THUDM / THUDM/slime

Run qwen3-4b example hangs on actor model update_weights

Open
#950 4 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
8.5k
Forks
1.3k
Avg merge
5h 36m
Merged PRs (30d)
22

Description

When I use official case run qwen3-4b rl example(https://github.com/THUDM/slime/blob/main/scripts/run-qwen3-4B.sh), found the following issues on update weights:
pdate weights: 6%|▋ | 1/16 [11:01<2:45:20, 661.36s/it]
Traceback (most recent call last):
File "/root/slime/train.py", line 119, in
train(args)
File "/root/slime/train.py", line 34, in train
actor_model.update_weights()
File "/root/slime/slime/ray/actor_group.py", line 124, in update_weights
return ray.get([actor.update_weights.remote() for actor in self._actor_handlers])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/ray/_private/auto_init_hook.py", line 22, in auto_init_wrapper
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/ray/_private/client_mode_hook.py", line 104, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/ray/_private/worker.py", line 2882, in get
values, debugger_breakpoint = worker.get_objects(object_refs, timeout=timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/ray/_private/worker.py", line 970, in get_objects
raise value
ray.exceptions.ActorUnavailableError: The actor 480ce8b4cb84b1cb6a0b66ba02000000 is unavailable: The actor is temporarily unavailable: RpcError: RPC Error message: Socket closed; RPC Error details: rpc_code: 14. The task may or may not have been executed on the actor.

I use sglang 0.5.5 and slime commit f47796226cf6d8e5810c6630e4214634c80aae0a

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the failure with scripts/run-qwen3-4B.sh using the reported slime commit and sglang 0.5.5. Inspect train.py:34 and slime/ray/actor_group.py:124 around actor_model.update_weights(), then trace the unavailable actor; done means the example completes weight updates without ActorUnavailableError.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
distributed-systems, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.