better message for configuring local network macOS app

Merge branch 'main' into releases/v1.0.65
re enable the evil network script (#1277 )
2026-01-24 22:12:39 -05:00 · 2026-01-24 06:32:15 -08:00 · 2026-01-24 05:36:15 -08:00 · 2026-01-24 13:36:06 +00:00 · 2026-01-23 15:29:22 -08:00 · 2026-01-23 20:48:51 +00:00
21 changed files with 395 additions and 535 deletions
--- a/MISSED_THINGS.md
+++ b/MISSED_THINGS.md
@@ -5,16 +5,16 @@
 [X] Fetching download status of all models on start
 [X] Deduplication of tasks in plan_step.
 [X] resolve_allow_patterns should just be wildcard now.
-[X] no mx_barrier in genreate.py mlx_generate at the end.
+[] no mx_barrier in genreate.py mlx_generate at the end.
 [] cache assertion not needed in auto_parallel.py PipelineLastLayer.
-[X] GPTOSS support dropped in auto_parallel.py.
-[X] sharding changed "all-to-sharded" became _all_to_sharded in auto_parallel.py.
-[X] same as above with "sharded-to-all" became _sharded_to_all in auto_parallel.py.
-[X] Dropped support for Ministral3Model, DeepseekV32Model, Glm4MoeModel, Qwen3NextModel, GptOssMode in auto_parallel.py.
+[] GPTOSS support dropped in auto_parallel.py.
+[] sharding changed "all-to-sharded" became _all_to_sharded in auto_parallel.py.
+[] same as above with "sharded-to-all" became _sharded_to_all in auto_parallel.py.
+[] Dropped support for Ministral3Model, DeepseekV32Model, Glm4MoeModel, Qwen3NextModel, GptOssMode in auto_parallel.py.
 [] Dropped prefill/decode code in auto_parallel.py and utils_mlx.py.
 [X] KV_CACHE_BITS should be None to disable quantized KV cache.
-[X] Dropped _set_nofile_limit in utils_mlx.py.
-[X] We have group optional in load_mlx_items in utils_mlx.py.
+[] Dropped _set_nofile_limit in utils_mlx.py.
+[] We have group optional in load_mlx_items in utils_mlx.py.
 [] Dropped add_missing_chat_templates for GptOss in load_mlx_items in utils_mlx.py.
 [] Dropped model.make_cache in make_kv_cache in utils_mlx.py.
 [X] We put cache limit back in utils_mlx.py.
--- a/app/EXO/EXO/Services/NetworkSetupHelper.swift
+++ b/app/EXO/EXO/Services/NetworkSetupHelper.swift
@@ -18,6 +18,9 @@ enum NetworkSetupHelper {

        set -euo pipefail

+        # Wait for macOS to finish network setup after boot
+        sleep 30
+
        PREFS="/Library/Preferences/SystemConfiguration/preferences.plist"

        # Remove bridge0 interface
@@ -31,6 +34,35 @@ enum NetworkSetupHelper {
        # Remove Thunderbolt Bridge from VirtualNetworkInterfaces in preferences.plist
        /usr/libexec/PlistBuddy -c "Delete :VirtualNetworkInterfaces:Bridge:bridge0" "$PREFS" 2>/dev/null || true

+        networksetup -listlocations | grep -q exo || {
+          networksetup -createlocation exo
+        }
+
+        networksetup -switchtolocation exo
+        networksetup -listallhardwareports \\
+          | awk -F': ' '/Hardware Port: / {print $2}' \\
+          | while IFS=":" read -r name; do
+              case "$name" in
+                "Ethernet Adapter"*)
+                        ;;
+                "Thunderbolt Bridge")
+                        ;;
+                "Thunderbolt "*)
+                  networksetup -listallnetworkservices \\
+                    | grep -q "EXO $name" \\
+                      || networksetup -createnetworkservice "EXO $name" "$name" 2>/dev/null \\
+                      || continue
+                  networksetup -setdhcp "EXO $name"
+                        ;;
+                *)
+                  networksetup -listallnetworkservices \\
+                    | grep -q "$name" \\
+                      || networksetup -createnetworkservice "$name" "$name" 2>/dev/null \\
+                      || continue
+                        ;;
+              esac
+            done
+
        networksetup -listnetworkservices | grep -q "Thunderbolt Bridge" && {
          networksetup -setnetworkserviceenabled "Thunderbolt Bridge" off
        } || true
@@ -51,7 +83,7 @@ enum NetworkSetupHelper {
                let alert = NSAlert()
                alert.messageText = "EXO Network Configuration"
                alert.informativeText =
-                    "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."
+                    "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."
                alert.alertStyle = .informational
                alert.addButton(withTitle: "Install")
                alert.addButton(withTitle: "Not Now")
--- a/dashboard/src/lib/components/ChatForm.svelte
+++ b/dashboard/src/lib/components/ChatForm.svelte
@@ -12,7 +12,6 @@
    ttftMs,
    tps,
    totalTokens,
-    cancelRequest,
  } from "$lib/stores/app.svelte";
  import ChatAttachments from "./ChatAttachments.svelte";
  import ImageParamsPanel from "./ImageParamsPanel.svelte";
@@ -606,15 +605,37 @@
        style="min-height: 28px; max-height: 150px;"
      ></textarea>

-      {#if loading}
-        <button
-          type="button"
-          onclick={() => cancelRequest()}
-          class="px-2.5 sm:px-4 py-1.5 sm:py-2 rounded text-xs sm:text-xs tracking-[0.1em] sm:tracking-[0.15em] uppercase font-medium transition-all duration-200 whitespace-nowrap bg-exo-medium-gray/50 text-exo-light-gray border border-exo-medium-gray/50 hover:border-red-500/50 hover:text-red-400 cursor-pointer"
-        >
+      <button
+        type="submit"
+        disabled={!canSend || loading || isEditOnlyWithoutImage}
+        class="px-2.5 sm:px-4 py-1.5 sm:py-2 rounded text-xs sm:text-xs tracking-[0.1em] sm:tracking-[0.15em] uppercase font-medium transition-all duration-200 whitespace-nowrap
+					{!canSend || loading || isEditOnlyWithoutImage
+          ? 'bg-exo-medium-gray/50 text-exo-light-gray cursor-not-allowed'
+          : 'bg-exo-yellow text-exo-black hover:bg-exo-yellow-darker hover:shadow-[0_0_20px_rgba(255,215,0,0.3)]'}"
+        aria-label={shouldShowEditMode
+          ? "Edit image"
+          : isImageModel()
+            ? "Generate image"
+            : "Send message"}
+      >
+        {#if loading}
          <span class="inline-flex items-center gap-1 sm:gap-2">
+            <span
+              class="w-2.5 h-2.5 sm:w-3 sm:h-3 border-2 border-current border-t-transparent rounded-full animate-spin"
+            ></span>
+            <span class="hidden sm:inline"
+              >{shouldShowEditMode
+                ? "EDITING"
+                : isImageModel()
+                  ? "GENERATING"
+                  : "PROCESSING"}</span
+            >
+            <span class="sm:hidden">...</span>
+          </span>
+        {:else if shouldShowEditMode}
+          <span class="inline-flex items-center gap-1.5">
            <svg
-              class="w-3 h-3"
+              class="w-3.5 h-3.5"
              fill="none"
              viewBox="0 0 24 24"
              stroke="currentColor"
@@ -623,81 +644,47 @@
              <path
                stroke-linecap="round"
                stroke-linejoin="round"
-                d="M6 18L18 6M6 6l12 12"
+                d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
              />
            </svg>
-            <span class="hidden sm:inline">CANCEL</span>
-            <span class="sm:hidden">X</span>
+            <span>EDIT</span>
          </span>
-        </button>
-      {:else}
-        <button
-          type="submit"
-          disabled={!canSend || isEditOnlyWithoutImage}
-          class="px-2.5 sm:px-4 py-1.5 sm:py-2 rounded text-xs sm:text-xs tracking-[0.1em] sm:tracking-[0.15em] uppercase font-medium transition-all duration-200 whitespace-nowrap
-            {!canSend || isEditOnlyWithoutImage
-            ? 'bg-exo-medium-gray/50 text-exo-light-gray cursor-not-allowed'
-            : 'bg-exo-yellow text-exo-black hover:bg-exo-yellow-darker hover:shadow-[0_0_20px_rgba(255,215,0,0.3)]'}"
-          aria-label={shouldShowEditMode
-            ? "Edit image"
-            : isImageModel()
-              ? "Generate image"
-              : "Send message"}
-        >
-          {#if shouldShowEditMode}
-            <span class="inline-flex items-center gap-1.5">
-              <svg
-                class="w-3.5 h-3.5"
-                fill="none"
-                viewBox="0 0 24 24"
-                stroke="currentColor"
-                stroke-width="2"
-              >
-                <path
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                  d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
-                />
-              </svg>
-              <span>EDIT</span>
-            </span>
-          {:else if isEditOnlyWithoutImage}
-            <span class="inline-flex items-center gap-1.5">
-              <svg
-                class="w-3.5 h-3.5"
-                fill="none"
-                viewBox="0 0 24 24"
-                stroke="currentColor"
-                stroke-width="2"
-              >
-                <path
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                  d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
-                />
-              </svg>
-              <span>EDIT</span>
-            </span>
-          {:else if isImageModel()}
-            <span class="inline-flex items-center gap-1.5">
-              <svg
-                class="w-3.5 h-3.5"
-                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>
-              <span>GENERATE</span>
-            </span>
-          {:else}
-            SEND
-          {/if}
-        </button>
-      {/if}
+        {:else if isEditOnlyWithoutImage}
+          <span class="inline-flex items-center gap-1.5">
+            <svg
+              class="w-3.5 h-3.5"
+              fill="none"
+              viewBox="0 0 24 24"
+              stroke="currentColor"
+              stroke-width="2"
+            >
+              <path
+                stroke-linecap="round"
+                stroke-linejoin="round"
+                d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
+              />
+            </svg>
+            <span>EDIT</span>
+          </span>
+        {:else if isImageModel()}
+          <span class="inline-flex items-center gap-1.5">
+            <svg
+              class="w-3.5 h-3.5"
+              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>
+            <span>GENERATE</span>
+          </span>
+        {:else}
+          SEND
+        {/if}
+      </button>
    </div>

    <!-- Bottom accent line -->
--- a/dashboard/src/lib/stores/app.svelte.ts
+++ b/dashboard/src/lib/stores/app.svelte.ts
@@ -464,7 +464,6 @@ class AppStore {
  private previewsInterval: ReturnType<typeof setInterval> | null = null;
  private lastConversationPersistTs = 0;
  private previousNodeIds: Set<string> = new Set();
-  private activeAbortController: AbortController | null = null;

  constructor() {
    if (browser) {
@@ -1747,9 +1746,6 @@ class AppStore {
    const targetConversationId = this.activeConversationId;
    if (!targetConversationId) return;

-    this.activeAbortController = new AbortController();
-    const signal = this.activeAbortController.signal;
-
    this.isLoading = true;
    this.currentResponse = "";
    this.ttftMs = null;
@@ -1884,7 +1880,6 @@ class AppStore {
          temperature: 0.7,
          stream: true,
        }),
-        signal,
      });

      if (!response.ok) {
@@ -1980,9 +1975,6 @@ class AppStore {
        this.persistConversation(targetConversationId);
      }
    } catch (error) {
-      if (signal.aborted) {
-        return;
-      }
      console.error("Error sending message:", error);
      this.handleStreamingError(
        error,
@@ -1991,7 +1983,6 @@ class AppStore {
        "Failed to get response",
      );
    } finally {
-      this.activeAbortController = null;
      this.isLoading = false;
      this.currentResponse = "";
      this.saveConversationsToStorage();
@@ -2012,9 +2003,6 @@ class AppStore {
    const targetConversationId = this.activeConversationId;
    if (!targetConversationId) return;

-    this.activeAbortController = new AbortController();
-    const signal = this.activeAbortController.signal;
-
    this.isLoading = true;
    this.currentResponse = "";

@@ -2100,7 +2088,6 @@ class AppStore {
          "Content-Type": "application/json",
        },
        body: JSON.stringify(requestBody),
-        signal,
      });

      if (!response.ok) {
@@ -2210,19 +2197,6 @@ class AppStore {
        },
      );
    } catch (error) {
-      if (signal.aborted) {
-        // Clean up the "Generating image..." message on cancellation
-        this.updateConversationMessage(
-          targetConversationId,
-          assistantMessage.id,
-          (msg) => {
-            msg.content = "Cancelled";
-            msg.attachments = [];
-          },
-        );
-        this.syncActiveMessagesIfNeeded(targetConversationId);
-        return;
-      }
      console.error("Error generating image:", error);
      this.handleStreamingError(
        error,
@@ -2231,7 +2205,6 @@ class AppStore {
        "Failed to generate image",
      );
    } finally {
-      this.activeAbortController = null;
      this.isLoading = false;
      this.saveConversationsToStorage();
    }
@@ -2255,9 +2228,6 @@ class AppStore {
    const targetConversationId = this.activeConversationId;
    if (!targetConversationId) return;

-    this.activeAbortController = new AbortController();
-    const signal = this.activeAbortController.signal;
-
    this.isLoading = true;
    this.currentResponse = "";

@@ -2366,7 +2336,6 @@ class AppStore {
      const apiResponse = await fetch("/v1/images/edits", {
        method: "POST",
        body: formData,
-        signal,
      });

      if (!apiResponse.ok) {
@@ -2438,19 +2407,6 @@ class AppStore {
        },
      );
    } catch (error) {
-      if (signal.aborted) {
-        // Clean up the "Editing image..." message on cancellation
-        this.updateConversationMessage(
-          targetConversationId,
-          assistantMessage.id,
-          (msg) => {
-            msg.content = "cancelled";
-            msg.attachments = [];
-          },
-        );
-        this.syncActiveMessagesIfNeeded(targetConversationId);
-        return;
-      }
      console.error("Error editing image:", error);
      this.handleStreamingError(
        error,
@@ -2459,24 +2415,11 @@ class AppStore {
        "Failed to edit image",
      );
    } finally {
-      this.activeAbortController = null;
      this.isLoading = false;
      this.saveConversationsToStorage();
    }
  }

-  /**
-   * Cancel an in-flight request by aborting the active fetch
-   */
-  cancelRequest(): void {
-    if (this.activeAbortController) {
-      this.activeAbortController.abort();
-      this.activeAbortController = null;
-    }
-    this.isLoading = false;
-    this.currentResponse = "";
-  }
-
  /**
   * Clear current chat and go back to welcome state
   */
@@ -2613,7 +2556,6 @@ export const editMessage = (messageId: string, newContent: string) =>
 export const editAndRegenerate = (messageId: string, newContent: string) =>
  appStore.editAndRegenerate(messageId, newContent);
 export const regenerateLastResponse = () => appStore.regenerateLastResponse();
-export const cancelRequest = () => appStore.cancelRequest();

 // Conversation actions
 export const conversations = () => appStore.conversations;
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -17,7 +17,7 @@ dependencies = [
    "loguru>=0.7.3",
    "exo_pyo3_bindings", # rust bindings
    "anyio==4.11.0",
-    "mlx==0.30.3; sys_platform == 'darwin'",
+    "mlx @ git+https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git; sys_platform == 'darwin'",
    "mlx[cpu]==0.30.3; sys_platform == 'linux'",
    "mlx-lm @ git+https://github.com/AlexCheema/mlx-lm.git@fix-transformers-5.0.0rc2",
    "tiktoken>=0.12.0", # required for kimi k2 tokenizer
--- a/src/exo/master/api.py
+++ b/src/exo/master/api.py
@@ -88,7 +88,6 @@ from exo.shared.types.commands import (
    PlaceInstance,
    SendInputChunk,
    StartDownload,
-    TaskCancelled,
    TaskFinished,
 )
 from exo.shared.types.common import CommandId, Id, NodeId, SessionId
@@ -509,14 +508,16 @@ class API:
                        break

        except anyio.get_cancelled_exc_class():
-            command = TaskCancelled(cancelled_command_id=command_id)
-            with anyio.CancelScope(shield=True):
-                await self.command_sender.send(
-                    ForwarderCommand(origin=self.node_id, command=command)
-                )
+            # TODO: TaskCancelled
+            """
+            self.command_sender.send_nowait(
+                ForwarderCommand(origin=self.node_id, command=command)
+            )
+            """
            raise
        finally:
-            await self._send(TaskFinished(finished_command_id=command_id))
+            command = TaskFinished(finished_command_id=command_id)
+            await self._send(command)
            if command_id in self._chat_completion_queues:
                del self._chat_completion_queues[command_id]

@@ -900,11 +901,6 @@ class API:
                        del image_metadata[key]

        except anyio.get_cancelled_exc_class():
-            command = TaskCancelled(cancelled_command_id=command_id)
-            with anyio.CancelScope(shield=True):
-                await self.command_sender.send(
-                    ForwarderCommand(origin=self.node_id, command=command)
-                )
            raise
        finally:
            await self._send(TaskFinished(finished_command_id=command_id))
@@ -986,11 +982,6 @@ class API:

            return (images, stats if capture_stats else None)
        except anyio.get_cancelled_exc_class():
-            command = TaskCancelled(cancelled_command_id=command_id)
-            with anyio.CancelScope(shield=True):
-                await self.command_sender.send(
-                    ForwarderCommand(origin=self.node_id, command=command)
-                )
            raise
        finally:
            await self._send(TaskFinished(finished_command_id=command_id))
--- a/src/exo/master/main.py
+++ b/src/exo/master/main.py
@@ -21,7 +21,6 @@ from exo.shared.types.commands import (
    PlaceInstance,
    RequestEventLog,
    SendInputChunk,
-    TaskCancelled,
    TaskFinished,
    TestCommand,
 )
@@ -36,7 +35,6 @@ from exo.shared.types.events import (
    NodeTimedOut,
    TaskCreated,
    TaskDeleted,
-    TaskStatusUpdated,
 )
 from exo.shared.types.state import State
 from exo.shared.types.tasks import (
@@ -280,18 +278,6 @@ class Master:
                                    chunk=chunk,
                                )
                            )
-                        case TaskCancelled():
-                            if (
-                                task_id := self.command_task_mapping.get(
-                                    command.cancelled_command_id
-                                )
-                            ) is not None:
-                                generated_events.append(
-                                    TaskStatusUpdated(
-                                        task_status=TaskStatus.Cancelled,
-                                        task_id=task_id,
-                                    )
-                                )
                        case TaskFinished():
                            generated_events.append(
                                TaskDeleted(
@@ -300,9 +286,10 @@ class Master:
                                    ]
                                )
                            )
-                            self.command_task_mapping.pop(
-                                command.finished_command_id, None
-                            )
+                            if command.finished_command_id in self.command_task_mapping:
+                                del self.command_task_mapping[
+                                    command.finished_command_id
+                                ]
                        case RequestEventLog():
                            # We should just be able to send everything, since other buffers will ignore old messages
                            for i in range(command.since_idx, len(self._event_log)):
--- a/src/exo/shared/types/commands.py
+++ b/src/exo/shared/types/commands.py
@@ -48,10 +48,6 @@ class DeleteInstance(BaseCommand):
    instance_id: InstanceId


-class TaskCancelled(BaseCommand):
-    cancelled_command_id: CommandId
-
-
 class TaskFinished(BaseCommand):
    finished_command_id: CommandId

@@ -88,7 +84,6 @@ Command = (
    | PlaceInstance
    | CreateInstance
    | DeleteInstance
-    | TaskCancelled
    | TaskFinished
    | SendInputChunk
 )
--- a/src/exo/shared/types/tasks.py
+++ b/src/exo/shared/types/tasks.py
@@ -24,7 +24,6 @@ class TaskStatus(str, Enum):
    Complete = "Complete"
    TimedOut = "TimedOut"
    Failed = "Failed"
-    Cancelled = "Cancelled"


 class BaseTask(TaggedModel):
@@ -61,10 +60,6 @@ class ChatCompletion(BaseTask):  # emitted by Master
    error_message: str | None = Field(default=None)


-class CancelTask(BaseTask):
-    cancelled_task_id: TaskId
-
-
 class ImageGeneration(BaseTask):  # emitted by Master
    command_id: CommandId
    task_params: ImageGenerationTaskParams
@@ -92,7 +87,6 @@ Task = (
    | LoadModel
    | StartWarmup
    | ChatCompletion
-    | CancelTask
    | ImageGeneration
    | ImageEdits
    | Shutdown
--- a/src/exo/worker/engines/image/distributed_model.py
+++ b/src/exo/worker/engines/image/distributed_model.py
@@ -1,4 +1,4 @@
-from collections.abc import Callable, Generator
+from collections.abc import Generator
 from pathlib import Path
 from typing import Any, Literal, Optional

@@ -109,7 +109,6 @@ class DistributedImageModel:
        image_path: Path | None = None,
        partial_images: int = 0,
        advanced_params: AdvancedImageParams | None = None,
-        cancel_checker: Callable[[], bool] | None = None,
    ) -> Generator[Image.Image | tuple[Image.Image, int, int], None, None]:
        if (
            advanced_params is not None
@@ -154,7 +153,6 @@ class DistributedImageModel:
            guidance_override=guidance_override,
            negative_prompt=negative_prompt,
            num_sync_steps=num_sync_steps,
-            cancel_checker=cancel_checker,
        ):
            if isinstance(result, tuple):
                # Partial image: (GeneratedImage, partial_index, total_partials)
--- a/src/exo/worker/engines/image/generate.py
+++ b/src/exo/worker/engines/image/generate.py
@@ -3,7 +3,6 @@ import io
 import random
 import tempfile
 import time
-from collections.abc import Callable
 from pathlib import Path
 from typing import Generator, Literal

@@ -69,18 +68,12 @@ def warmup_image_generator(model: DistributedImageModel) -> Image.Image | None:
 def generate_image(
    model: DistributedImageModel,
    task: ImageGenerationTaskParams | ImageEditsInternalParams,
-    cancel_checker: Callable[[], bool] | None = None,
 ) -> Generator[ImageGenerationResponse | PartialImageResponse, None, None]:
    """Generate image(s), optionally yielding partial results.

    When partial_images > 0 or stream=True, yields PartialImageResponse for
    intermediate images, then ImageGenerationResponse for the final image.

-    Args:
-        model: The distributed image model to use for generation.
-        task: The task parameters for image generation or editing.
-        cancel_checker: Optional callback to check if generation should be cancelled.
-
    Yields:
        PartialImageResponse for intermediate images (if partial_images > 0, first image only)
        ImageGenerationResponse for final complete images
@@ -130,7 +123,6 @@ def generate_image(
                image_path=image_path,
                partial_images=partial_images,
                advanced_params=advanced_params,
-                cancel_checker=cancel_checker,
            ):
                if isinstance(result, tuple):
                    # Partial image: (Image, partial_index, total_partials)
--- a/src/exo/worker/engines/image/pipeline/runner.py
+++ b/src/exo/worker/engines/image/pipeline/runner.py
@@ -1,4 +1,3 @@
-from collections.abc import Callable
 from math import ceil
 from typing import Any, Optional

@@ -95,8 +94,6 @@ class DiffusionRunner:
        self.total_layers = config.total_blocks

        self._guidance_override: float | None = None
-        self._cancel_checker: Callable[[], bool] | None = None
-        self._cancelling = False

        self._compute_assigned_blocks()

@@ -151,54 +148,6 @@ class DiffusionRunner:
            return self._guidance_override
        return self.config.guidance_scale

-    def _check_cancellation(self) -> bool:
-        if self._cancelling:
-            return True
-        if (
-            self.is_first_stage
-            and self._cancel_checker is not None
-            and self._cancel_checker()
-        ):
-            self._cancelling = True
-        return self._cancelling
-
-    def _is_sentinel(self, tensor: mx.array) -> bool:
-        return bool(mx.any(mx.isnan(tensor)).item())
-
-    def _make_sentinel_like(self, tensor: mx.array) -> mx.array:
-        return mx.full(tensor.shape, float("nan"), dtype=tensor.dtype)
-
-    def _recv(
-        self,
-        shape: tuple[int, ...],
-        dtype: mx.Dtype,
-        src: int,
-    ) -> mx.array:
-        """Receive data and check for cancellation sentinel."""
-        data = mx.distributed.recv(shape, dtype, src, group=self.group)
-        mx.eval(data)
-        if self._is_sentinel(data):
-            self._cancelling = True
-        return data
-
-    def _recv_like(self, template: mx.array, src: int) -> mx.array:
-        """Receive data matching template and check for cancellation sentinel."""
-        data = mx.distributed.recv_like(template, src=src, group=self.group)
-        mx.eval(data)
-        if self._is_sentinel(data):
-            self._cancelling = True
-        return data
-
-    def _send(self, data: mx.array, dst: int) -> mx.array:
-        """Send data, or sentinel if cancelling."""
-
-        if self._cancelling:
-            data = self._make_sentinel_like(data)
-
-        result = mx.distributed.send(data, dst, group=self.group)
-        mx.async_eval(result)
-        return result
-
    def _ensure_wrappers(
        self,
        text_seq_len: int,
@@ -295,7 +244,6 @@ class DiffusionRunner:
        guidance_override: float | None = None,
        negative_prompt: str | None = None,
        num_sync_steps: int = 1,
-        cancel_checker: Callable[[], bool] | None = None,
    ):
        """Primary entry point for image generation.

@@ -307,21 +255,17 @@ class DiffusionRunner:
        5. Decode to image

        Args:
-            runtime_config: Runtime configuration (steps, height, width)
+            settings: Generation config (steps, height, width)
            prompt: Text prompt
            seed: Random seed
            partial_images: Number of intermediate images to yield (0 for none)
            guidance_override: Optional override for guidance scale (CFG)
-            negative_prompt: Optional negative prompt for CFG
-            num_sync_steps: Number of synchronous pipeline steps
-            cancel_checker: Optional callback to check for cancellation

        Yields:
            Partial images as (GeneratedImage, partial_index, total_partials) tuples
            Final GeneratedImage
        """
        self._guidance_override = guidance_override
-        self._cancel_checker = cancel_checker
        latents = self.adapter.create_latents(seed, runtime_config)
        prompt_data = self.adapter.encode_prompt(prompt, negative_prompt)

@@ -363,7 +307,7 @@ class DiffusionRunner:
            except StopIteration as e:
                latents = e.value  # pyright: ignore[reportAny]

-        if self.is_last_stage and not self._cancelling:
+        if self.is_last_stage:
            yield self.adapter.decode_latents(latents, runtime_config, seed, prompt)  # pyright: ignore[reportAny]

    def _run_diffusion_loop(
@@ -379,7 +323,6 @@ class DiffusionRunner:
        if capture_steps is None:
            capture_steps = set()

-        self._cancelling = False
        self._reset_all_caches()

        time_steps = tqdm(range(runtime_config.num_inference_steps))
@@ -402,9 +345,6 @@ class DiffusionRunner:
                    num_sync_steps=num_sync_steps,
                )

-                if self._cancelling:
-                    break
-
                ctx.in_loop(  # pyright: ignore[reportAny]
                    t=t,
                    latents=latents,
@@ -626,8 +566,6 @@ class DiffusionRunner:
            for wrapper in self.joint_block_wrappers:
                wrapper.set_encoder_mask(encoder_hidden_states_mask)

-        self._check_cancellation()
-
        encoder_hidden_states: mx.array | None = None
        if self.is_first_stage:
            hidden_states, encoder_hidden_states = self.adapter.compute_embeddings(
@@ -647,12 +585,19 @@ class DiffusionRunner:

        if self.has_joint_blocks:
            if not self.is_first_stage:
-                hidden_states = self._recv(
-                    (batch_size, num_img_tokens, hidden_dim), dtype, self.prev_rank
+                hidden_states = mx.distributed.recv(
+                    (batch_size, num_img_tokens, hidden_dim),
+                    dtype,
+                    self.prev_rank,
+                    group=self.group,
                )
-                encoder_hidden_states = self._recv(
-                    (batch_size, text_seq_len, hidden_dim), dtype, self.prev_rank
+                encoder_hidden_states = mx.distributed.recv(
+                    (batch_size, text_seq_len, hidden_dim),
+                    dtype,
+                    self.prev_rank,
+                    group=self.group,
                )
+                mx.eval(hidden_states, encoder_hidden_states)

            assert self.joint_block_wrappers is not None
            assert encoder_hidden_states is not None
@@ -674,20 +619,30 @@ class DiffusionRunner:
            if self.has_single_blocks or self.is_last_stage:
                hidden_states = concatenated
            else:
-                concatenated = self._send(concatenated, self.next_rank)
+                concatenated = mx.distributed.send(
+                    concatenated, self.next_rank, group=self.group
+                )
+                mx.async_eval(concatenated)

        elif self.has_joint_blocks and not self.is_last_stage:
            assert encoder_hidden_states is not None
-            hidden_states = self._send(hidden_states, self.next_rank)
-            encoder_hidden_states = self._send(encoder_hidden_states, self.next_rank)
+            hidden_states = mx.distributed.send(
+                hidden_states, self.next_rank, group=self.group
+            )
+            encoder_hidden_states = mx.distributed.send(
+                encoder_hidden_states, self.next_rank, group=self.group
+            )
+            mx.async_eval(hidden_states, encoder_hidden_states)

        if self.has_single_blocks:
            if not self.owns_concat_stage and not self.is_first_stage:
-                hidden_states = self._recv(
+                hidden_states = mx.distributed.recv(
                    (batch_size, text_seq_len + num_img_tokens, hidden_dim),
                    dtype,
                    self.prev_rank,
+                    group=self.group,
                )
+                mx.eval(hidden_states)

            assert self.single_block_wrappers is not None
            for wrapper in self.single_block_wrappers:
@@ -699,7 +654,10 @@ class DiffusionRunner:
                )

            if not self.is_last_stage:
-                hidden_states = self._send(hidden_states, self.next_rank)
+                hidden_states = mx.distributed.send(
+                    hidden_states, self.next_rank, group=self.group
+                )
+                mx.async_eval(hidden_states)

        hidden_states = hidden_states[:, text_seq_len:, ...]

@@ -783,13 +741,14 @@ class DiffusionRunner:
            )

            if not self.is_first_stage:
-                hidden_states = self._send(hidden_states, 0)
+                hidden_states = mx.distributed.send(hidden_states, 0, group=self.group)
+                mx.async_eval(hidden_states)

        elif self.is_first_stage:
-            hidden_states = self._recv_like(prev_latents, src=self.world_size - 1)
-
-            if self._cancelling:
-                return prev_latents
+            hidden_states = mx.distributed.recv_like(
+                prev_latents, src=self.world_size - 1, group=self.group
+            )
+            mx.eval(hidden_states)

        else:
            hidden_states = prev_latents
@@ -849,9 +808,10 @@ class DiffusionRunner:
                and not self.is_last_stage
                and not is_first_async_step
            ):
-                patch = self._recv_like(patch, src=self.prev_rank)
-
-            self._check_cancellation()
+                patch = mx.distributed.recv_like(
+                    patch, src=self.prev_rank, group=self.group
+                )
+                mx.eval(patch)

            step_patch = mx.concatenate([patch, patch], axis=0) if needs_cfg else patch

@@ -881,11 +841,11 @@ class DiffusionRunner:
                    latents=prev_patch_latents[patch_idx],
                )

-                # Ring send back to first stage (except on last timestep)
                if not self.is_first_stage and t != config.num_inference_steps - 1:
-                    patch_latents[patch_idx] = self._send(
-                        patch_latents[patch_idx], self.next_rank
+                    patch_latents[patch_idx] = mx.distributed.send(
+                        patch_latents[patch_idx], self.next_rank, group=self.group
                    )
+                    mx.async_eval(patch_latents[patch_idx])

        return mx.concatenate(patch_latents, axis=1)

@@ -924,16 +884,22 @@ class DiffusionRunner:
        if self.has_joint_blocks:
            if not self.is_first_stage:
                patch_len = patch.shape[1]
-                patch = self._recv(
-                    (batch_size, patch_len, hidden_dim), patch.dtype, self.prev_rank
+                patch = mx.distributed.recv(
+                    (batch_size, patch_len, hidden_dim),
+                    patch.dtype,
+                    self.prev_rank,
+                    group=self.group,
                )
+                mx.eval(patch)

                if patch_idx == 0:
-                    encoder_hidden_states = self._recv(
+                    encoder_hidden_states = mx.distributed.recv(
                        (batch_size, text_seq_len, hidden_dim),
                        patch.dtype,
                        self.prev_rank,
+                        group=self.group,
                    )
+                    mx.eval(encoder_hidden_states)

            if self.is_first_stage:
                patch, encoder_hidden_states = self.adapter.compute_embeddings(
@@ -958,25 +924,32 @@ class DiffusionRunner:
            if self.has_single_blocks or self.is_last_stage:
                patch = patch_concat
            else:
-                patch_concat = self._send(patch_concat, self.next_rank)
+                patch_concat = mx.distributed.send(
+                    patch_concat, self.next_rank, group=self.group
+                )
+                mx.async_eval(patch_concat)

        elif self.has_joint_blocks and not self.is_last_stage:
-            patch = self._send(patch, self.next_rank)
+            patch = mx.distributed.send(patch, self.next_rank, group=self.group)
+            mx.async_eval(patch)

            if patch_idx == 0:
                assert encoder_hidden_states is not None
-                encoder_hidden_states = self._send(
-                    encoder_hidden_states, self.next_rank
+                encoder_hidden_states = mx.distributed.send(
+                    encoder_hidden_states, self.next_rank, group=self.group
                )
+                mx.async_eval(encoder_hidden_states)

        if self.has_single_blocks:
            if not self.owns_concat_stage and not self.is_first_stage:
                patch_len = patch.shape[1]
-                patch = self._recv(
+                patch = mx.distributed.recv(
                    (batch_size, text_seq_len + patch_len, hidden_dim),
                    patch.dtype,
                    self.prev_rank,
+                    group=self.group,
                )
+                mx.eval(patch)

            assert self.single_block_wrappers is not None
            for wrapper in self.single_block_wrappers:
@@ -988,7 +961,8 @@ class DiffusionRunner:
                )

            if not self.is_last_stage:
-                patch = self._send(patch, self.next_rank)
+                patch = mx.distributed.send(patch, self.next_rank, group=self.group)
+                mx.async_eval(patch)

        noise: mx.array | None = None
        if self.is_last_stage:
--- a/src/exo/worker/engines/mlx/auto_parallel.py
+++ b/src/exo/worker/engines/mlx/auto_parallel.py
@@ -145,6 +145,10 @@ class PipelineLastLayer(CustomMlxLayer):
            if cache is not None:
                cache.keys = mx.depends(cache.keys, output)  # type: ignore[reportUnknownMemberType]

+        output = mx.distributed.all_gather(output, group=self.group)[
+            -output.shape[0] :
+        ]  # type :ignore
+
        return output


@@ -252,10 +256,6 @@ def patch_pipeline_model[T](model: T, group: mx.distributed.Group) -> T:
        if cache is not None:
            cache[-1].state = mx.depends(cache[-1].state, logits)  # type: ignore

-        logits = mx.distributed.all_gather(logits, group=group)[
-            -logits.shape[0] :
-        ]  # type :ignore
-
        return logits

    cls.__call__ = patched_call
--- a/src/exo/worker/engines/mlx/generator/generate.py
+++ b/src/exo/worker/engines/mlx/generator/generate.py
@@ -23,6 +23,7 @@ from exo.worker.engines.mlx.constants import KV_BITS, KV_GROUP_SIZE, MAX_TOKENS
 from exo.worker.engines.mlx.utils_mlx import (
    apply_chat_template,
    make_kv_cache,
+    mx_barrier,
 )
 from exo.worker.runner.bootstrap import logger

@@ -89,6 +90,10 @@ def warmup_inference(

    logger.info("Generated ALL warmup tokens")

+    # TODO: Do we want an mx_barrier?
+    #  At least this version is actively incorrect, as it should use mx_barrier(group)
+    mx_barrier()
+
    return tokens_generated


@@ -181,3 +186,5 @@ def mlx_generate(

        if out.finish_reason is not None:
            break
+
+        # TODO: Do we want an mx_barrier?
--- a/src/exo/worker/engines/mlx/utils_mlx.py
+++ b/src/exo/worker/engines/mlx/utils_mlx.py
@@ -70,6 +70,8 @@ Group = mx.distributed.Group
 resource.setrlimit(resource.RLIMIT_NOFILE, (2048, 4096))


+# TODO: Test this
+#  ALSO https://github.com/exo-explore/exo/pull/233#discussion_r2549683673
 def get_weights_size(model_shard_meta: ShardMetadata) -> Memory:
    return Memory.from_float_kb(
        (model_shard_meta.end_layer - model_shard_meta.start_layer)
@@ -87,6 +89,30 @@ class ModelLoadingTimeoutError(Exception):
    pass


+def mx_barrier(group: Group | None = None):
+    mx.eval(
+        mx.distributed.all_sum(
+            mx.array(1.0),
+            stream=mx.default_stream(mx.Device(mx.cpu)),
+            group=group,
+        )
+    )
+
+
+def broadcast_from_zero(value: int, group: Group | None = None):
+    if group is None:
+        return value
+
+    if group.rank() == 0:
+        a = mx.array([value], dtype=mx.int32)
+    else:
+        a = mx.array([0], dtype=mx.int32)
+
+    m = mx.distributed.all_sum(a, stream=mx.Device(mx.DeviceType.cpu), group=group)
+    mx.eval(m)
+    return int(m.item())
+
+
 class HostList(RootModel[list[str]]):
    @classmethod
    def from_hosts(cls, hosts: list[Host]) -> "HostList":
@@ -144,10 +170,10 @@ def mlx_distributed_init(

                # TODO: update once upstream fixes
                logger.info(
-                    f"rank {rank} MLX_JACCL_DEVICES: {coordination_file} with devices: {jaccl_devices_json}"
+                    f"rank {rank} MLX_IBV_DEVICES: {coordination_file} with devices: {jaccl_devices_json}"
                )
                logger.info(f"rank {rank} MLX_JACCL_COORDINATOR: {jaccl_coordinator}")
-                os.environ["MLX_JACCL_DEVICES"] = coordination_file
+                os.environ["MLX_IBV_DEVICES"] = coordination_file
                os.environ["MLX_RANK"] = str(rank)
                os.environ["MLX_JACCL_COORDINATOR"] = jaccl_coordinator
                group = mx.distributed.init(backend="jaccl", strict=True)
@@ -510,33 +536,3 @@ def mlx_cleanup(
    import gc

    gc.collect()
-
-
-def mx_any(bool_: bool, group: Group | None) -> bool:
-    if group is None:
-        return bool_
-    num_true = mx.distributed.all_sum(
-        mx.array(bool_), group=group, stream=mx.default_stream(mx.Device(mx.cpu))
-    )
-    mx.eval(num_true)
-    return num_true.item() > 0
-
-
-def mx_all(bool_: bool, group: Group | None) -> bool:
-    if group is None:
-        return bool_
-    num_true = mx.distributed.all_sum(
-        mx.array(bool_), group=group, stream=mx.default_stream(mx.Device(mx.cpu))
-    )
-    mx.eval(num_true)
-    return num_true.item() == group.size()
-
-
-def mx_barrier(group: Group | None):
-    if group is None:
-        return
-    mx.eval(
-        mx.distributed.all_sum(
-            mx.array(1.0), group=group, stream=mx.default_stream(mx.Device(mx.cpu))
-        )
-    )
--- a/src/exo/worker/main.py
+++ b/src/exo/worker/main.py
@@ -33,7 +33,6 @@ from exo.shared.types.events import (
 from exo.shared.types.multiaddr import Multiaddr
 from exo.shared.types.state import State
 from exo.shared.types.tasks import (
-    CancelTask,
    CreateRunner,
    DownloadModel,
    ImageEdits,
@@ -116,9 +115,8 @@ class Worker:
        self.local_event_sender.close()
        self.command_sender.close()
        self.download_command_sender.close()
-        async with create_task_group() as tg:
-            for runner in self.runners.values():
-                tg.start_soon(runner.shutdown)
+        for runner in self.runners.values():
+            runner.shutdown()

    async def _forward_info(self, recv: Receiver[GatheredInfo]):
        with recv as info_stream:
@@ -222,22 +220,15 @@ class Worker:
                        )
                    )
                case Shutdown(runner_id=runner_id):
-                    runner = self.runners.pop(runner_id)
                    try:
                        with fail_after(3):
-                            await runner.start_task(task)
+                            await self.runners.pop(runner_id).start_task(task)
                    except TimeoutError:
                        await self.event_sender.send(
                            TaskStatusUpdated(
                                task_id=task.task_id, task_status=TaskStatus.TimedOut
                            )
                        )
-                    finally:
-                        await runner.shutdown()
-                case CancelTask(cancelled_task_id=cancelled_task_id):
-                    await self.runners[self._task_to_runner_id(task)].cancel_task(
-                        cancelled_task_id
-                    )
                case ImageEdits() if task.task_params.total_input_chunks > 0:
                    # Assemble image from chunks and inject into task
                    cmd_id = task.command_id
@@ -360,6 +351,8 @@ class Worker:
            for event in self.out_for_delivery.copy().values():
                await self.local_event_sender.send(event)

+    ## Op Executors
+
    def _create_supervisor(self, task: CreateRunner) -> RunnerSupervisor:
        """Creates and stores a new AssignedRunner with initial downloading status."""
        runner = RunnerSupervisor.create(
--- a/src/exo/worker/plan.py
+++ b/src/exo/worker/plan.py
@@ -4,7 +4,6 @@ from collections.abc import Mapping, Sequence

 from exo.shared.types.common import CommandId, NodeId
 from exo.shared.types.tasks import (
-    CancelTask,
    ChatCompletion,
    ConnectToGroup,
    CreateRunner,
@@ -60,8 +59,7 @@ def plan(
        or _init_distributed_backend(runners, all_runners)
        or _load_model(runners, all_runners, global_download_status)
        or _ready_to_warmup(runners, all_runners)
-        or _cancel_tasks(runners, tasks)
-        or _pending_tasks(runners, tasks, all_runners, input_chunk_buffer or {})
+        or _pending_tasks(runners, tasks, all_runners, input_chunk_buffer)
    )


@@ -272,7 +270,7 @@ def _pending_tasks(
    runners: Mapping[RunnerId, RunnerSupervisor],
    tasks: Mapping[TaskId, Task],
    all_runners: Mapping[RunnerId, RunnerStatus],
-    input_chunk_buffer: Mapping[CommandId, dict[int, str]],
+    input_chunk_buffer: Mapping[CommandId, dict[int, str]] | None = None,
 ) -> Task | None:
    for task in tasks.values():
        # for now, just forward chat completions
@@ -286,7 +284,7 @@ def _pending_tasks(
        if isinstance(task, ImageEdits) and task.task_params.total_input_chunks > 0:
            cmd_id = task.command_id
            expected = task.task_params.total_input_chunks
-            received = len(input_chunk_buffer.get(cmd_id, {}))
+            received = len((input_chunk_buffer or {}).get(cmd_id, {}))
            if received < expected:
                continue  # Wait for all chunks to arrive

@@ -294,31 +292,16 @@ def _pending_tasks(
            if task.instance_id != runner.bound_instance.instance.instance_id:
                continue

-            # the task status _should_ be set to completed by the LAST runner
-            # it is currently set by the first
-            # this is definitely a hack
+            # I have a design point here; this is a state race in disguise as the task status doesn't get updated to completed fast enough
+            # however, realistically the task status should be set to completed by the LAST runner, so this is a true race
+            # the actual solution is somewhat deeper than this bypass - TODO!
            if task.task_id in runner.completed:
                continue

+            # TODO: Check ordering aligns with MLX distributeds expectations.
+
            if isinstance(runner.status, RunnerReady) and all(
                isinstance(all_runners[global_runner_id], (RunnerReady, RunnerRunning))
                for global_runner_id in runner.bound_instance.instance.shard_assignments.runner_to_shard
            ):
                return task
-
-
-def _cancel_tasks(
-    runners: Mapping[RunnerId, RunnerSupervisor],
-    tasks: Mapping[TaskId, Task],
-) -> Task | None:
-    for task in tasks.values():
-        if task.task_status != TaskStatus.Cancelled:
-            continue
-        for runner in runners.values():
-            if task.instance_id != runner.bound_instance.instance.instance_id:
-                continue
-            if task.task_id in runner.cancelled:
-                continue
-            return CancelTask(
-                instance_id=task.instance_id, cancelled_task_id=task.task_id
-            )
--- a/src/exo/worker/runner/bootstrap.py
+++ b/src/exo/worker/runner/bootstrap.py
@@ -3,7 +3,7 @@ import os
 import loguru

 from exo.shared.types.events import Event, RunnerStatusUpdated
-from exo.shared.types.tasks import Task, TaskId
+from exo.shared.types.tasks import Task
 from exo.shared.types.worker.instances import BoundInstance, MlxJacclInstance
 from exo.shared.types.worker.runners import RunnerFailed
 from exo.utils.channels import ClosedResourceError, MpReceiver, MpSender
@@ -15,7 +15,6 @@ def entrypoint(
    bound_instance: BoundInstance,
    event_sender: MpSender[Event],
    task_receiver: MpReceiver[Task],
-    cancel_receiver: MpReceiver[TaskId],
    _logger: "loguru.Logger",
 ) -> None:
    fast_synch_override = os.environ.get("EXO_FAST_SYNCH")
@@ -39,7 +38,7 @@ def entrypoint(
    try:
        from exo.worker.runner.runner import main

-        main(bound_instance, event_sender, task_receiver, cancel_receiver)
+        main(bound_instance, event_sender, task_receiver)
    except ClosedResourceError:
        logger.warning("Runner communication closed unexpectedly")
    except Exception as e:
--- a/src/exo/worker/runner/runner.py
+++ b/src/exo/worker/runner/runner.py
@@ -37,7 +37,6 @@ from exo.shared.types.tasks import (
    Shutdown,
    StartWarmup,
    Task,
-    TaskId,
    TaskStatus,
 )
 from exo.shared.types.worker.instances import BoundInstance
@@ -78,7 +77,6 @@ from exo.worker.engines.mlx.utils_mlx import (
    initialize_mlx,
    load_mlx_items,
    mlx_force_oom,
-    mx_any,
 )
 from exo.worker.runner.bootstrap import logger

@@ -87,7 +85,6 @@ def main(
    bound_instance: BoundInstance,
    event_sender: MpSender[Event],
    task_receiver: MpReceiver[Task],
-    cancel_receiver: MpReceiver[TaskId],
 ):
    instance, runner_id, shard_metadata = (
        bound_instance.instance,
@@ -102,11 +99,8 @@ def main(
        time.sleep(timeout)

    setup_start_time = time.time()
-    cancelled_tasks = set[TaskId]()

-    # type checker was unhappy with me - splitting these fixed it
-    inference_model: Model | None = None
-    image_model: DistributedImageModel | None = None
+    model: Model | DistributedImageModel | None = None
    tokenizer = None
    group = None

@@ -117,7 +111,6 @@ def main(
    )
    with task_receiver as tasks:
        for task in tasks:
-            cancelled_tasks.discard(TaskId("CANCEL_CURRENT_TASK"))
            event_sender.send(
                TaskStatusUpdated(task_id=task.task_id, task_status=TaskStatus.Running)
            )
@@ -162,7 +155,7 @@ def main(
                        time.sleep(0.5)

                    if ModelTask.TextGeneration in shard_metadata.model_card.tasks:
-                        inference_model, tokenizer = load_mlx_items(
+                        model, tokenizer = load_mlx_items(
                            bound_instance, group, on_timeout=on_model_load_timeout
                        )
                        logger.info(
@@ -172,7 +165,7 @@ def main(
                        ModelTask.TextToImage in shard_metadata.model_card.tasks
                        or ModelTask.ImageToImage in shard_metadata.model_card.tasks
                    ):
-                        image_model = initialize_image_model(bound_instance)
+                        model = initialize_image_model(bound_instance)
                    else:
                        raise ValueError(
                            f"Unknown model task(s): {shard_metadata.model_card.tasks}"
@@ -181,6 +174,8 @@ def main(
                    current_status = RunnerLoaded()
                    logger.info("runner loaded")
                case StartWarmup() if isinstance(current_status, RunnerLoaded):
+                    assert model
+
                    current_status = RunnerWarmingUp()
                    logger.info("runner warming up")
                    event_sender.send(
@@ -191,11 +186,11 @@ def main(

                    logger.info(f"warming up inference for instance: {instance}")
                    if ModelTask.TextGeneration in shard_metadata.model_card.tasks:
-                        assert inference_model
+                        assert not isinstance(model, DistributedImageModel)
                        assert tokenizer

                        toks = warmup_inference(
-                            model=inference_model,
+                            model=model,
                            tokenizer=tokenizer,
                            # kv_prefix_cache=kv_prefix_cache,  # supply for warmup-time prefix caching
                        )
@@ -207,8 +202,8 @@ def main(
                        ModelTask.TextToImage in shard_metadata.model_card.tasks
                        or ModelTask.ImageToImage in shard_metadata.model_card.tasks
                    ):
-                        assert image_model
-                        image = warmup_image_generator(model=image_model)
+                        assert isinstance(model, DistributedImageModel)
+                        image = warmup_image_generator(model=model)
                        if image is not None:
                            logger.info(f"warmed up by generating {image.size} image")
                        else:
@@ -227,7 +222,7 @@ def main(
                            runner_id=runner_id, runner_status=current_status
                        )
                    )
-                    assert inference_model
+                    assert model and not isinstance(model, DistributedImageModel)
                    assert tokenizer
                    assert task_params.messages[0].content is not None

@@ -239,7 +234,7 @@ def main(

                        # Generate responses using the actual MLX generation
                        mlx_generator = mlx_generate(
-                            model=inference_model,
+                            model=model,
                            tokenizer=tokenizer,
                            task=task_params,
                            prompt=prompt,
@@ -262,11 +257,11 @@ def main(
                            patch_glm_tokenizer(tokenizer)

                        # GPT-OSS specific parsing to match other model formats.
-                        elif isinstance(inference_model, GptOssModel):
+                        elif isinstance(model, GptOssModel):
                            mlx_generator = parse_gpt_oss(mlx_generator)

                        if tokenizer.has_tool_calling and not isinstance(
-                            inference_model, GptOssModel
+                            model, GptOssModel
                        ):
                            assert tokenizer.tool_call_start
                            assert tokenizer.tool_call_end
@@ -278,17 +273,7 @@ def main(
                                tokenizer.tool_parser,  # pyright: ignore[reportAny]
                            )

-                        last_checked = time.perf_counter()
                        for response in mlx_generator:
-                            if (t := time.perf_counter()) - last_checked > 0.1:
-                                last_checked = t
-                                cancelled_tasks.update(cancel_receiver.collect())
-                                want_to_cancel = (task.task_id in cancelled_tasks) or (
-                                    TaskId("CANCEL_CURRENT_TASK") in cancelled_tasks
-                                )
-                                if mx_any(want_to_cancel, group):
-                                    break
-
                            match response:
                                case GenerationResponse():
                                    if (
@@ -352,16 +337,11 @@ def main(

                    current_status = RunnerReady()
                    logger.info("runner ready")
-                case ImageGeneration() | ImageEdits() if isinstance(
-                    current_status, RunnerReady
-                ):
-                    assert image_model
-                    task_name = (
-                        "image generation"
-                        if isinstance(task, ImageGeneration)
-                        else "image edits"
-                    )
-                    logger.info(f"received {task_name} request: {str(task)[:500]}")
+                case ImageGeneration(
+                    task_params=task_params, command_id=command_id
+                ) if isinstance(current_status, RunnerReady):
+                    assert isinstance(model, DistributedImageModel)
+                    logger.info(f"received image generation request: {str(task)[:500]}")
                    current_status = RunnerRunning()
                    logger.info("runner running")
                    event_sender.send(
@@ -371,19 +351,100 @@ def main(
                    )

                    try:
-                        _run_image_task(
-                            task=task,
-                            image_model=image_model,
-                            shard_metadata=shard_metadata,
-                            event_sender=event_sender,
-                            cancel_receiver=cancel_receiver,
-                            cancelled_tasks=cancelled_tasks,
-                        )
+                        # Generate images using the image generation backend
+                        # Track image_index for final images only
+                        image_index = 0
+                        for response in generate_image(model=model, task=task_params):
+                            if (
+                                shard_metadata.device_rank
+                                == shard_metadata.world_size - 1
+                            ):
+                                match response:
+                                    case PartialImageResponse():
+                                        logger.info(
+                                            f"sending partial ImageChunk {response.partial_index}/{response.total_partials}"
+                                        )
+                                        _process_image_response(
+                                            response,
+                                            command_id,
+                                            shard_metadata,
+                                            event_sender,
+                                            image_index,
+                                        )
+                                    case ImageGenerationResponse():
+                                        logger.info("sending final ImageChunk")
+                                        _process_image_response(
+                                            response,
+                                            command_id,
+                                            shard_metadata,
+                                            event_sender,
+                                            image_index,
+                                        )
+                                        image_index += 1
+                    # can we make this more explicit?
                    except Exception as e:
                        if shard_metadata.device_rank == shard_metadata.world_size - 1:
                            event_sender.send(
                                ChunkGenerated(
-                                    command_id=task.command_id,
+                                    command_id=command_id,
+                                    chunk=ErrorChunk(
+                                        model=shard_metadata.model_card.model_id,
+                                        finish_reason="error",
+                                        error_message=str(e),
+                                    ),
+                                )
+                            )
+                        raise
+
+                    current_status = RunnerReady()
+                    logger.info("runner ready")
+                case ImageEdits(task_params=task_params, command_id=command_id) if (
+                    isinstance(current_status, RunnerReady)
+                ):
+                    assert isinstance(model, DistributedImageModel)
+                    logger.info(f"received image edits request: {str(task)[:500]}")
+                    current_status = RunnerRunning()
+                    logger.info("runner running")
+                    event_sender.send(
+                        RunnerStatusUpdated(
+                            runner_id=runner_id, runner_status=current_status
+                        )
+                    )
+
+                    try:
+                        image_index = 0
+                        for response in generate_image(model=model, task=task_params):
+                            if (
+                                shard_metadata.device_rank
+                                == shard_metadata.world_size - 1
+                            ):
+                                match response:
+                                    case PartialImageResponse():
+                                        logger.info(
+                                            f"sending partial ImageChunk {response.partial_index}/{response.total_partials}"
+                                        )
+                                        _process_image_response(
+                                            response,
+                                            command_id,
+                                            shard_metadata,
+                                            event_sender,
+                                            image_index,
+                                        )
+                                    case ImageGenerationResponse():
+                                        logger.info("sending final ImageChunk")
+                                        _process_image_response(
+                                            response,
+                                            command_id,
+                                            shard_metadata,
+                                            event_sender,
+                                            image_index,
+                                        )
+                                        image_index += 1
+                    except Exception as e:
+                        if shard_metadata.device_rank == shard_metadata.world_size - 1:
+                            event_sender.send(
+                                ChunkGenerated(
+                                    command_id=command_id,
                                    chunk=ErrorChunk(
                                        model=shard_metadata.model_card.model_id,
                                        finish_reason="error",
@@ -415,7 +476,7 @@ def main(
                RunnerStatusUpdated(runner_id=runner_id, runner_status=current_status)
            )
            if isinstance(current_status, RunnerShutdown):
-                del inference_model, image_model, tokenizer, group
+                del model, tokenizer, group
                mx.clear_cache()
                import gc

@@ -524,54 +585,6 @@ def parse_thinking_models(
        yield response


-def _run_image_task(
-    task: ImageGeneration | ImageEdits,
-    image_model: DistributedImageModel,
-    shard_metadata: ShardMetadata,
-    event_sender: MpSender[Event],
-    cancel_receiver: MpReceiver[TaskId],
-    cancelled_tasks: set[TaskId],
-) -> None:
-    task_id = task.task_id
-    command_id = task.command_id
-
-    def check_cancelled(task_id: TaskId = task_id) -> bool:
-        cancelled_tasks.update(cancel_receiver.collect())
-        return (task_id in cancelled_tasks) or (
-            TaskId("CANCEL_CURRENT_TASK") in cancelled_tasks
-        )
-
-    image_index = 0
-    for response in generate_image(
-        model=image_model,
-        task=task.task_params,
-        cancel_checker=check_cancelled,
-    ):
-        if shard_metadata.device_rank == shard_metadata.world_size - 1:
-            match response:
-                case PartialImageResponse():
-                    logger.info(
-                        f"sending partial ImageChunk {response.partial_index}/{response.total_partials}"
-                    )
-                    _process_image_response(
-                        response,
-                        command_id,
-                        shard_metadata,
-                        event_sender,
-                        image_index,
-                    )
-                case ImageGenerationResponse():
-                    logger.info("sending final ImageChunk")
-                    _process_image_response(
-                        response,
-                        command_id,
-                        shard_metadata,
-                        event_sender,
-                        image_index,
-                    )
-                    image_index += 1
-
-
 def _send_image_chunk(
    encoded_data: str,
    command_id: CommandId,
--- a/src/exo/worker/runner/runner_supervisor.py
+++ b/src/exo/worker/runner/runner_supervisor.py
@@ -49,12 +49,10 @@ class RunnerSupervisor:
    _ev_recv: MpReceiver[Event]
    _task_sender: MpSender[Task]
    _event_sender: Sender[Event]
-    _cancel_sender: MpSender[TaskId]
-    _tg: TaskGroup = field(default_factory=create_task_group, init=False)
+    _tg: TaskGroup | None = field(default=None, init=False)
    status: RunnerStatus = field(default_factory=RunnerIdle, init=False)
    pending: dict[TaskId, anyio.Event] = field(default_factory=dict, init=False)
    completed: set[TaskId] = field(default_factory=set, init=False)
-    cancelled: set[TaskId] = field(default_factory=set, init=False)

    @classmethod
    def create(
@@ -65,8 +63,8 @@ class RunnerSupervisor:
        initialize_timeout: float = 400,
    ) -> Self:
        ev_send, ev_recv = mp_channel[Event]()
+        # A task is kind of a runner command
        task_sender, task_recv = mp_channel[Task]()
-        cancel_sender, cancel_recv = mp_channel[TaskId]()

        runner_process = Process(
            target=entrypoint,
@@ -74,7 +72,6 @@ class RunnerSupervisor:
                bound_instance,
                ev_send,
                task_recv,
-                cancel_recv,
                logger,
            ),
            daemon=True,
@@ -89,7 +86,6 @@ class RunnerSupervisor:
            initialize_timeout=initialize_timeout,
            _ev_recv=ev_recv,
            _task_sender=task_sender,
-            _cancel_sender=cancel_sender,
            _event_sender=event_sender,
        )

@@ -97,41 +93,37 @@ class RunnerSupervisor:

    async def run(self):
        self.runner_process.start()
-        async with self._tg as tg:
+        async with create_task_group() as tg:
+            self._tg = tg
            tg.start_soon(self._forward_events)

-        with anyio.CancelScope(shield=True), contextlib.suppress(ClosedResourceError):
-            await self._cancel_sender.send_async(TaskId("CANCEL_CURRENT_TASK"))
+        self._ev_recv.close()
+        self._task_sender.close()
+        self._event_sender.close()
+        await to_thread.run_sync(self.runner_process.join, 30)
+        if not self.runner_process.is_alive():
+            return

-            self._ev_recv.close()
-            self._task_sender.close()
-            self._event_sender.close()
-            self._cancel_sender.close()
+        # This is overkill but it's not technically bad, just unnecessary.
+        logger.warning("Runner process didn't shutdown succesfully, terminating")
+        self.runner_process.terminate()
+        await to_thread.run_sync(self.runner_process.join, 5)
+        if not self.runner_process.is_alive():
+            return

-            await to_thread.run_sync(self.runner_process.join, 10)
-            if not self.runner_process.is_alive():
-                return
+        logger.critical("Runner process didn't respond to SIGTERM, killing")
+        self.runner_process.kill()

-            # This is overkill but it's not technically bad, just unnecessary.
-            logger.warning("Runner process didn't shutdown succesfully, terminating")
-            self.runner_process.terminate()
-            await to_thread.run_sync(self.runner_process.join, 5)
-            if not self.runner_process.is_alive():
-                return
+        await to_thread.run_sync(self.runner_process.join, 5)
+        if not self.runner_process.is_alive():
+            return

-            logger.critical("Runner process didn't respond to SIGTERM, killing")
-            self.runner_process.kill()
+        logger.critical(
+            "Runner process didn't respond to SIGKILL. System resources may have leaked"
+        )

-            await to_thread.run_sync(self.runner_process.join, 5)
-            if not self.runner_process.is_alive():
-                return
-
-            logger.critical(
-                "Runner process didn't respond to SIGKILL. System resources may have leaked"
-            )
-
-    async def shutdown(self):
-        await self._cancel_sender.send_async(TaskId("CANCEL_CURRENT_TASK"))
+    def shutdown(self):
+        assert self._tg
        self._tg.cancel_scope.cancel()

    async def start_task(self, task: Task):
@@ -139,7 +131,6 @@ class RunnerSupervisor:
            logger.info(
                f"Skipping invalid task {task} as it has already been completed"
            )
-            return
        logger.info(f"Starting task {task}")
        event = anyio.Event()
        self.pending[task.task_id] = event
@@ -149,13 +140,7 @@ class RunnerSupervisor:
            logger.warning(f"Task {task} dropped, runner closed communication.")
            return
        await event.wait()
-
-    async def cancel_task(self, task_id: TaskId):
-        if task_id in self.completed:
-            logger.info(f"Unable to cancel {task_id} as it has been completed")
-            return
-        self.cancelled.add(task_id)
-        await self._cancel_sender.send_async(task_id)
+        logger.info(f"Finished task {task}")

    async def _forward_events(self):
        with self._ev_recv as events:
@@ -221,4 +206,4 @@ class RunnerSupervisor:
                runner_status=RunnerFailed(error_message=f"Terminated ({cause})"),
            )
        )
-        await self.shutdown()
+        self.shutdown()
--- a/uv.lock
+++ b/uv.lock
@@ -376,8 +376,8 @@ dependencies = [
    { name = "hypercorn", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "loguru", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "mflux", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", extra = ["cpu"], marker = "sys_platform == 'linux'" },
+    { name = "mlx", version = "0.30.3", source = { registry = "https://pypi.org/simple" }, extra = ["cpu"], marker = "sys_platform == 'linux'" },
+    { name = "mlx", version = "0.30.4.dev20260121+fbe306f9", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git#fbe306f92a47d9b887ee7af2e3af6f1b9e28e663" }, marker = "sys_platform == 'darwin'" },
    { name = "mlx-lm", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "openai-harmony", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "pillow", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -412,8 +412,8 @@ requires-dist = [
    { name = "huggingface-hub", specifier = ">=0.33.4" },
    { name = "hypercorn", specifier = ">=0.18.0" },
    { name = "loguru", specifier = ">=0.7.3" },
+    { name = "mlx", marker = "sys_platform == 'darwin'", git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git" },
    { name = "mflux", specifier = "==0.15.4" },
-    { name = "mlx", marker = "sys_platform == 'darwin'", specifier = "==0.30.3" },
    { name = "mlx", extras = ["cpu"], marker = "sys_platform == 'linux'", specifier = "==0.30.3" },
    { name = "mlx-lm", git = "https://github.com/AlexCheema/mlx-lm.git?rev=fix-transformers-5.0.0rc2" },
    { name = "openai-harmony", specifier = ">=0.0.8" },
@@ -994,8 +994,8 @@ dependencies = [
    { name = "fonttools", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "huggingface-hub", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "matplotlib", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", extra = ["cuda13"], marker = "sys_platform == 'linux'" },
+    { name = "mlx", version = "0.30.3", source = { registry = "https://pypi.org/simple" }, extra = ["cuda13"], marker = "sys_platform == 'linux'" },
+    { name = "mlx", version = "0.30.4.dev20260121+fbe306f9", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git#fbe306f92a47d9b887ee7af2e3af6f1b9e28e663" }, marker = "sys_platform == 'darwin'" },
    { name = "numpy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "opencv-python", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "piexif", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -1022,18 +1022,12 @@ wheels = [
 name = "mlx"
 version = "0.30.3"
 source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "mlx-metal", marker = "sys_platform == 'darwin'" },
+resolution-markers = [
+    "sys_platform == 'linux'",
 ]
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d0/22/42935d593fe82d3b98eb9d60e4620ed99703886635106f89d407c68f33bc/mlx-0.30.3-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:743fac1e4f9e8e46c8262943c643a31139c255cdb256c99ad496958215ccac1e", size = 569344, upload-time = "2026-01-14T01:16:54.847Z" },
-    { url = "https://files.pythonhosted.org/packages/7d/27/f2e7a5236289d45315d0215e8553b4dd7e2faaba3bcb5025b34b25d5ab66/mlx-0.30.3-cp313-cp313-macosx_15_0_arm64.whl", hash = "sha256:3b04ae81655aa0e63a6e8f2c749de3bbce64cf5b168ae10f39ed086dfa99e7f8", size = 569345, upload-time = "2026-01-14T01:16:56.564Z" },
-    { url = "https://files.pythonhosted.org/packages/01/41/06b042457f51952456e9bb46b2c6e205ab3a28fc52d6751b5787fdb762b2/mlx-0.30.3-cp313-cp313-macosx_26_0_arm64.whl", hash = "sha256:ba9b5bdb1e929cc130af72efd7f73508c0f4e526d224489af7ec1c6419564659", size = 569213, upload-time = "2026-01-14T05:52:10.86Z" },
    { url = "https://files.pythonhosted.org/packages/ec/1e/f62c98fc0d2d878ee4235671f9d406b13cc9240493ba6fcfde2f72c2ff83/mlx-0.30.3-cp313-cp313-manylinux_2_35_aarch64.whl", hash = "sha256:dfe5c5b64e55398a22100804abbf9681996b03129e720e36b1727ed704db12b5", size = 617309, upload-time = "2026-01-14T01:16:57.58Z" },
    { url = "https://files.pythonhosted.org/packages/e9/62/811f064693449de740350d27793ce39343a460305ec8d878c318b80921d0/mlx-0.30.3-cp313-cp313-manylinux_2_35_x86_64.whl", hash = "sha256:a3364924610929936e6aaf13c71106161258e5a5d3f7813a64c07cc2435f9f55", size = 659521, upload-time = "2026-01-14T01:16:58.719Z" },
-    { url = "https://files.pythonhosted.org/packages/82/e2/6e551bd48fb350fbf0ee4cc5cd09485437d260b8f4937f22d8623e14687a/mlx-0.30.3-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:2c27fd8daaae14ca6cf407fcd236006a6e968f7708c8f61a2709116f2e754852", size = 571920, upload-time = "2026-01-14T01:16:59.683Z" },
-    { url = "https://files.pythonhosted.org/packages/82/c0/561d1c9d3d12830b0e7fdcbd807585ef20909e398d4bcdbf25e4367543eb/mlx-0.30.3-cp314-cp314-macosx_15_0_arm64.whl", hash = "sha256:b755fd4ed4b6a2ae4dee3766b5a2ea52fcbe83ebd1cf018458e18b74139409f3", size = 571921, upload-time = "2026-01-14T01:17:00.868Z" },
-    { url = "https://files.pythonhosted.org/packages/42/1a/fb573fc2edc22a777fa254ff5c0c886ffd2c88aeb1f21c45778ef170f990/mlx-0.30.3-cp314-cp314-macosx_26_0_arm64.whl", hash = "sha256:7e352c0369a2f7e54d4f317b434eab3333918ea9edde1c43c61d36386b6f76bf", size = 571732, upload-time = "2026-01-14T05:52:11.893Z" },
    { url = "https://files.pythonhosted.org/packages/9e/db/d0083e8f2205b3b2dcd9670eb6f0d6c1b7cbfea6b01a1f8bff39142edf44/mlx-0.30.3-cp314-cp314-manylinux_2_35_aarch64.whl", hash = "sha256:00ac867f3d003c1477a66a579442c2040ba7ea43ce3c174490d1f8bf379606bd", size = 619635, upload-time = "2026-01-14T01:17:01.812Z" },
    { url = "https://files.pythonhosted.org/packages/ab/90/ab0b93ff0e76da4fe0e878722c76a308cfb950b044a4676e9617276d8ccd/mlx-0.30.3-cp314-cp314-manylinux_2_35_x86_64.whl", hash = "sha256:5be7d0329036f09c6ed003ea3e307e97e3144f20a3e4711b01810d7d5013cf2c", size = 659652, upload-time = "2026-01-14T01:17:02.915Z" },
 ]
@@ -1046,6 +1040,14 @@ cuda13 = [
    { name = "mlx-cuda-13", marker = "sys_platform == 'linux'" },
 ]

+[[package]]
+name = "mlx"
+version = "0.30.4.dev20260121+fbe306f9"
+source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git#fbe306f92a47d9b887ee7af2e3af6f1b9e28e663" }
+resolution-markers = [
+    "sys_platform == 'darwin'",
+]
+
 [[package]]
 name = "mlx-cpu"
 version = "0.30.3"
@@ -1076,7 +1078,7 @@ version = "0.30.4"
 source = { git = "https://github.com/AlexCheema/mlx-lm.git?rev=fix-transformers-5.0.0rc2#a5daf2b894f31793dfaef0fdf9bc3ed683176ad6" }
 dependencies = [
    { name = "jinja2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", marker = "sys_platform == 'darwin'" },
+    { name = "mlx", version = "0.30.4.dev20260121+fbe306f9", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git#fbe306f92a47d9b887ee7af2e3af6f1b9e28e663" }, marker = "sys_platform == 'darwin'" },
    { name = "numpy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "protobuf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "pyyaml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -1084,16 +1086,6 @@ dependencies = [
    { name = "transformers", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]

-[[package]]
-name = "mlx-metal"
-version = "0.30.3"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/f6/63/4d8f6fefb507c028df4454dabfe8d8e0ad2961bb06510b6aca23d2d5b2be/mlx_metal-0.30.3-py3-none-macosx_14_0_arm64.whl", hash = "sha256:6276312b02353714c7c6515169569fe1c4bebe3229c8ecf1fdb375a13e78c966", size = 37716245, upload-time = "2026-01-14T01:16:34.838Z" },
-    { url = "https://files.pythonhosted.org/packages/35/91/1d452e48a4bb4958844fd3bb28ae31b8de110549c009ebec5024ce27ebf3/mlx_metal-0.30.3-py3-none-macosx_15_0_arm64.whl", hash = "sha256:c096c0a3428f3f96a06220f97a36f9528b18bc05173f821eb05bc8458e723fa8", size = 37712125, upload-time = "2026-01-14T01:16:38.619Z" },
-    { url = "https://files.pythonhosted.org/packages/fe/36/7a3cbca85542b5ca4faf871e35927f43aa0e3fc830ae5b699780fe723677/mlx_metal-0.30.3-py3-none-macosx_26_0_arm64.whl", hash = "sha256:69068533bd1ee8b0379ce5de57ed5fd313577a10ecab58e1332fd1ff7248a75e", size = 46488962, upload-time = "2026-01-14T05:52:04.523Z" },
-]
-
 [[package]]
 name = "more-itertools"
 version = "10.8.0"
Author	SHA1	Message	Date
Alex Cheema	281aaeb013	better message for configuring local network macOS app	2026-01-24 06:32:15 -08:00
Alex Cheema	10fdc439a5	Merge branch 'main' into releases/v1.0.65	2026-01-24 05:36:15 -08:00
Evan Quiney	d93db3d6bf	re enable the evil network script (#1277 ) seems like we still need the interfaces to be routable for mdns. at least we're not dependent on this behaviour anymore.	2026-01-24 13:36:06 +00:00
Alex Cheema	78a8c06d57	Add 30s delay to wait for macOS network setup Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-01-23 15:29:22 -08:00
Alex Cheema	4c0c6dcae9	Merge branch 'main' into releases/v1.0.65	2026-01-23 20:48:51 +00:00
Alex Cheema	d885600a4c	Merge branch 'main' into releases/v1.0.64	2026-01-23 20:40:26 +00:00
Alex Cheema	55b67e2be2	Merge branch 'main' into releases/v1.0.64	2026-01-23 01:40:20 +00:00
Ryuichi Leo Takashige	30cfad9b68	Use custom fork	2026-01-22 22:19:35 +00:00