {isModelDropdownOpen
+                  ? 'border-exo-yellow/70'
+                  : ''}"
               >
                 {#if selectedModelId}
                   {@const foundModel = models.find(
@@ -2427,12 +2375,54 @@
                   )}
                   {#if foundModel}
                     {@const sizeGB = getModelSizeGB(foundModel)}
+                    {@const isImageModel = modelSupportsImageGeneration(
+                      foundModel.id,
+                    )}
+                    {@const isImageEditModel = modelSupportsImageEditing(
+                      foundModel.id,
+                    )}
                     <span
                       class="flex items-center justify-between gap-2 w-full pr-4"
                     >
                       <span
                         class="flex items-center gap-2 text-exo-light-gray truncate"
                       >
+                        {#if isImageModel}
+                          <svg
+                            class="w-4 h-4 flex-shrink-0 text-exo-yellow"
+                            fill="none"
+                            viewBox="0 0 24 24"
+                            stroke="currentColor"
+                            stroke-width="2"
+                          >
+                            <rect
+                              x="3"
+                              y="3"
+                              width="18"
+                              height="18"
+                              rx="2"
+                              ry="2"
+                            />
+                            <circle cx="8.5" cy="8.5" r="1.5" />
+                            <polyline points="21 15 16 10 5 21" />
+                          </svg>
+                        {/if}
+                        {#if isImageEditModel}
+                          <svg
+                            class="w-4 h-4 flex-shrink-0 text-exo-yellow"
+                            fill="none"
+                            viewBox="0 0 24 24"
+                            stroke="currentColor"
+                            stroke-width="2"
+                          >
+                            <path
+                              d="M11 4H4a2 2 0 0 0-2 2v14a2 2 0 0 0 2 2h14a2 2 0 0 0 2-2v-7"
+                            />
+                            <path
+                              d="M18.5 2.5a2.121 2.121 0 0 1 3 3L12 15l-4 1 1-4 9.5-9.5z"
+                            />
+                          </svg>
+                        {/if}
                         <span class="truncate"
                           >{foundModel.name || foundModel.id}</span
                         >
@@ -2449,24 +2439,142 @@
                 {:else}
                   <span class="text-white/50">— SELECT MODEL —</span>
                 {/if}
-                <div
-                  class="absolute right-3 top-1/2 -translate-y-1/2 pointer-events-none"
-                >
-                  <svg
-                    class="w-4 h-4 text-exo-yellow/60"
-                    fill="none"
-                    viewBox="0 0 24 24"
-                    stroke="currentColor"
-                  >
-                    <path
-                      stroke-linecap="round"
-                      stroke-linejoin="round"
-                      stroke-width="2"
-                      d="M19 9l-7 7-7-7"
-                    />
-                  </svg>
-                </div>
               </button>
+              <div
+                class="absolute right-3 top-1/2 -translate-y-1/2 pointer-events-none transition-transform duration-200 {isModelDropdownOpen
+                  ? 'rotate-180'
+                  : ''}"
+              >
+                <svg
+                  class="w-4 h-4 text-exo-yellow/60"
+                  fill="none"
+                  viewBox="0 0 24 24"
+                  stroke="currentColor"
+                >
+                  <path
+                    stroke-linecap="round"
+                    stroke-linejoin="round"
+                    stroke-width="2"
+                    d="M19 9l-7 7-7-7"
+                  />
+                </svg>
+              </div>
+
+              {#if isModelDropdownOpen}
+                <!-- Backdrop to close dropdown -->
+                <button
+                  type="button"
+                  class="fixed inset-0 z-40 cursor-default"
+                  onclick={() => (isModelDropdownOpen = false)}
+                  aria-label="Close dropdown"
+                ></button>
+
+                <!-- Dropdown Panel -->
+                <div
+                  class="absolute top-full left-0 right-0 mt-1 bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-50 max-h-64 overflow-y-auto"
+                >
+                  <!-- Search within dropdown -->
+                  <div
+                    class="sticky top-0 bg-exo-dark-gray border-b border-exo-medium-gray/30 p-2"
+                  >
+                    <input
+                      type="text"
+                      placeholder="Search models..."
+                      bind:value={modelDropdownSearch}
+                      class="w-full bg-exo-dark-gray/60 border border-exo-medium-gray/30 rounded px-2 py-1.5 text-xs font-mono text-white/80 placeholder:text-white/40 focus:outline-none focus:border-exo-yellow/50"
+                    />
+                  </div>
+
+                  <!-- Options -->
+                  <div class="py-1">
+                    {#each sortedModels().filter((m) => !modelDropdownSearch || (m.name || m.id)
+                          .toLowerCase()
+                          .includes(modelDropdownSearch.toLowerCase())) as model}
+                      {@const sizeGB = getModelSizeGB(model)}
+                      {@const modelCanFit = hasEnoughMemory(model)}
+                      {@const isImageModel = modelSupportsImageGeneration(
+                        model.id,
+                      )}
+                      {@const isImageEditModel = modelSupportsImageEditing(
+                        model.id,
+                      )}
+                      <button
+                        type="button"
+                        onclick={() => {
+                          if (modelCanFit) {
+                            selectPreviewModel(model.id);
+                            saveLaunchDefaults();
+                            isModelDropdownOpen = false;
+                            modelDropdownSearch = "";
+                          }
+                        }}
+                        disabled={!modelCanFit}
+                        class="w-full px-3 py-2 text-left text-sm font-mono tracking-wide transition-colors duration-100 flex items-center justify-between gap-2 {selectedModelId ===
+                        model.id
+                          ? 'bg-transparent text-exo-yellow cursor-pointer'
+                          : modelCanFit
+                            ? 'text-white/80 hover:text-exo-yellow cursor-pointer'
+                            : 'text-white/30 cursor-default'}"
+                      >
+                        <span class="flex items-center gap-2 truncate flex-1">
+                          {#if isImageModel}
+                            <svg
+                              class="w-4 h-4 flex-shrink-0 text-exo-yellow"
+                              fill="none"
+                              viewBox="0 0 24 24"
+                              stroke="currentColor"
+                              stroke-width="2"
+                              aria-label="Image generation model"
+                            >
+                              <rect
+                                x="3"
+                                y="3"
+                                width="18"
+                                height="18"
+                                rx="2"
+                                ry="2"
+                              />
+                              <circle cx="8.5" cy="8.5" r="1.5" />
+                              <polyline points="21 15 16 10 5 21" />
+                            </svg>
+                          {/if}
+                          {#if isImageEditModel}
+                            <svg
+                              class="w-4 h-4 flex-shrink-0 text-exo-yellow"
+                              fill="none"
+                              viewBox="0 0 24 24"
+                              stroke="currentColor"
+                              stroke-width="2"
+                              aria-label="Image editing model"
+                            >
+                              <path
+                                d="M11 4H4a2 2 0 0 0-2 2v14a2 2 0 0 0 2 2h14a2 2 0 0 0 2-2v-7"
+                              />
+                              <path
+                                d="M18.5 2.5a2.121 2.121 0 0 1 3 3L12 15l-4 1 1-4 9.5-9.5z"
+                              />
+                            </svg>
+                          {/if}
+                          <span class="truncate">{model.name || model.id}</span>
+                        </span>
+                        <span
+                          class="flex-shrink-0 text-xs {modelCanFit
+                            ? 'text-white/50'
+                            : 'text-red-400/60'}"
+                        >
+                          {sizeGB >= 1
+                            ? sizeGB.toFixed(0)
+                            : sizeGB.toFixed(1)}GB
+                        </span>
+                      </button>
+                    {:else}
+                      <div class="px-3 py-2 text-xs text-white/50 font-mono">
+                        No models found
+                      </div>
+                    {/each}
+                  </div>
+                </div>
+              {/if}
             </div>
 
             <!-- Configuration Options -->
@@ -3246,22 +3354,3 @@
     {/if}
   </main>
 </div>
-
-<ModelPickerModal
-  isOpen={isModelPickerOpen}
-  {models}
-  {selectedModelId}
-  favorites={favoritesSet}
-  existingModelIds={new Set(models.map((m) => m.id))}
-  canModelFit={(modelId) => {
-    const model = models.find((m) => m.id === modelId);
-    return model ? hasEnoughMemory(model) : false;
-  }}
-  onSelect={handleModelPickerSelect}
-  onClose={() => (isModelPickerOpen = false)}
-  onToggleFavorite={toggleFavorite}
-  onAddModel={addModelFromPicker}
-  onDeleteModel={deleteCustomModel}
-  totalMemoryGB={clusterMemory().total / (1024 * 1024 * 1024)}
-  usedMemoryGB={clusterMemory().used / (1024 * 1024 * 1024)}
-/>

dashboard/src/routes/traces/+page.svelte

@@ -1,190 +0,0 @@
-<script lang="ts">
-  import { onMount } from "svelte";
-  import {
-    listTraces,
-    getTraceRawUrl,
-    type TraceListItem,
-  } from "$lib/stores/app.svelte";
-  import HeaderNav from "$lib/components/HeaderNav.svelte";
-
-  let traces = $state<TraceListItem[]>([]);
-  let loading = $state(true);
-  let error = $state<string | null>(null);
-
-  function formatBytes(bytes: number): string {
-    if (!bytes || bytes <= 0) return "0B";
-    const units = ["B", "KB", "MB", "GB"];
-    const i = Math.min(
-      Math.floor(Math.log(bytes) / Math.log(1024)),
-      units.length - 1,
-    );
-    const val = bytes / Math.pow(1024, i);
-    return `${val.toFixed(val >= 10 ? 0 : 1)}${units[i]}`;
-  }
-
-  function formatDate(isoString: string): string {
-    const date = new Date(isoString);
-    return date.toLocaleString();
-  }
-
-  async function downloadTrace(taskId: string) {
-    const response = await fetch(getTraceRawUrl(taskId));
-    const blob = await response.blob();
-    const url = URL.createObjectURL(blob);
-    const a = document.createElement("a");
-    a.href = url;
-    a.download = `trace_${taskId}.json`;
-    a.click();
-    URL.revokeObjectURL(url);
-  }
-
-  async function openInPerfetto(taskId: string) {
-    // Fetch trace data from our local API
-    const response = await fetch(getTraceRawUrl(taskId));
-    const traceData = await response.arrayBuffer();
-
-    // Open Perfetto UI
-    const perfettoWindow = window.open("https://ui.perfetto.dev");
-    if (!perfettoWindow) {
-      alert("Failed to open Perfetto. Please allow popups.");
-      return;
-    }
-
-    // Wait for Perfetto to be ready, then send trace via postMessage
-    const onMessage = (e: MessageEvent) => {
-      if (e.data === "PONG") {
-        window.removeEventListener("message", onMessage);
-        perfettoWindow.postMessage(
-          {
-            perfetto: {
-              buffer: traceData,
-              title: `Trace ${taskId}`,
-            },
-          },
-          "https://ui.perfetto.dev",
-        );
-      }
-    };
-    window.addEventListener("message", onMessage);
-
-    // Ping Perfetto until it responds
-    const pingInterval = setInterval(() => {
-      perfettoWindow.postMessage("PING", "https://ui.perfetto.dev");
-    }, 50);
-
-    // Clean up after 10 seconds
-    setTimeout(() => {
-      clearInterval(pingInterval);
-      window.removeEventListener("message", onMessage);
-    }, 10000);
-  }
-
-  async function refresh() {
-    loading = true;
-    error = null;
-    try {
-      const response = await listTraces();
-      traces = response.traces;
-    } catch (e) {
-      error = e instanceof Error ? e.message : "Failed to load traces";
-    } finally {
-      loading = false;
-    }
-  }
-
-  onMount(() => {
-    refresh();
-  });
-</script>
-
-<div class="min-h-screen bg-exo-dark-gray text-white">
-  <HeaderNav showHome={true} />
-  <div class="max-w-7xl mx-auto px-4 lg:px-8 py-6 space-y-6">
-    <div class="flex items-center justify-between gap-4 flex-wrap">
-      <div>
-        <h1
-          class="text-2xl font-mono tracking-[0.2em] uppercase text-exo-yellow"
-        >
-          Traces
-        </h1>
-      </div>
-      <div class="flex items-center gap-3">
-        <button
-          type="button"
-          class="text-xs font-mono text-exo-light-gray hover:text-exo-yellow transition-colors uppercase border border-exo-medium-gray/40 px-2 py-1 rounded"
-          onclick={refresh}
-          disabled={loading}
-        >
-          Refresh
-        </button>
-      </div>
-    </div>
-
-    {#if loading}
-      <div
-        class="rounded border border-exo-medium-gray/30 bg-exo-black/30 p-6 text-center text-exo-light-gray"
-      >
-        <div class="text-sm">Loading traces...</div>
-      </div>
-    {:else if error}
-      <div
-        class="rounded border border-red-500/30 bg-red-500/10 p-6 text-center text-red-400"
-      >
-        <div class="text-sm">{error}</div>
-      </div>
-    {:else if traces.length === 0}
-      <div
-        class="rounded border border-exo-medium-gray/30 bg-exo-black/30 p-6 text-center text-exo-light-gray space-y-2"
-      >
-        <div class="text-sm">No traces found.</div>
-        <div class="text-xs text-exo-light-gray/70">
-          Run exo with EXO_TRACING_ENABLED=1 to collect traces.
-        </div>
-      </div>
-    {:else}
-      <div class="space-y-3">
-        {#each traces as trace}
-          <div
-            class="rounded border border-exo-medium-gray/30 bg-exo-black/30 p-4 flex items-center justify-between gap-4"
-          >
-            <div class="min-w-0 flex-1">
-              <a
-                href="#/traces/{trace.taskId}"
-                class="text-sm font-mono text-white hover:text-exo-yellow transition-colors truncate block"
-              >
-                {trace.taskId}
-              </a>
-              <div class="text-xs text-exo-light-gray font-mono mt-1">
-                {formatDate(trace.createdAt)} &bull; {formatBytes(
-                  trace.fileSize,
-                )}
-              </div>
-            </div>
-            <div class="flex items-center gap-2 shrink-0">
-              <a
-                href="#/traces/{trace.taskId}"
-                class="text-xs font-mono text-exo-light-gray hover:text-exo-yellow transition-colors uppercase border border-exo-medium-gray/40 px-2 py-1 rounded"
-              >
-                View Stats
-              </a>
-              <button
-                type="button"
-                class="text-xs font-mono text-exo-light-gray hover:text-exo-yellow transition-colors uppercase border border-exo-medium-gray/40 px-2 py-1 rounded"
-                onclick={() => downloadTrace(trace.taskId)}
-              >
-                Download
-              </button>
-              <button
-                type="button"
-                class="text-xs font-mono text-exo-dark-gray bg-exo-yellow hover:bg-exo-yellow/90 transition-colors uppercase px-2 py-1 rounded font-semibold"
-                onclick={() => openInPerfetto(trace.taskId)}
-              >
-                View Trace
-              </button>
-            </div>
-          </div>
-        {/each}
-      </div>
-    {/if}
-  </div>
-</div>

dashboard/src/routes/traces/[taskId]/+page.svelte

@@ -1,367 +0,0 @@
-<script lang="ts">
-  import { page } from "$app/stores";
-  import { onMount } from "svelte";
-  import {
-    fetchTraceStats,
-    getTraceRawUrl,
-    type TraceStatsResponse,
-    type TraceCategoryStats,
-  } from "$lib/stores/app.svelte";
-  import HeaderNav from "$lib/components/HeaderNav.svelte";
-
-  const taskId = $derived($page.params.taskId);
-
-  let stats = $state<TraceStatsResponse | null>(null);
-  let loading = $state(true);
-  let error = $state<string | null>(null);
-
-  function formatDuration(us: number): string {
-    if (us < 1000) return `${us.toFixed(0)}us`;
-    if (us < 1_000_000) return `${(us / 1000).toFixed(2)}ms`;
-    return `${(us / 1_000_000).toFixed(2)}s`;
-  }
-
-  function formatPercentage(part: number, total: number): string {
-    if (total === 0) return "0.0%";
-    return `${((part / total) * 100).toFixed(1)}%`;
-  }
-
-  // Parse hierarchical categories like "sync/compute" into phases
-  type PhaseData = {
-    name: string;
-    subcategories: { name: string; stats: TraceCategoryStats }[];
-    totalUs: number; // From outer span (e.g., "sync" category)
-    stepCount: number; // Count of outer span events
-  };
-
-  function parsePhases(
-    byCategory: Record<string, TraceCategoryStats>,
-  ): PhaseData[] {
-    const phases = new Map<
-      string,
-      {
-        subcats: Map<string, TraceCategoryStats>;
-        outerStats: TraceCategoryStats | null;
-      }
-    >();
-
-    for (const [category, catStats] of Object.entries(byCategory)) {
-      if (category.includes("/")) {
-        const [phase, subcat] = category.split("/", 2);
-        if (!phases.has(phase)) {
-          phases.set(phase, { subcats: new Map(), outerStats: null });
-        }
-        phases.get(phase)!.subcats.set(subcat, catStats);
-      } else {
-        // Outer span - this IS the phase total
-        if (!phases.has(category)) {
-          phases.set(category, { subcats: new Map(), outerStats: null });
-        }
-        phases.get(category)!.outerStats = catStats;
-      }
-    }
-
-    return Array.from(phases.entries())
-      .filter(([_, data]) => data.outerStats !== null) // Only phases with outer spans
-      .map(([name, data]) => ({
-        name,
-        subcategories: Array.from(data.subcats.entries())
-          .map(([subName, subStats]) => ({ name: subName, stats: subStats }))
-          .sort((a, b) => b.stats.totalUs - a.stats.totalUs),
-        totalUs: data.outerStats!.totalUs, // Outer span total
-        stepCount: data.outerStats!.count, // Number of steps
-      }))
-      .sort((a, b) => b.totalUs - a.totalUs);
-  }
-
-  async function downloadTrace() {
-    if (!taskId) return;
-    const response = await fetch(getTraceRawUrl(taskId));
-    const blob = await response.blob();
-    const url = URL.createObjectURL(blob);
-    const a = document.createElement("a");
-    a.href = url;
-    a.download = `trace_${taskId}.json`;
-    a.click();
-    URL.revokeObjectURL(url);
-  }
-
-  async function openInPerfetto() {
-    if (!taskId) return;
-
-    // Fetch trace data from our local API
-    const response = await fetch(getTraceRawUrl(taskId));
-    const traceData = await response.arrayBuffer();
-
-    // Open Perfetto UI
-    const perfettoWindow = window.open("https://ui.perfetto.dev");
-    if (!perfettoWindow) {
-      alert("Failed to open Perfetto. Please allow popups.");
-      return;
-    }
-
-    // Wait for Perfetto to be ready, then send trace via postMessage
-    const onMessage = (e: MessageEvent) => {
-      if (e.data === "PONG") {
-        window.removeEventListener("message", onMessage);
-        perfettoWindow.postMessage(
-          {
-            perfetto: {
-              buffer: traceData,
-              title: `Trace ${taskId}`,
-            },
-          },
-          "https://ui.perfetto.dev",
-        );
-      }
-    };
-    window.addEventListener("message", onMessage);
-
-    // Ping Perfetto until it responds
-    const pingInterval = setInterval(() => {
-      perfettoWindow.postMessage("PING", "https://ui.perfetto.dev");
-    }, 50);
-
-    // Clean up after 10 seconds
-    setTimeout(() => {
-      clearInterval(pingInterval);
-      window.removeEventListener("message", onMessage);
-    }, 10000);
-  }
-
-  onMount(async () => {
-    if (!taskId) {
-      error = "No task ID provided";
-      loading = false;
-      return;
-    }
-
-    try {
-      stats = await fetchTraceStats(taskId);
-    } catch (e) {
-      error = e instanceof Error ? e.message : "Failed to load trace";
-    } finally {
-      loading = false;
-    }
-  });
-
-  const phases = $derived(stats ? parsePhases(stats.byCategory) : []);
-  const sortedRanks = $derived(
-    stats
-      ? Object.keys(stats.byRank)
-          .map(Number)
-          .sort((a, b) => a - b)
-      : [],
-  );
-  const nodeCount = $derived(sortedRanks.length || 1);
-</script>
-
-<div class="min-h-screen bg-exo-dark-gray text-white">
-  <HeaderNav showHome={true} />
-  <div class="max-w-7xl mx-auto px-4 lg:px-8 py-6 space-y-6">
-    <div class="flex items-center justify-between gap-4 flex-wrap">
-      <div>
-        <h1
-          class="text-2xl font-mono tracking-[0.2em] uppercase text-exo-yellow"
-        >
-          Trace
-        </h1>
-        <p class="text-sm text-exo-light-gray font-mono truncate max-w-lg">
-          {taskId}
-        </p>
-      </div>
-      <div class="flex items-center gap-3">
-        <a
-          href="#/traces"
-          class="text-xs font-mono text-exo-light-gray hover:text-exo-yellow transition-colors uppercase border border-exo-medium-gray/40 px-3 py-1.5 rounded"
-        >
-          All Traces
-        </a>
-        <button
-          type="button"
-          class="text-xs font-mono text-exo-light-gray hover:text-exo-yellow transition-colors uppercase border border-exo-medium-gray/40 px-3 py-1.5 rounded"
-          onclick={downloadTrace}
-          disabled={loading || !!error}
-        >
-          Download
-        </button>
-        <button
-          type="button"
-          class="text-xs font-mono text-exo-dark-gray bg-exo-yellow hover:bg-exo-yellow/90 transition-colors uppercase px-3 py-1.5 rounded font-semibold"
-          onclick={openInPerfetto}
-          disabled={loading || !!error}
-        >
-          View Trace
-        </button>
-      </div>
-    </div>
-
-    {#if loading}
-      <div
-        class="rounded border border-exo-medium-gray/30 bg-exo-black/30 p-6 text-center text-exo-light-gray"
-      >
-        <div class="text-sm">Loading trace data...</div>
-      </div>
-    {:else if error}
-      <div
-        class="rounded border border-red-500/30 bg-red-500/10 p-6 text-center text-red-400"
-      >
-        <div class="text-sm">{error}</div>
-      </div>
-    {:else if stats}
-      <!-- Wall Time Summary -->
-      <div
-        class="rounded border border-exo-medium-gray/30 bg-exo-black/30 p-4 space-y-2"
-      >
-        <h2
-          class="text-sm font-mono uppercase tracking-wider text-exo-light-gray"
-        >
-          Summary
-        </h2>
-        <div class="text-3xl font-mono text-exo-yellow">
-          {formatDuration(stats.totalWallTimeUs)}
-        </div>
-        <div class="text-xs text-exo-light-gray">Total wall time</div>
-      </div>
-
-      <!-- By Phase -->
-      {#if phases.length > 0}
-        <div
-          class="rounded border border-exo-medium-gray/30 bg-exo-black/30 p-4 space-y-4"
-        >
-          <h2
-            class="text-sm font-mono uppercase tracking-wider text-exo-light-gray"
-          >
-            By Phase <span class="text-exo-light-gray/50">(avg per node)</span>
-          </h2>
-          <div class="space-y-4">
-            {#each phases as phase}
-              {@const normalizedTotal = phase.totalUs / nodeCount}
-              {@const normalizedStepCount = phase.stepCount / nodeCount}
-              <div class="space-y-2">
-                <div class="flex items-center justify-between">
-                  <span class="text-sm font-mono text-white">{phase.name}</span>
-                  <span class="text-sm font-mono">
-                    <span class="text-exo-yellow"
-                      >{formatDuration(normalizedTotal)}</span
-                    >
-                    <span class="text-exo-light-gray ml-2">
-                      ({normalizedStepCount} steps, {formatDuration(
-                        normalizedTotal / normalizedStepCount,
-                      )}/step)
-                    </span>
-                  </span>
-                </div>
-                {#if phase.subcategories.length > 0}
-                  <div class="pl-4 space-y-1.5">
-                    {#each phase.subcategories as subcat}
-                      {@const normalizedSubcat =
-                        subcat.stats.totalUs / nodeCount}
-                      {@const pct = formatPercentage(
-                        normalizedSubcat,
-                        normalizedTotal,
-                      )}
-                      {@const perStep = normalizedSubcat / normalizedStepCount}
-                      <div
-                        class="flex items-center justify-between text-xs font-mono"
-                      >
-                        <span class="text-exo-light-gray">{subcat.name}</span>
-                        <span class="text-white">
-                          {formatDuration(normalizedSubcat)}
-                          <span class="text-exo-light-gray ml-2">({pct})</span>
-                          <span class="text-exo-light-gray/60 ml-2"
-                            >{formatDuration(perStep)}/step</span
-                          >
-                        </span>
-                      </div>
-                      <!-- Progress bar -->
-                      <div
-                        class="relative h-1.5 bg-exo-black/60 rounded-sm overflow-hidden"
-                      >
-                        <div
-                          class="absolute inset-y-0 left-0 bg-gradient-to-r from-exo-yellow to-exo-yellow/70 transition-all duration-300"
-                          style="width: {pct}"
-                        ></div>
-                      </div>
-                    {/each}
-                  </div>
-                {/if}
-              </div>
-            {/each}
-          </div>
-        </div>
-      {/if}
-
-      <!-- By Rank -->
-      {#if sortedRanks.length > 0}
-        <div
-          class="rounded border border-exo-medium-gray/30 bg-exo-black/30 p-4 space-y-4"
-        >
-          <h2
-            class="text-sm font-mono uppercase tracking-wider text-exo-light-gray"
-          >
-            By Rank
-          </h2>
-          <div class="grid grid-cols-1 md:grid-cols-2 lg:grid-cols-3 gap-4">
-            {#each sortedRanks as rank}
-              {@const rankStats = stats.byRank[rank]}
-              {@const rankPhases = parsePhases(rankStats.byCategory)}
-              <div
-                class="rounded border border-exo-medium-gray/20 bg-exo-dark-gray/60 p-3 space-y-3"
-              >
-                <div class="text-sm font-mono text-exo-yellow">
-                  Rank {rank}
-                </div>
-                <div class="space-y-2">
-                  {#each rankPhases as phase}
-                    <div class="space-y-1">
-                      <div class="flex items-center justify-between text-xs">
-                        <span class="font-mono text-exo-light-gray"
-                          >{phase.name}</span
-                        >
-                        <span class="font-mono text-white">
-                          {formatDuration(phase.totalUs)}
-                          <span class="text-exo-light-gray/50 ml-1">
-                            ({phase.stepCount}x)
-                          </span>
-                        </span>
-                      </div>
-                      {#if phase.subcategories.length > 0}
-                        <div class="pl-2 space-y-0.5">
-                          {#each phase.subcategories as subcat}
-                            {@const pct = formatPercentage(
-                              subcat.stats.totalUs,
-                              phase.totalUs,
-                            )}
-                            {@const perStep =
-                              subcat.stats.totalUs / phase.stepCount}
-                            <div
-                              class="flex items-center justify-between text-[10px] font-mono"
-                            >
-                              <span class="text-exo-light-gray/70"
-                                >{subcat.name}</span
-                              >
-                              <span class="text-exo-light-gray">
-                                {formatDuration(subcat.stats.totalUs)}
-                                <span class="text-exo-light-gray/50"
-                                  >({pct})</span
-                                >
-                                <span class="text-exo-light-gray/30 ml-1"
-                                  >{formatDuration(perStep)}/step</span
-                                >
-                              </span>
-                            </div>
-                          {/each}
-                        </div>
-                      {/if}
-                    </div>
-                  {/each}
-                </div>
-              </div>
-            {/each}
-          </div>
-        </div>
-      {/if}
-    {/if}
-  </div>
-</div>

flake.lock

@@ -21,9 +21,7 @@
           "nixpkgs"
         ],
         "purescript-overlay": "purescript-overlay",
-        "pyproject-nix": [
-          "pyproject-nix"
-        ]
+        "pyproject-nix": "pyproject-nix"
       },
       "locked": {
         "lastModified": 1765953015,
@@ -151,44 +149,19 @@
         "type": "github"
       }
     },
-    "pyproject-build-systems": {
-      "inputs": {
-        "nixpkgs": [
-          "nixpkgs"
-        ],
-        "pyproject-nix": [
-          "pyproject-nix"
-        ],
-        "uv2nix": [
-          "uv2nix"
-        ]
-      },
-      "locked": {
-        "lastModified": 1763662255,
-        "narHash": "sha256-4bocaOyLa3AfiS8KrWjZQYu+IAta05u3gYZzZ6zXbT0=",
-        "owner": "pyproject-nix",
-        "repo": "build-system-pkgs",
-        "rev": "042904167604c681a090c07eb6967b4dd4dae88c",
-        "type": "github"
-      },
-      "original": {
-        "owner": "pyproject-nix",
-        "repo": "build-system-pkgs",
-        "type": "github"
-      }
-    },
     "pyproject-nix": {
       "inputs": {
         "nixpkgs": [
+          "dream2nix",
           "nixpkgs"
         ]
       },
       "locked": {
-        "lastModified": 1764134915,
-        "narHash": "sha256-xaKvtPx6YAnA3HQVp5LwyYG1MaN4LLehpQI8xEdBvBY=",
+        "lastModified": 1763017646,
+        "narHash": "sha256-Z+R2lveIp6Skn1VPH3taQIuMhABg1IizJd8oVdmdHsQ=",
         "owner": "pyproject-nix",
         "repo": "pyproject.nix",
-        "rev": "2c8df1383b32e5443c921f61224b198a2282a657",
+        "rev": "47bd6f296502842643078d66128f7b5e5370790c",
         "type": "github"
       },
       "original": {
@@ -205,10 +178,7 @@
         "flake-parts": "flake-parts",
         "nixpkgs": "nixpkgs",
         "nixpkgs-swift": "nixpkgs-swift",
-        "pyproject-build-systems": "pyproject-build-systems",
-        "pyproject-nix": "pyproject-nix",
-        "treefmt-nix": "treefmt-nix",
-        "uv2nix": "uv2nix"
+        "treefmt-nix": "treefmt-nix"
       }
     },
     "rust-analyzer-src": {
@@ -269,29 +239,6 @@
         "repo": "treefmt-nix",
         "type": "github"
       }
-    },
-    "uv2nix": {
-      "inputs": {
-        "nixpkgs": [
-          "nixpkgs"
-        ],
-        "pyproject-nix": [
-          "pyproject-nix"
-        ]
-      },
-      "locked": {
-        "lastModified": 1767701098,
-        "narHash": "sha256-CJhKZnWb3gumR9oTRjFvCg/6lYTGbZRU7xtvcyWIRwU=",
-        "owner": "pyproject-nix",
-        "repo": "uv2nix",
-        "rev": "9d357f0d2ce6f5f35ec7959d7e704452352eb4da",
-        "type": "github"
-      },
-      "original": {
-        "owner": "pyproject-nix",
-        "repo": "uv2nix",
-        "type": "github"
-      }
     }
   },
   "root": "root",

flake.nix

@@ -24,26 +24,6 @@
     dream2nix = {
       url = "github:nix-community/dream2nix";
       inputs.nixpkgs.follows = "nixpkgs";
-      inputs.pyproject-nix.follows = "pyproject-nix";
-    };
-
-    # Python packaging with uv2nix
-    pyproject-nix = {
-      url = "github:pyproject-nix/pyproject.nix";
-      inputs.nixpkgs.follows = "nixpkgs";
-    };
-
-    uv2nix = {
-      url = "github:pyproject-nix/uv2nix";
-      inputs.pyproject-nix.follows = "pyproject-nix";
-      inputs.nixpkgs.follows = "nixpkgs";
-    };
-
-    pyproject-build-systems = {
-      url = "github:pyproject-nix/build-system-pkgs";
-      inputs.pyproject-nix.follows = "pyproject-nix";
-      inputs.uv2nix.follows = "uv2nix";
-      inputs.nixpkgs.follows = "nixpkgs";
     };
 
     # Pinned nixpkgs for swift-format (swift is broken on x86_64-linux in newer nixpkgs)
@@ -68,8 +48,6 @@
         inputs.treefmt-nix.flakeModule
         ./dashboard/parts.nix
         ./rust/parts.nix
-        ./python/parts.nix
-        ./resources/parts.nix
       ];
 
       perSystem =
@@ -80,11 +58,6 @@
           pkgsSwift = import inputs.nixpkgs-swift { inherit system; };
         in
         {
-          # Allow unfree for metal-toolchain (needed for Darwin Metal packages)
-          _module.args.pkgs = import inputs.nixpkgs {
-            inherit system;
-            config.allowUnfreePredicate = pkg: (pkg.pname or "") == "metal-toolchain";
-          };
           treefmt = {
             projectRootFile = "flake.nix";
             programs = {
@@ -106,24 +79,14 @@
                 enable = true;
                 package = pkgsSwift.swiftPackages.swift-format;
               };
-              shfmt.enable = true;
             };
           };
 
-          packages = lib.optionalAttrs pkgs.stdenv.hostPlatform.isDarwin (
-            let
-              uvLock = builtins.fromTOML (builtins.readFile ./uv.lock);
-              mlxPackage = builtins.head (builtins.filter (p: p.name == "mlx") uvLock.package);
-              uvLockMlxVersion = mlxPackage.version;
-            in
-            {
-              metal-toolchain = pkgs.callPackage ./nix/metal-toolchain.nix { };
-              mlx = pkgs.callPackage ./nix/mlx.nix {
-                metal-toolchain = self'.packages.metal-toolchain;
-                inherit uvLockMlxVersion;
-              };
-            }
-          );
+          checks.lint = pkgs.runCommand "lint-check" { } ''
+            export RUFF_CACHE_DIR="$TMPDIR/ruff-cache"
+            ${pkgs.ruff}/bin/ruff check ${inputs.self}/
+            touch $out
+          '';
 
           devShells.default = with pkgs; pkgs.mkShell {
             inputsFrom = [ self'.checks.cargo-build ];

justfile

@@ -1,7 +1,7 @@
 export NIX_CONFIG := "extra-experimental-features = nix-command flakes"
 
 fmt:
-    treefmt || nix fmt
+    nix fmt
 
 lint:
     uv run ruff check --fix

nix/darwin-build-fixes.patch

@@ -1,79 +0,0 @@
-diff --git a/CMakeLists.txt b/CMakeLists.txt
-index 0ed30932..d8528132 100644
---- a/CMakeLists.txt
-+++ b/CMakeLists.txt
-@@ -177,11 +177,7 @@ if(MLX_BUILD_METAL)
-     add_compile_definitions(MLX_METAL_DEBUG)
-   endif()
-
--  # Throw an error if xcrun not found
--  execute_process(
--    COMMAND zsh "-c" "/usr/bin/xcrun -sdk macosx --show-sdk-version"
--    OUTPUT_VARIABLE MACOS_SDK_VERSION
--    OUTPUT_STRIP_TRAILING_WHITESPACE COMMAND_ERROR_IS_FATAL ANY)
-+  set(MACOS_SDK_VERSION @sdkVersion@)
-
-   if(${MACOS_SDK_VERSION} LESS 14.0)
-     message(
-@@ -199,11 +195,8 @@ if(MLX_BUILD_METAL)
-     endif()
-     set(XCRUN_FLAGS "-mmacosx-version-min=${CMAKE_OSX_DEPLOYMENT_TARGET}")
-   endif()
--  execute_process(
--    COMMAND
--      zsh "-c"
--      "echo \"__METAL_VERSION__\" | xcrun -sdk macosx metal ${XCRUN_FLAGS} -E -x metal -P - | tail -1 | tr -d '\n'"
--    OUTPUT_VARIABLE MLX_METAL_VERSION COMMAND_ERROR_IS_FATAL ANY)
-+  set(
-+    MLX_METAL_VERSION @metalVersion@)
-   FetchContent_Declare(metal_cpp URL ${METAL_CPP_URL})
-   FetchContent_MakeAvailable(metal_cpp)
-   target_include_directories(
-diff --git a/cmake/extension.cmake b/cmake/extension.cmake
-index 13db804a..5b385132 100644
---- a/cmake/extension.cmake
-+++ b/cmake/extension.cmake
-@@ -36,7 +36,7 @@ macro(mlx_build_metallib)
-   add_custom_command(
-     OUTPUT ${MTLLIB_BUILD_TARGET}
-     COMMAND
--      xcrun -sdk macosx metal
-+      metal -fmodules-cache-path=${CMAKE_BINARY_DIR}/metal-cache
-       "$<LIST:TRANSFORM,${MTLLIB_INCLUDE_DIRS},PREPEND,-I>"
-       ${MTLLIB_COMPILE_OPTIONS} ${MTLLIB_SOURCES} -o ${MTLLIB_BUILD_TARGET}
-     DEPENDS ${MTLLIB_DEPS} ${MTLLIB_SOURCES}
-diff --git a/mlx/backend/metal/kernels/CMakeLists.txt b/mlx/backend/metal/kernels/CMakeLists.txt
-index 262b0495..5c7446ad 100644
---- a/mlx/backend/metal/kernels/CMakeLists.txt
-+++ b/mlx/backend/metal/kernels/CMakeLists.txt
-@@ -29,7 +29,7 @@ function(build_kernel_base TARGET SRCFILE DEPS)
-                     "-mmacosx-version-min=${CMAKE_OSX_DEPLOYMENT_TARGET}")
-   endif()
-   add_custom_command(
--    COMMAND xcrun -sdk macosx metal ${METAL_FLAGS} -c ${SRCFILE}
-+    COMMAND metal -fmodules-cache-path=${CMAKE_BINARY_DIR}/metal-cache ${METAL_FLAGS} -c ${SRCFILE}
-             -I${PROJECT_SOURCE_DIR} -o ${TARGET}.air
-     DEPENDS ${SRCFILE} ${DEPS} ${BASE_HEADERS}
-     OUTPUT ${TARGET}.air
-@@ -170,7 +170,7 @@ endif()
-
- add_custom_command(
-   OUTPUT ${MLX_METAL_PATH}/mlx.metallib
--  COMMAND xcrun -sdk macosx metallib ${KERNEL_AIR} -o
-+  COMMAND metallib ${KERNEL_AIR} -o
-           ${MLX_METAL_PATH}/mlx.metallib
-   DEPENDS ${KERNEL_AIR}
-   COMMENT "Building mlx.metallib"
-diff --git a/mlx/backend/metal/make_compiled_preamble.sh b/mlx/backend/metal/make_compiled_preamble.sh
-index bb55ed3a..94ea7dd7 100644
---- a/mlx/backend/metal/make_compiled_preamble.sh
-+++ b/mlx/backend/metal/make_compiled_preamble.sh
-@@ -31,7 +31,7 @@ OUTPUT_FILE=${OUTPUT_DIR}/${SRC_NAME}.cpp
- mkdir -p "$OUTPUT_DIR"
-
- # Use the metal compiler to get a list of headers (with depth)
--CCC="xcrun -sdk macosx metal -x metal"
-+CCC="metal -x metal -fmodules-cache-path=${OUTPUT_DIR}/metal-cache"
- HDRS=$( $CCC -I"$SRC_DIR" -I"$JIT_INCLUDES" -DMLX_METAL_JIT -E -P -CC -C -H "$INPUT_FILE" $CFLAGS -w 2>&1 1>/dev/null )
-
- # Remove any included system frameworks (for MetalPerformancePrimitive headers)

nix/metal-toolchain.nix

@@ -1,56 +0,0 @@
-{ lib, stdenvNoCC, requireFile, nix }:
-
-let
-  narFile = requireFile {
-    name = "metal-toolchain-17C48.nar";
-    message = ''
-      The Metal Toolchain NAR must be available.
-
-      If you have cachix configured for exo.cachix.org, this should be automatic.
-
-      Otherwise:
-        1. Install Xcode 26+ from the App Store
-        2. Run: xcodebuild -downloadComponent MetalToolchain
-        3. Export the toolchain:
-           hdiutil attach "$(find /System/Library/AssetsV2/com_apple_MobileAsset_MetalToolchain -name '*.dmg' | head -1)" -mountpoint /tmp/metal-dmg
-           cp -R /tmp/metal-dmg/Metal.xctoolchain /tmp/metal-export
-           hdiutil detach /tmp/metal-dmg
-        4. Create NAR and add to store:
-           nix nar pack /tmp/metal-export > /tmp/metal-toolchain-17C48.nar
-           nix store add --mode flat /tmp/metal-toolchain-17C48.nar
-    '';
-    hash = "sha256-ayR5mXN4sZAddwKEG2OszGRF93k9ZFc7H0yi2xbylQw=";
-  };
-in
-stdenvNoCC.mkDerivation {
-  pname = "metal-toolchain";
-  version = "17C48";
-
-  dontUnpack = true;
-  dontBuild = true;
-  dontFixup = true;
-
-  nativeBuildInputs = [ nix ];
-
-  installPhase = ''
-    runHook preInstall
-
-    nix-store --restore $out < ${narFile}
-
-    # Create bin directory with symlinks for PATH
-    mkdir -p $out/bin
-    ln -s $out/usr/bin/metal $out/bin/metal
-    ln -s $out/usr/bin/metallib $out/bin/metallib
-
-    runHook postInstall
-  '';
-
-  # Metal language version for CMake (from: echo __METAL_VERSION__ | metal -E -x metal -P -)
-  passthru.metalVersion = "400";
-
-  meta = {
-    description = "Apple Metal compiler toolchain";
-    platforms = [ "aarch64-darwin" ];
-    license = lib.licenses.unfree;
-  };
-}

nix/mlx.nix

@@ -1,158 +0,0 @@
-{ stdenv
-, lib
-, fetchFromGitHub
-, replaceVars
-, fetchzip
-, cmake
-, nlohmann_json
-, apple-sdk_26
-, metal-toolchain
-, runCommand
-, fmt
-, python313Packages
-, uvLockMlxVersion
-}:
-
-assert stdenv.isDarwin;
-
-let
-  python = python313Packages.python;
-
-  # Static dependencies included directly during compilation
-  gguf-tools = fetchFromGitHub {
-    owner = "antirez";
-    repo = "gguf-tools";
-    rev = "8fa6eb65236618e28fd7710a0fba565f7faa1848";
-    hash = "sha256-15FvyPOFqTOr5vdWQoPnZz+mYH919++EtghjozDlnSA=";
-  };
-
-  metal_cpp = fetchzip {
-    url = "https://developer.apple.com/metal/cpp/files/metal-cpp_26.zip";
-    hash = "sha256-7n2eI2lw/S+Us6l7YPAATKwcIbRRpaQ8VmES7S8ZjY8=";
-  };
-
-  nanobind = fetchFromGitHub {
-    owner = "wjakob";
-    repo = "nanobind";
-    rev = "v2.10.2";
-    hash = "sha256-io44YhN+VpfHFWyvvLWSanRgbzA0whK8WlDNRi3hahU=";
-    fetchSubmodules = true;
-  };
-
-  mlx = stdenv.mkDerivation rec {
-    pname = "mlx";
-    version = let v = "0.30.4"; in
-      assert v == uvLockMlxVersion || throw "MLX version mismatch: nix/mlx.nix has ${v} but uv.lock has ${uvLockMlxVersion}. Update both the version and hash in nix/mlx.nix.";
-      v;
-    pyproject = true;
-
-    src = fetchFromGitHub {
-      owner = "ml-explore";
-      repo = "mlx";
-      tag = "v${version}";
-      hash = "sha256-OJk6jPlbaSlsUdk3ADz3tWcRzTWXRof3/q8Soe1AO6w=";
-    };
-
-    patches = [
-      (replaceVars ./darwin-build-fixes.patch {
-        sdkVersion = apple-sdk_26.version;
-        metalVersion = metal-toolchain.metalVersion;
-      })
-    ];
-
-    postPatch = ''
-      substituteInPlace mlx/backend/cpu/jit_compiler.cpp \
-        --replace-fail "g++" "$CXX"
-    '';
-
-    dontUseCmakeConfigure = true;
-
-    enableParallelBuilding = true;
-
-    # Allows multiple cores to be used in Python builds.
-    postUnpack = ''
-      export MAKEFLAGS+="''${enableParallelBuilding:+-j$NIX_BUILD_CORES}"
-    '';
-
-    # Updates the wrong fetcher rev attribute
-    passthru.skipBulkUpdate = true;
-
-    env = {
-      DEV_RELEASE = 1;
-      CMAKE_ARGS = toString [
-        (lib.cmakeBool "USE_SYSTEM_FMT" true)
-        (lib.cmakeOptionType "filepath" "FETCHCONTENT_SOURCE_DIR_GGUFLIB" "${gguf-tools}")
-        (lib.cmakeOptionType "filepath" "FETCHCONTENT_SOURCE_DIR_JSON" "${nlohmann_json.src}")
-        (lib.cmakeOptionType "filepath" "FETCHCONTENT_SOURCE_DIR_NANOBIND" "${nanobind}")
-        (lib.cmakeBool "FETCHCONTENT_FULLY_DISCONNECTED" true)
-        (lib.cmakeBool "MLX_BUILD_METAL" true)
-        (lib.cmakeOptionType "filepath" "FETCHCONTENT_SOURCE_DIR_METAL_CPP" "${metal_cpp}")
-        (lib.cmakeOptionType "string" "CMAKE_OSX_DEPLOYMENT_TARGET" "${apple-sdk_26.version}")
-        (lib.cmakeOptionType "filepath" "CMAKE_OSX_SYSROOT" "${apple-sdk_26.passthru.sdkroot}")
-      ];
-      SDKROOT = apple-sdk_26.passthru.sdkroot;
-      MACOSX_DEPLOYMENT_TARGET = apple-sdk_26.version;
-    };
-
-    build-system = [
-      python313Packages.setuptools
-    ];
-
-    nativeBuildInputs = [
-      cmake
-      metal-toolchain
-      python313Packages.pypaBuildHook
-      python313Packages.pypaInstallHook
-      python313Packages.setuptools
-      python313Packages.typing-extensions
-      python313Packages.wheel
-      python313Packages.cmake
-      python313Packages.ninja
-    ];
-
-    buildInputs = [
-      fmt
-      gguf-tools
-      python313Packages.nanobind
-      python313Packages.pybind11
-      apple-sdk_26
-    ];
-
-    # Tests require Metal GPU access which isn't available in the Nix sandbox.
-    # To run tests, build with: nix build --option sandbox false .#mlx.passthru.tests.mlxTest
-    doCheck = false;
-
-    pythonImportsCheck = [ "mlx" ];
-
-    passthru.tests = {
-      # Runs example scripts to verify MLX works. Requires --option sandbox false
-      # since Metal GPU access is needed.
-      mlxTest =
-        runCommand "run-mlx-examples"
-          {
-            buildInputs = [ mlx ];
-            nativeBuildInputs = [ python ];
-          }
-          ''
-            cp ${src}/examples/python/logistic_regression.py .
-            ${python.interpreter} logistic_regression.py
-            rm logistic_regression.py
-
-            cp ${src}/examples/python/linear_regression.py .
-            ${python.interpreter} linear_regression.py
-            rm linear_regression.py
-
-            touch $out
-          '';
-    };
-
-    meta = {
-      homepage = "https://github.com/ml-explore/mlx";
-      description = "Array framework for Apple silicon";
-      changelog = "https://github.com/ml-explore/mlx/releases/tag/${src.tag}";
-      license = lib.licenses.mit;
-      platforms = [ "aarch64-darwin" ];
-    };
-  };
-in
-mlx

packaging/pyinstaller/exo.spec

@@ -10,7 +10,6 @@ PROJECT_ROOT = Path.cwd()
 SOURCE_ROOT = PROJECT_ROOT / "src"
 ENTRYPOINT = SOURCE_ROOT / "exo" / "__main__.py"
 DASHBOARD_DIR = PROJECT_ROOT / "dashboard" / "build"
-RESOURCES_DIR = PROJECT_ROOT / "resources"
 EXO_SHARED_MODELS_DIR = SOURCE_ROOT / "exo" / "shared" / "models"
 
 if not ENTRYPOINT.is_file():
@@ -19,9 +18,6 @@ if not ENTRYPOINT.is_file():
 if not DASHBOARD_DIR.is_dir():
     raise SystemExit(f"Dashboard assets are missing: {DASHBOARD_DIR}")
 
-if not RESOURCES_DIR.is_dir():
-    raise SystemExit(f"Resource assets are missing: {RESOURCES_DIR}")
-
 if not EXO_SHARED_MODELS_DIR.is_dir():
     raise SystemExit(f"Shared model assets are missing: {EXO_SHARED_MODELS_DIR}")
 
@@ -62,7 +58,6 @@ HIDDEN_IMPORTS = sorted(
 
 DATAS: list[tuple[str, str]] = [
     (str(DASHBOARD_DIR), "dashboard"),
-    (str(RESOURCES_DIR), "resources"),
     (str(MLX_LIB_DIR), "mlx/lib"),
     (str(EXO_SHARED_MODELS_DIR), "exo/shared/models"),
 ]

pyproject.toml

@@ -13,13 +13,14 @@ dependencies = [
     "filelock>=3.18.0",
     "rustworkx>=0.17.1",
     "huggingface-hub>=0.33.4",
+    "typer", # for huggingface-cli
     "psutil>=7.0.0",
     "loguru>=0.7.3",
     "exo_pyo3_bindings", # rust bindings
     "anyio==4.11.0",
-    "mlx==0.30.4; sys_platform == 'darwin'",
-    "mlx[cpu]==0.30.4; sys_platform == 'linux'",
-    "mlx-lm",
+    "mlx==0.30.3; sys_platform == 'darwin'",
+    "mlx[cpu]==0.30.3; sys_platform == 'linux'",
+    "mlx-lm==0.30.5",
     "tiktoken>=0.12.0", # required for kimi k2 tokenizer
     "hypercorn>=0.18.0",
     "openai-harmony>=0.0.8",
@@ -34,6 +35,7 @@ dependencies = [
 exo-master = "exo.master.main:main"
 exo-worker = "exo.worker.main:main"
 exo = "exo.main:main"
+exo-eval = "bench.exo_eval:main"
 
 # dependencies only required for development
 [dependency-groups]
@@ -51,6 +53,9 @@ dev = [
 # cuda = [
 #     "mlx[cuda]==0.26.3",
 # ]
+eval = [
+    "lm_eval[api]",
+]
 
 ###
 # workspace configuration
@@ -63,10 +68,10 @@ members = [
 
 [tool.uv.sources]
 exo_pyo3_bindings = { workspace = true }
-mlx-lm = { git = "https://github.com/ml-explore/mlx-lm", branch = "main" }
 # Uncomment to use local mlx/mlx-lm development versions:
 # mlx = { path = "/Users/Shared/mlx", editable=true }
 # mlx-lm = { path = "/Users/Shared/mlx-lm", editable=true }
+mlx-lm = { git = "https://github.com/davidmcc73/mlx-lm.git", branch = "main" }
 
 [build-system]
 requires = ["uv_build>=0.8.9,<0.9.0"]

python/parts.nix

@@ -1,95 +0,0 @@
-{ inputs, ... }:
-{
-  perSystem =
-    { config, self', pkgs, lib, system, ... }:
-    let
-      # Load workspace from uv.lock
-      workspace = inputs.uv2nix.lib.workspace.loadWorkspace {
-        workspaceRoot = inputs.self;
-      };
-
-      # Create overlay from workspace
-      # Use wheels from PyPI for most packages; we override mlx with our pure Nix Metal build
-      overlay = workspace.mkPyprojectOverlay { sourcePreference = "wheel"; };
-
-      # Override overlay to inject Nix-built components
-      exoOverlay = final: prev: {
-        # Replace workspace exo_pyo3_bindings with Nix-built wheel
-        exo-pyo3-bindings = pkgs.stdenv.mkDerivation {
-          pname = "exo-pyo3-bindings";
-          version = "0.1.0";
-          src = self'.packages.exo_pyo3_bindings;
-          # Install from pre-built wheel
-          nativeBuildInputs = [ final.pyprojectWheelHook ];
-          dontStrip = true;
-        };
-      };
-
-      python = pkgs.python313;
-
-      # Overlay to provide build systems and custom packages
-      buildSystemsOverlay = final: prev: {
-        # Use our pure Nix-built MLX with Metal support
-        mlx = self'.packages.mlx;
-
-        # mlx-lm is a git dependency that needs setuptools
-        mlx-lm = prev.mlx-lm.overrideAttrs (old: {
-          nativeBuildInputs = (old.nativeBuildInputs or [ ]) ++ [
-            final.setuptools
-          ];
-        });
-      };
-
-      pythonSet = (pkgs.callPackage inputs.pyproject-nix.build.packages {
-        inherit python;
-      }).overrideScope (
-        lib.composeManyExtensions [
-          inputs.pyproject-build-systems.overlays.default
-          overlay
-          exoOverlay
-          buildSystemsOverlay
-        ]
-      );
-      exoVenv = pythonSet.mkVirtualEnv "exo-env" workspace.deps.default;
-
-      # Virtual environment with dev dependencies for testing
-      testVenv = pythonSet.mkVirtualEnv "exo-test-env" (
-        workspace.deps.default // {
-          exo = [ "dev" ]; # Include pytest, pytest-asyncio, pytest-env
-        }
-      );
-
-      exoPackage = pkgs.runCommand "exo"
-        {
-          nativeBuildInputs = [ pkgs.makeWrapper ];
-        }
-        ''
-          mkdir -p $out/bin
-
-          # Create wrapper scripts
-          for script in exo exo-master exo-worker; do
-            makeWrapper ${exoVenv}/bin/$script $out/bin/$script \
-              --set EXO_DASHBOARD_DIR ${self'.packages.dashboard} \
-              --set EXO_RESOURCES_DIR ${self'.packages.resources} \
-              ${lib.optionalString pkgs.stdenv.isDarwin "--prefix PATH : ${pkgs.macmon}/bin"}
-          done
-        '';
-    in
-    {
-      # Python package only available on macOS (requires MLX/Metal)
-      packages = lib.optionalAttrs pkgs.stdenv.hostPlatform.isDarwin {
-        exo = exoPackage;
-        # Test environment for running pytest outside of Nix sandbox (needs GPU access)
-        exo-test-env = testVenv;
-      };
-
-      checks = {
-        # Ruff linting (works on all platforms)
-        lint = pkgs.runCommand "ruff-lint" { } ''
-          export RUFF_CACHE_DIR="$TMPDIR/ruff-cache"
-          ${pkgs.ruff}/bin/ruff check ${inputs.self}/
-          touch $out
-        '';
-      };
-    };
-}

resources/image_model_cards/exolabs--FLUX.1-Krea-dev-4bit.toml

@@ -1,45 +0,0 @@
-model_id = "exolabs/FLUX.1-Krea-dev-4bit"
-n_layers = 57
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 15475325472
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0
-
-[[components]]
-component_name = "text_encoder_2"
-component_path = "text_encoder_2/"
-n_layers = 24
-can_shard = false
-safetensors_index_filename = "model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 9524621312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 57
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 5950704160
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-Krea-dev-8bit.toml

@@ -1,45 +0,0 @@
-model_id = "exolabs/FLUX.1-Krea-dev-8bit"
-n_layers = 57
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 21426029632
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0
-
-[[components]]
-component_name = "text_encoder_2"
-component_path = "text_encoder_2/"
-n_layers = 24
-can_shard = false
-safetensors_index_filename = "model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 9524621312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 57
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 11901408320
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-Krea-dev.toml

@@ -1,45 +0,0 @@
-model_id = "exolabs/FLUX.1-Krea-dev"
-n_layers = 57
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 33327437952
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0
-
-[[components]]
-component_name = "text_encoder_2"
-component_path = "text_encoder_2/"
-n_layers = 24
-can_shard = false
-safetensors_index_filename = "model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 9524621312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 57
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 23802816640
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-dev-4bit.toml

@@ -1,45 +0,0 @@
-model_id = "exolabs/FLUX.1-dev-4bit"
-n_layers = 57
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 15475325472
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0
-
-[[components]]
-component_name = "text_encoder_2"
-component_path = "text_encoder_2/"
-n_layers = 24
-can_shard = false
-safetensors_index_filename = "model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 9524621312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 57
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 5950704160
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-dev-8bit.toml

@@ -1,45 +0,0 @@
-model_id = "exolabs/FLUX.1-dev-8bit"
-n_layers = 57
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 21426029632
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0
-
-[[components]]
-component_name = "text_encoder_2"
-component_path = "text_encoder_2/"
-n_layers = 24
-can_shard = false
-safetensors_index_filename = "model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 9524621312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 57
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 11901408320
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-dev.toml

@@ -1,45 +0,0 @@
-model_id = "exolabs/FLUX.1-dev"
-n_layers = 57
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 33327437952
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0
-
-[[components]]
-component_name = "text_encoder_2"
-component_path = "text_encoder_2/"
-n_layers = 24
-can_shard = false
-safetensors_index_filename = "model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 9524621312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 57
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 23802816640
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-schnell-4bit.toml

@@ -1,45 +0,0 @@
-model_id = "exolabs/FLUX.1-schnell-4bit"
-n_layers = 57
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 15470210592
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0
-
-[[components]]
-component_name = "text_encoder_2"
-component_path = "text_encoder_2/"
-n_layers = 24
-can_shard = false
-safetensors_index_filename = "model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 9524621312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 57
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 5945589280
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-schnell-8bit.toml

@@ -1,45 +0,0 @@
-model_id = "exolabs/FLUX.1-schnell-8bit"
-n_layers = 57
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 21415799872
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0
-
-[[components]]
-component_name = "text_encoder_2"
-component_path = "text_encoder_2/"
-n_layers = 24
-can_shard = false
-safetensors_index_filename = "model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 9524621312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 57
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 11891178560
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-schnell.toml

@@ -1,45 +0,0 @@
-model_id = "exolabs/FLUX.1-schnell"
-n_layers = 57
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 33306978432
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0
-
-[[components]]
-component_name = "text_encoder_2"
-component_path = "text_encoder_2/"
-n_layers = 24
-can_shard = false
-safetensors_index_filename = "model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 9524621312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 57
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 23782357120
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image-4bit.toml

@@ -1,35 +0,0 @@
-model_id = "exolabs/Qwen-Image-4bit"
-n_layers = 60
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 26799533856
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 16584333312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 60
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 10215200544
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image-8bit.toml

@@ -1,35 +0,0 @@
-model_id = "exolabs/Qwen-Image-8bit"
-n_layers = 60
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 37014734400
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 16584333312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 60
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 20430401088
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image-Edit-2509-4bit.toml

@@ -1,35 +0,0 @@
-model_id = "exolabs/Qwen-Image-Edit-2509-4bit"
-n_layers = 60
-hidden_size = 1
-supports_tensor = false
-tasks = ["ImageToImage"]
-
-[storage_size]
-in_bytes = 26799533856
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 16584333312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 60
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 10215200544
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image-Edit-2509-8bit.toml

@@ -1,35 +0,0 @@
-model_id = "exolabs/Qwen-Image-Edit-2509-8bit"
-n_layers = 60
-hidden_size = 1
-supports_tensor = false
-tasks = ["ImageToImage"]
-
-[storage_size]
-in_bytes = 37014734400
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 16584333312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 60
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 20430401088
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image-Edit-2509.toml

@@ -1,35 +0,0 @@
-model_id = "exolabs/Qwen-Image-Edit-2509"
-n_layers = 60
-hidden_size = 1
-supports_tensor = false
-tasks = ["ImageToImage"]
-
-[storage_size]
-in_bytes = 57445135488
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 16584333312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 60
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 40860802176
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image.toml

@@ -1,35 +0,0 @@
-model_id = "exolabs/Qwen-Image"
-n_layers = 60
-hidden_size = 1
-supports_tensor = false
-tasks = ["TextToImage"]
-
-[storage_size]
-in_bytes = 57445135488
-
-[[components]]
-component_name = "text_encoder"
-component_path = "text_encoder/"
-n_layers = 12
-can_shard = false
-
-[components.storage_size]
-in_bytes = 16584333312
-
-[[components]]
-component_name = "transformer"
-component_path = "transformer/"
-n_layers = 60
-can_shard = true
-safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
-
-[components.storage_size]
-in_bytes = 40860802176
-
-[[components]]
-component_name = "vae"
-component_path = "vae/"
-can_shard = false
-
-[components.storage_size]
-in_bytes = 0

resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/DeepSeek-V3.1-4bit"
-n_layers = 61
-hidden_size = 7168
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "deepseek"
-quantization = "4bit"
-base_model = "DeepSeek V3.1"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 405874409472

resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/DeepSeek-V3.1-8bit"
-n_layers = 61
-hidden_size = 7168
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "deepseek"
-quantization = "8bit"
-base_model = "DeepSeek V3.1"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 765577920512

resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-4.5-Air-8bit"
-n_layers = 46
-hidden_size = 4096
-supports_tensor = false
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "8bit"
-base_model = "GLM 4.5 Air"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 122406567936

resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-4.5-Air-bf16"
-n_layers = 46
-hidden_size = 4096
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "bf16"
-base_model = "GLM 4.5 Air"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 229780750336

resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-4.7-4bit"
-n_layers = 91
-hidden_size = 5120
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "4bit"
-base_model = "GLM 4.7"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 198556925568

resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-4.7-6bit"
-n_layers = 91
-hidden_size = 5120
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "6bit"
-base_model = "GLM 4.7"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 286737579648

resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-4.7-8bit-gs32"
-n_layers = 91
-hidden_size = 5120
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "8bit"
-base_model = "GLM 4.7"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 396963397248

resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-4.7-Flash-4bit"
-n_layers = 47
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "4bit"
-base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 19327352832

resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-4.7-Flash-5bit"
-n_layers = 47
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "5bit"
-base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 22548578304

resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-4.7-Flash-6bit"
-n_layers = 47
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "6bit"
-base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 26843545600

resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-4.7-Flash-8bit"
-n_layers = 47
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "8bit"
-base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 34359738368

resources/inference_model_cards/mlx-community--Kimi-K2-Instruct-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Kimi-K2-Instruct-4bit"
-n_layers = 61
-hidden_size = 7168
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "kimi"
-quantization = "4bit"
-base_model = "Kimi K2"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 620622774272

resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Kimi-K2-Thinking"
-n_layers = 61
-hidden_size = 7168
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "kimi"
-quantization = ""
-base_model = "Kimi K2"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 706522120192

resources/inference_model_cards/mlx-community--Kimi-K2.5.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Kimi-K2.5"
-n_layers = 61
-hidden_size = 7168
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "kimi"
-quantization = ""
-base_model = "Kimi K2.5"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 662498705408

resources/inference_model_cards/mlx-community--Llama-3.2-1B-Instruct-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Llama-3.2-1B-Instruct-4bit"
-n_layers = 16
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "4bit"
-base_model = "Llama 3.2 1B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 729808896

resources/inference_model_cards/mlx-community--Llama-3.2-3B-Instruct-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Llama-3.2-3B-Instruct-4bit"
-n_layers = 28
-hidden_size = 3072
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "4bit"
-base_model = "Llama 3.2 3B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 1863319552

resources/inference_model_cards/mlx-community--Llama-3.2-3B-Instruct-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Llama-3.2-3B-Instruct-8bit"
-n_layers = 28
-hidden_size = 3072
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "8bit"
-base_model = "Llama 3.2 3B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 3501195264

resources/inference_model_cards/mlx-community--Llama-3.3-70B-Instruct-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Llama-3.3-70B-Instruct-4bit"
-n_layers = 80
-hidden_size = 8192
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "4bit"
-base_model = "Llama 3.3 70B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 40652242944

resources/inference_model_cards/mlx-community--Llama-3.3-70B-Instruct-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Llama-3.3-70B-Instruct-8bit"
-n_layers = 80
-hidden_size = 8192
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "8bit"
-base_model = "Llama 3.3 70B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 76799803392

resources/inference_model_cards/mlx-community--Meta-Llama-3.1-70B-Instruct-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Meta-Llama-3.1-70B-Instruct-4bit"
-n_layers = 80
-hidden_size = 8192
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "4bit"
-base_model = "Llama 3.1 70B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 40652242944

resources/inference_model_cards/mlx-community--Meta-Llama-3.1-8B-Instruct-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Meta-Llama-3.1-8B-Instruct-4bit"
-n_layers = 32
-hidden_size = 4096
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "4bit"
-base_model = "Llama 3.1 8B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 4637851648

resources/inference_model_cards/mlx-community--Meta-Llama-3.1-8B-Instruct-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Meta-Llama-3.1-8B-Instruct-8bit"
-n_layers = 32
-hidden_size = 4096
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "8bit"
-base_model = "Llama 3.1 8B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 8954839040

resources/inference_model_cards/mlx-community--Meta-Llama-3.1-8B-Instruct-bf16.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Meta-Llama-3.1-8B-Instruct-bf16"
-n_layers = 32
-hidden_size = 4096
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "bf16"
-base_model = "Llama 3.1 8B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 16882073600

resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/MiniMax-M2.1-3bit"
-n_layers = 61
-hidden_size = 3072
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "minimax"
-quantization = "3bit"
-base_model = "MiniMax M2.1"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 100086644736

resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/MiniMax-M2.1-8bit"
-n_layers = 61
-hidden_size = 3072
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "minimax"
-quantization = "8bit"
-base_model = "MiniMax M2.1"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 242986745856

resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-0.6B-4bit"
-n_layers = 28
-hidden_size = 1024
-supports_tensor = false
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "4bit"
-base_model = "Qwen3 0.6B"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 342884352

resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-0.6B-8bit"
-n_layers = 28
-hidden_size = 1024
-supports_tensor = false
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "8bit"
-base_model = "Qwen3 0.6B"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 698351616

resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-235B-A22B-Instruct-2507-4bit"
-n_layers = 94
-hidden_size = 4096
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "4bit"
-base_model = "Qwen3 235B"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 141733920768

resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit"
-n_layers = 94
-hidden_size = 4096
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "8bit"
-base_model = "Qwen3 235B"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 268435456000

resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-30B-A3B-4bit"
-n_layers = 48
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "4bit"
-base_model = "Qwen3 30B"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 17612931072

resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-30B-A3B-8bit"
-n_layers = 48
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "8bit"
-base_model = "Qwen3 30B"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 33279705088

resources/inference_model_cards/mlx-community--Qwen3-Coder-480B-A35B-Instruct-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit"
-n_layers = 62
-hidden_size = 6144
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "4bit"
-base_model = "Qwen3 Coder 480B"
-capabilities = ["text", "code"]
-
-[storage_size]
-in_bytes = 289910292480

resources/inference_model_cards/mlx-community--Qwen3-Coder-480B-A35B-Instruct-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-Coder-480B-A35B-Instruct-8bit"
-n_layers = 62
-hidden_size = 6144
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "8bit"
-base_model = "Qwen3 Coder 480B"
-capabilities = ["text", "code"]
-
-[storage_size]
-in_bytes = 579820584960

resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Instruct-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit"
-n_layers = 48
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "4bit"
-base_model = "Qwen3 Next 80B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 46976204800

resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Instruct-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit"
-n_layers = 48
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "8bit"
-base_model = "Qwen3 Next 80B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 88814387200

resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit"
-n_layers = 48
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "4bit"
-base_model = "Qwen3 Next 80B"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 47080074240

resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Qwen3-Next-80B-A3B-Thinking-8bit"
-n_layers = 48
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "qwen"
-quantization = "8bit"
-base_model = "Qwen3 Next 80B"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 88814387200

resources/inference_model_cards/mlx-community--gpt-oss-120b-MXFP4-Q8.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/gpt-oss-120b-MXFP4-Q8"
-n_layers = 36
-hidden_size = 2880
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "gpt-oss"
-quantization = "MXFP4-Q8"
-base_model = "GPT-OSS 120B"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 70652212224

resources/inference_model_cards/mlx-community--gpt-oss-20b-MXFP4-Q8.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/gpt-oss-20b-MXFP4-Q8"
-n_layers = 24
-hidden_size = 2880
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "gpt-oss"
-quantization = "MXFP4-Q8"
-base_model = "GPT-OSS 20B"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 12025908224

resources/inference_model_cards/mlx-community--llama-3.3-70b-instruct-fp16.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/llama-3.3-70b-instruct-fp16"
-n_layers = 80
-hidden_size = 8192
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "fp16"
-base_model = "Llama 3.3 70B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 144383672320

resources/parts.nix

@@ -1,17 +0,0 @@
-{ inputs, ... }:
-{
-  perSystem =
-    { pkgs, lib, ... }:
-    let
-      # Filter source to only include resources directory
-      resourcesSrc = lib.cleanSourceWith {
-        src = inputs.self + "/resources";
-      };
-    in
-    {
-      packages.resources = pkgs.runCommand "exo-resources" { } ''
-        cp -r ${resourcesSrc} $out
-      '';
-    };
-}
-

src/exo/download/coordinator.py

@@ -1,5 +1,4 @@
 import asyncio
-import socket
 from dataclasses import dataclass, field
 from typing import Iterator
 
@@ -61,37 +60,10 @@ class DownloadCoordinator:
 
     async def run(self) -> None:
         logger.info("Starting DownloadCoordinator")
-        self._test_internet_connection()
         async with self._tg as tg:
             tg.start_soon(self._command_processor)
             tg.start_soon(self._forward_events)
             tg.start_soon(self._emit_existing_download_progress)
-            tg.start_soon(self._check_internet_connection)
-
-    def _test_internet_connection(self) -> None:
-        try:
-            socket.create_connection(("1.1.1.1", 443), timeout=3).close()
-            self.shard_downloader.set_internet_connection(True)
-        except OSError:
-            self.shard_downloader.set_internet_connection(False)
-        logger.debug(
-            f"Internet connectivity: {self.shard_downloader.internet_connection}"
-        )
-
-    async def _check_internet_connection(self) -> None:
-        first_connection = True
-        while True:
-            await asyncio.sleep(10)
-
-            # Assume that internet connection is set to False on 443 errors.
-            if self.shard_downloader.internet_connection:
-                continue
-
-            self._test_internet_connection()
-
-            if first_connection and self.shard_downloader.internet_connection:
-                first_connection = False
-                self._tg.start_soon(self._emit_existing_download_progress)
 
     def shutdown(self) -> None:
         self._tg.cancel_scope.cancel()
@@ -269,7 +241,7 @@ class DownloadCoordinator:
     async def _emit_existing_download_progress(self) -> None:
         try:
             while True:
-                logger.debug(
+                logger.info(
                     "DownloadCoordinator: Fetching and emitting existing download progress..."
                 )
                 async for (
@@ -302,10 +274,10 @@ class DownloadCoordinator:
                     await self.event_sender.send(
                         NodeDownloadProgress(download_progress=status)
                     )
-                logger.debug(
+                logger.info(
                     "DownloadCoordinator: Done emitting existing download progress."
                 )
-                await anyio.sleep(60)
+                await anyio.sleep(5 * 60)  # 5 minutes
         except Exception as e:
             logger.error(
                 f"DownloadCoordinator: Error emitting existing download progress: {e}"

src/exo/download/download_utils.py

@@ -49,10 +49,6 @@ class HuggingFaceAuthenticationError(Exception):
     """Raised when HuggingFace returns 401/403 for a model download."""
 
 
-class HuggingFaceRateLimitError(Exception):
-    """429 Huggingface code"""
-
-
 async def _build_auth_error_message(status_code: int, model_id: ModelId) -> str:
     token = await get_hf_token()
     if status_code == 401 and token is None:
@@ -158,76 +154,49 @@ async def seed_models(seed_dir: str | Path):
                     logger.error(traceback.format_exc())
 
 
-_fetched_file_lists_this_session: set[str] = set()
-
-
 async def fetch_file_list_with_cache(
-    model_id: ModelId,
-    revision: str = "main",
-    recursive: bool = False,
-    skip_internet: bool = False,
-    on_connection_lost: Callable[[], None] = lambda: None,
+    model_id: ModelId, revision: str = "main", recursive: bool = False
 ) -> list[FileListEntry]:
     target_dir = (await ensure_models_dir()) / "caches" / model_id.normalize()
     await aios.makedirs(target_dir, exist_ok=True)
     cache_file = target_dir / f"{model_id.normalize()}--{revision}--file_list.json"
-    cache_key = f"{model_id.normalize()}--{revision}"
-
-    if cache_key in _fetched_file_lists_this_session and await aios.path.exists(
-        cache_file
-    ):
-        async with aiofiles.open(cache_file, "r") as f:
-            return TypeAdapter(list[FileListEntry]).validate_json(await f.read())
-
-    if skip_internet:
-        if await aios.path.exists(cache_file):
-            async with aiofiles.open(cache_file, "r") as f:
-                return TypeAdapter(list[FileListEntry]).validate_json(await f.read())
-        raise FileNotFoundError(
-            f"No internet connection and no cached file list for {model_id}"
-        )
 
+    # Always try fresh first
     try:
         file_list = await fetch_file_list_with_retry(
-            model_id,
-            revision,
-            recursive=recursive,
-            on_connection_lost=on_connection_lost,
+            model_id, revision, recursive=recursive
         )
+        # Update cache with fresh data
         async with aiofiles.open(cache_file, "w") as f:
             await f.write(
                 TypeAdapter(list[FileListEntry]).dump_json(file_list).decode()
             )
-        _fetched_file_lists_this_session.add(cache_key)
         return file_list
     except Exception as e:
+        # Fetch failed - try cache fallback
         if await aios.path.exists(cache_file):
             logger.warning(
                 f"Failed to fetch file list for {model_id}, using cached data: {e}"
             )
             async with aiofiles.open(cache_file, "r") as f:
                 return TypeAdapter(list[FileListEntry]).validate_json(await f.read())
-        raise FileNotFoundError(f"Failed to fetch file list for {model_id}: {e}") from e
+        # No cache available, propagate the error
+        raise
 
 
 async def fetch_file_list_with_retry(
-    model_id: ModelId,
-    revision: str = "main",
-    path: str = "",
-    recursive: bool = False,
-    on_connection_lost: Callable[[], None] = lambda: None,
+    model_id: ModelId, revision: str = "main", path: str = "", recursive: bool = False
 ) -> list[FileListEntry]:
-    n_attempts = 3
+    n_attempts = 30
     for attempt in range(n_attempts):
         try:
             return await _fetch_file_list(model_id, revision, path, recursive)
         except HuggingFaceAuthenticationError:
             raise
         except Exception as e:
-            on_connection_lost()
             if attempt == n_attempts - 1:
                 raise e
-            await asyncio.sleep(2.0**attempt)
+            await asyncio.sleep(min(8, 0.1 * float(2.0 ** int(attempt))))
     raise Exception(
         f"Failed to fetch file list for {model_id=} {revision=} {path=} {recursive=}"
     )
@@ -247,11 +216,7 @@ async def _fetch_file_list(
         if response.status in [401, 403]:
             msg = await _build_auth_error_message(response.status, model_id)
             raise HuggingFaceAuthenticationError(msg)
-        elif response.status == 429:
-            raise HuggingFaceRateLimitError(
-                f"Couldn't download {model_id} because of HuggingFace rate limit."
-            )
-        elif response.status == 200:
+        if response.status == 200:
             data_json = await response.text()
             data = TypeAdapter(list[FileListEntry]).validate_json(data_json)
             files: list[FileListEntry] = []
@@ -284,7 +249,7 @@ def create_http_session(
     else:
         total_timeout = 1800
         connect_timeout = 60
-        sock_read_timeout = 60
+        sock_read_timeout = 1800
         sock_connect_timeout = 60
 
     ssl_context = ssl.create_default_context(
@@ -359,9 +324,8 @@ async def download_file_with_retry(
     path: str,
     target_dir: Path,
     on_progress: Callable[[int, int, bool], None] = lambda _, __, ___: None,
-    on_connection_lost: Callable[[], None] = lambda: None,
 ) -> Path:
-    n_attempts = 3
+    n_attempts = 30
     for attempt in range(n_attempts):
         try:
             return await _download_file(
@@ -369,19 +333,14 @@ async def download_file_with_retry(
             )
         except HuggingFaceAuthenticationError:
             raise
-        except HuggingFaceRateLimitError as e:
-            if attempt == n_attempts - 1:
+        except Exception as e:
+            if isinstance(e, FileNotFoundError) or attempt == n_attempts - 1:
                 raise e
             logger.error(
                 f"Download error on attempt {attempt}/{n_attempts} for {model_id=} {revision=} {path=} {target_dir=}"
             )
             logger.error(traceback.format_exc())
-            await asyncio.sleep(2.0**attempt)
-        except Exception as e:
-            on_connection_lost()
-            if attempt == n_attempts - 1:
-                raise e
-            break
+            await asyncio.sleep(min(8, 0.1 * (2.0**attempt)))
     raise Exception(
         f"Failed to download file {model_id=} {revision=} {path=} {target_dir=}"
     )
@@ -583,9 +542,7 @@ async def download_shard(
     on_progress: Callable[[ShardMetadata, RepoDownloadProgress], Awaitable[None]],
     max_parallel_downloads: int = 8,
     skip_download: bool = False,
-    skip_internet: bool = False,
     allow_patterns: list[str] | None = None,
-    on_connection_lost: Callable[[], None] = lambda: None,
 ) -> tuple[Path, RepoDownloadProgress]:
     if not skip_download:
         logger.debug(f"Downloading {shard.model_card.model_id=}")
@@ -605,11 +562,7 @@ async def download_shard(
 
     all_start_time = time.time()
     file_list = await fetch_file_list_with_cache(
-        shard.model_card.model_id,
-        revision,
-        recursive=True,
-        skip_internet=skip_internet,
-        on_connection_lost=on_connection_lost,
+        shard.model_card.model_id, revision, recursive=True
     )
     filtered_file_list = list(
         filter_repo_objects(
@@ -719,7 +672,6 @@ async def download_shard(
                 lambda curr_bytes, total_bytes, is_renamed: schedule_progress(
                     file, curr_bytes, total_bytes, is_renamed
                 ),
-                on_connection_lost=on_connection_lost,
             )
 
     if not skip_download:

src/exo/download/impl_shard_downloader.py

@@ -1,5 +1,4 @@
 import asyncio
-from asyncio import create_task
 from collections.abc import Awaitable
 from pathlib import Path
 from typing import AsyncIterator, Callable
@@ -8,7 +7,7 @@ from loguru import logger
 
 from exo.download.download_utils import RepoDownloadProgress, download_shard
 from exo.download.shard_downloader import ShardDownloader
-from exo.shared.models.model_cards import ModelCard, ModelId, get_model_cards
+from exo.shared.models.model_cards import MODEL_CARDS, ModelCard, ModelId
 from exo.shared.types.worker.shards import (
     PipelineShardMetadata,
     ShardMetadata,
@@ -22,7 +21,7 @@ def exo_shard_downloader(max_parallel_downloads: int = 8) -> ShardDownloader:
 
 
 async def build_base_shard(model_id: ModelId) -> ShardMetadata:
-    model_card = await ModelCard.load(model_id)
+    model_card = await ModelCard.from_hf(model_id)
     return PipelineShardMetadata(
         model_card=model_card,
         device_rank=0,
@@ -50,10 +49,6 @@ class SingletonShardDownloader(ShardDownloader):
         self.shard_downloader = shard_downloader
         self.active_downloads: dict[ShardMetadata, asyncio.Task[Path]] = {}
 
-    def set_internet_connection(self, value: bool) -> None:
-        self.internet_connection = value
-        self.shard_downloader.set_internet_connection(value)
-
     def on_progress(
         self,
         callback: Callable[[ShardMetadata, RepoDownloadProgress], Awaitable[None]],
@@ -90,10 +85,6 @@ class CachedShardDownloader(ShardDownloader):
         self.shard_downloader = shard_downloader
         self.cache: dict[tuple[str, ShardMetadata], Path] = {}
 
-    def set_internet_connection(self, value: bool) -> None:
-        self.internet_connection = value
-        self.shard_downloader.set_internet_connection(value)
-
     def on_progress(
         self,
         callback: Callable[[ShardMetadata, RepoDownloadProgress], Awaitable[None]],
@@ -151,8 +142,6 @@ class ResumableShardDownloader(ShardDownloader):
             self.on_progress_wrapper,
             max_parallel_downloads=self.max_parallel_downloads,
             allow_patterns=allow_patterns,
-            skip_internet=not self.internet_connection,
-            on_connection_lost=lambda: self.set_internet_connection(False),
         )
         return target_dir
 
@@ -165,31 +154,21 @@ class ResumableShardDownloader(ShardDownloader):
             """Helper coroutine that builds the shard for a model and gets its download status."""
             shard = await build_full_shard(model_id)
             return await download_shard(
-                shard,
-                self.on_progress_wrapper,
-                skip_download=True,
-                skip_internet=not self.internet_connection,
-                on_connection_lost=lambda: self.set_internet_connection(False),
+                shard, self.on_progress_wrapper, skip_download=True
             )
 
-        semaphore = asyncio.Semaphore(self.max_parallel_downloads)
-
-        async def download_with_semaphore(
-            model_card: ModelCard,
-        ) -> tuple[Path, RepoDownloadProgress]:
-            async with semaphore:
-                return await _status_for_model(model_card.model_id)
-
+        # Kick off download status coroutines concurrently
         tasks = [
-            create_task(download_with_semaphore(model_card))
-            for model_card in await get_model_cards()
+            asyncio.create_task(_status_for_model(model_card.model_id))
+            for model_card in MODEL_CARDS.values()
         ]
 
         for task in asyncio.as_completed(tasks):
             try:
                 yield await task
+            # TODO: except Exception
             except Exception as e:
-                logger.warning(f"Error downloading shard: {type(e).__name__}")
+                logger.error("Error downloading shard:", e)
 
     async def get_shard_download_status_for_shard(
         self, shard: ShardMetadata

src/exo/download/shard_downloader.py

@@ -16,11 +16,6 @@ from exo.shared.types.worker.shards import (
 
 # TODO: the PipelineShardMetadata getting reinstantiated is a bit messy. Should this be a classmethod?
 class ShardDownloader(ABC):
-    internet_connection: bool = False
-
-    def set_internet_connection(self, value: bool) -> None:
-        self.internet_connection = value
-
     @abstractmethod
     async def ensure_shard(
         self, shard: ShardMetadata, config_only: bool = False