Add RDMA caveats to README.md (#1316)

## Motivation

Running RDMA from source is not well documented as is. Several
surprising things that took time to debug internally too.

App should be updated to detect MacOS versions in future.

README.md

@@ -107,6 +107,10 @@ 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:**
@@ -230,7 +234,7 @@ 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).
 
-Note that on Mac Studio, you cannot use the Thunderbolt 5 port next to the Ethernet port.
+Please refer to the caveats for immediate troubleshooting.
 
 To enable RDMA on macOS, follow these steps:
 
@@ -247,6 +251,14 @@ 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

@@ -18,9 +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")

src/exo/shared/models/model_cards.py

@@ -1,5 +1,5 @@
 from enum import Enum
-from typing import Annotated
+from typing import Annotated, Any
 
 import aiofiles
 import aiofiles.os as aios
@@ -7,7 +7,14 @@ import tomlkit
 from anyio import Path, open_file
 from huggingface_hub import model_info
 from loguru import logger
-from pydantic import BaseModel, Field, PositiveInt, field_validator
+from pydantic import (
+    AliasChoices,
+    BaseModel,
+    Field,
+    PositiveInt,
+    field_validator,
+    model_validator,
+)
 
 from exo.shared.constants import EXO_ENABLE_IMAGE_MODELS
 from exo.shared.types.common import ModelId
@@ -711,15 +718,18 @@ if EXO_ENABLE_IMAGE_MODELS:
 class ConfigData(BaseModel):
     model_config = {"extra": "ignore"}  # Allow unknown fields
 
-    # 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
     architectures: list[str] | None = None
+    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",
+        )
+    )
 
     @property
     def supports_tensor(self) -> bool:
@@ -734,25 +744,27 @@ class ConfigData(BaseModel):
             ["GptOssForCausalLM"],
         ]
 
-    @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,
-        ]
+    @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
 
-        for layer_count in layer_fields:
-            if layer_count is not None:
-                return layer_count
+        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
 
-        raise ValueError(
-            f"No layer count found in config.json: {self.model_dump_json()}"
-        )
+        return data
 
 
 async def get_config_data(model_id: ModelId) -> ConfigData:

tmp/set_rdma_network_config.sh

@@ -0,0 +1,49 @@
+#!/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