Can someone help this noob (2 node cluster unresponsive)

[NotReallyADeveloper]

Am trying to cluster a Mac Mini pro and a Mac Mini Studio Pro Max, connected via an Apple Thunderbolt 5 cable.

Nothing wrong with the connectivity, and can use Llama 3.2 3B without issues when using a single computer. But as soon as I add a second node, the LLM stops responding completely.

MLX is installed and configured on both.

What am I missing here?

[Sunchy389]

I have the same question. how to solve it?

[hefish]

i have the same . logs show that grpc has some error. so node communications may have troubles.

Traceback (most recent call last):
File "/Users/hefish/works/exo/exo/orchestration/node.py", line 606, in send_status_to_peer
await asyncio.wait_for(peer.send_opaque_status(request_id, status), timeout=15.0)
File "/Users/hefish/miniconda3/envs/exo/lib/python3.12/asyncio/tasks.py", line 520, in wait_for
return await fut
^^^^^^^^^
File "/Users/hefish/works/exo/exo/networking/grpc/grpc_peer_handle.py", line 204, in send_opaque_status
await asyncio.wait_for(self.stub.SendOpaqueStatus(request), timeout=10.0)
File "/Users/hefish/miniconda3/envs/exo/lib/python3.12/asyncio/tasks.py", line 520, in wait_for
return await fut
^^^^^^^^^
File "/Users/hefish/miniconda3/envs/exo/lib/python3.12/site-packages/grpc/aio/_call.py", line 327, in
await
raise _create_rpc_error(
grpc.aio._call.AioRpcError: <AioRpcError of RPC that terminated with:
status = StatusCode.UNAVAILABLE
details = "Received RST_STREAM with error code 7"
debug_error_string = "UNKNOWN:Error received from peer {grpc_message:"Received RST_STREAM with error
code 7", grpc_status:14, created_time:"2025-03-20T08:29:02.634141+08:00"}"

[hefish]

我发现把 grpc, grpc-tools 两个模块降级到 1.70 ，即可解决。 查看一下最新版的grpc，是2025年3月11日更新到1.71的。所以我回想起来 2月份的时候还是好的。 看起来是grpc的组件升级导致的。

[Sunchy389]

降级是这个语句么 "grpcio==1.67.0",
"grpcio-tools==1.67.0",