remove mdns discovered peers from appearing in state

- Update README tagline from "Run your own AI cluster at home with
everyday devices" to "Run frontier AI locally"

README.md

@@ -5,7 +5,7 @@
   <img alt="exo logo" src="/docs/imgs/exo-logo-transparent.png" width="50%" height="50%">
 </picture>
 
-exo: Run your own AI cluster at home with everyday devices. Maintained by [exo labs](https://x.com/exolabs).
+exo: Run frontier AI locally. 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>

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 30
-
         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")

pyproject.toml

@@ -17,8 +17,8 @@ dependencies = [
     "loguru>=0.7.3",
     "exo_pyo3_bindings", # rust bindings
     "anyio==4.11.0",
-    "mlx @ git+https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git; sys_platform == 'darwin'",
-    "mlx[cpu]==0.30.3; sys_platform == 'linux'",
+    "mlx==0.30.4; sys_platform == 'darwin'",
+    "mlx[cpu]==0.30.4; sys_platform == 'linux'",
     "mlx-lm",
     "tiktoken>=0.12.0", # required for kimi k2 tokenizer
     "hypercorn>=0.18.0",

src/exo/main.py

@@ -90,7 +90,6 @@ class Node:
             worker = Worker(
                 node_id,
                 session_id,
-                connection_message_receiver=router.receiver(topics.CONNECTION_MESSAGES),
                 global_event_receiver=router.receiver(topics.GLOBAL_EVENTS),
                 local_event_sender=router.sender(topics.LOCAL_EVENTS),
                 command_sender=router.sender(topics.COMMANDS),
@@ -227,9 +226,6 @@ class Node:
                         self.worker = Worker(
                             self.node_id,
                             result.session_id,
-                            connection_message_receiver=self.router.receiver(
-                                topics.CONNECTION_MESSAGES
-                            ),
                             global_event_receiver=self.router.receiver(
                                 topics.GLOBAL_EVENTS
                             ),

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

@@ -165,7 +165,6 @@ 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}"
                 )

src/exo/worker/main.py

@@ -7,7 +7,6 @@ from anyio import CancelScope, create_task_group, fail_after
 from anyio.abc import TaskGroup
 from loguru import logger
 
-from exo.routing.connection_message import ConnectionMessage, ConnectionMessageType
 from exo.shared.apply import apply
 from exo.shared.models.model_cards import ModelId
 from exo.shared.types.api import ImageEditsInternalParams
@@ -57,7 +56,6 @@ class Worker:
         node_id: NodeId,
         session_id: SessionId,
         *,
-        connection_message_receiver: Receiver[ConnectionMessage],
         global_event_receiver: Receiver[ForwarderEvent],
         local_event_sender: Sender[ForwarderEvent],
         # This is for requesting updates. It doesn't need to be a general command sender right now,
@@ -74,7 +72,6 @@ class Worker:
         self.event_index_counter = event_index_counter
         self.command_sender = command_sender
         self.download_command_sender = download_command_sender
-        self.connection_message_receiver = connection_message_receiver
         self.event_buffer = OrderedBuffer[Event]()
         self.out_for_delivery: dict[EventId, ForwarderEvent] = {}
 
@@ -105,7 +102,6 @@ class Worker:
             tg.start_soon(info_gatherer.run)
             tg.start_soon(self._forward_info, info_recv)
             tg.start_soon(self.plan_step)
-            tg.start_soon(self._connection_message_event_writer)
             tg.start_soon(self._resend_out_for_delivery)
             tg.start_soon(self._event_applier)
             tg.start_soon(self._forward_events)
@@ -279,41 +275,6 @@ class Worker:
         instance = self.state.instances[task.instance_id]
         return instance.shard_assignments.node_to_runner[self.node_id]
 
-    async def _connection_message_event_writer(self):
-        with self.connection_message_receiver as connection_messages:
-            async for msg in connection_messages:
-                await self.event_sender.send(
-                    self._convert_connection_message_to_event(msg)
-                )
-
-    def _convert_connection_message_to_event(self, msg: ConnectionMessage):
-        match msg.connection_type:
-            case ConnectionMessageType.Connected:
-                return TopologyEdgeCreated(
-                    conn=Connection(
-                        source=self.node_id,
-                        sink=msg.node_id,
-                        edge=SocketConnection(
-                            sink_multiaddr=Multiaddr(
-                                address=f"/ip4/{msg.remote_ipv4}/tcp/{msg.remote_tcp_port}"
-                            ),
-                        ),
-                    ),
-                )
-
-            case ConnectionMessageType.Disconnected:
-                return TopologyEdgeDeleted(
-                    conn=Connection(
-                        source=self.node_id,
-                        sink=msg.node_id,
-                        edge=SocketConnection(
-                            sink_multiaddr=Multiaddr(
-                                address=f"/ip4/{msg.remote_ipv4}/tcp/{msg.remote_tcp_port}"
-                            ),
-                        ),
-                    ),
-                )
-
     async def _nack_request(self, since_idx: int) -> None:
         # We request all events after (and including) the missing index.
         # This function is started whenever we receive an event that is out of sequence.