Merge remote-tracking branch 'origin/main' into releases/v1.0.67

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

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/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
@@ -80,7 +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")

pyproject.toml

@@ -17,8 +17,8 @@ dependencies = [
     "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 @ git+https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git; sys_platform == 'darwin'",
+    "mlx[cpu]==0.30.3; sys_platform == 'linux'",
     "mlx-lm",
     "tiktoken>=0.12.0", # required for kimi k2 tokenizer
     "hypercorn>=0.18.0",

src/exo/shared/models/model_cards.py

@@ -1,5 +1,5 @@
 from enum import Enum
-from typing import Annotated, Any
+from typing import Annotated
 
 import aiofiles
 import aiofiles.os as aios
@@ -7,14 +7,7 @@ import tomlkit
 from anyio import Path, open_file
 from huggingface_hub import model_info
 from loguru import logger
-from pydantic import (
-    AliasChoices,
-    BaseModel,
-    Field,
-    PositiveInt,
-    field_validator,
-    model_validator,
-)
+from pydantic import BaseModel, Field, PositiveInt, field_validator
 
 from exo.shared.constants import EXO_ENABLE_IMAGE_MODELS
 from exo.shared.types.common import ModelId
@@ -718,18 +711,15 @@ if EXO_ENABLE_IMAGE_MODELS:
 class ConfigData(BaseModel):
     model_config = {"extra": "ignore"}  # Allow unknown fields
 
-    architectures: list[str] | None = None
+    # Common field names for number of layers across different architectures
+    num_hidden_layers: Annotated[int, Field(ge=0)] | None = None
+    num_layers: Annotated[int, Field(ge=0)] | None = None
+    n_layer: Annotated[int, Field(ge=0)] | None = None
+    n_layers: Annotated[int, Field(ge=0)] | None = None  # Sometimes used
+    num_decoder_layers: Annotated[int, Field(ge=0)] | None = None  # Transformer models
+    decoder_layers: Annotated[int, Field(ge=0)] | None = None  # Some architectures
     hidden_size: Annotated[int, Field(ge=0)] | None = None
-    layer_count: int = Field(
-        validation_alias=AliasChoices(
-            "num_hidden_layers",
-            "num_layers",
-            "n_layer",
-            "n_layers",
-            "num_decoder_layers",
-            "decoder_layers",
-        )
-    )
+    architectures: list[str] | None = None
 
     @property
     def supports_tensor(self) -> bool:
@@ -744,27 +734,25 @@ class ConfigData(BaseModel):
             ["GptOssForCausalLM"],
         ]
 
-    @model_validator(mode="before")
-    @classmethod
-    def defer_to_text_config(cls, data: dict[str, Any]):
-        text_config = data.get("text_config")
-        if text_config is None:
-            return data
+    @property
+    def layer_count(self) -> int:
+        # Check common field names for layer count
+        layer_fields = [
+            self.num_hidden_layers,
+            self.num_layers,
+            self.n_layer,
+            self.n_layers,
+            self.num_decoder_layers,
+            self.decoder_layers,
+        ]
 
-        for field in [
-            "architectures",
-            "hidden_size",
-            "num_hidden_layers",
-            "num_layers",
-            "n_layer",
-            "n_layers",
-            "num_decoder_layers",
-            "decoder_layers",
-        ]:
-            if (val := text_config.get(field)) is not None:  # pyright: ignore[reportAny]
-                data[field] = val
+        for layer_count in layer_fields:
+            if layer_count is not None:
+                return layer_count
 
-        return data
+        raise ValueError(
+            f"No layer count found in config.json: {self.model_dump_json()}"
+        )
 
 
 async def get_config_data(model_id: ModelId) -> ConfigData:

src/exo/worker/engines/mlx/utils_mlx.py

@@ -165,6 +165,7 @@ def mlx_distributed_init(
 
                 jaccl_coordinator = jaccl_coordinators[bound_instance.bound_node_id]
 
+                # TODO: update once upstream fixes
                 logger.info(
                     f"rank {rank} MLX_IBV_DEVICES: {coordination_file} with devices: {jaccl_devices_json}"
                 )

tmp/set_rdma_network_config.sh

@@ -1,49 +0,0 @@
-#!/usr/bin/env bash
-
-set -euo pipefail
-
-PREFS="/Library/Preferences/SystemConfiguration/preferences.plist"
-
-# Remove bridge0 interface
-ifconfig bridge0 &>/dev/null && {
-  ifconfig bridge0 | grep -q 'member' && {
-    ifconfig bridge0 | awk '/member/ {print $2}' | xargs -n1 ifconfig bridge0 deletem 2>/dev/null || true
-  }
-  ifconfig bridge0 destroy 2>/dev/null || true
-}
-
-# Remove Thunderbolt Bridge from VirtualNetworkInterfaces in preferences.plist
-/usr/libexec/PlistBuddy -c "Delete :VirtualNetworkInterfaces:Bridge:bridge0" "$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