[vllm] fix: catch exception of vllm async engine (#3789)

### What does this PR do?

vllm async engine error is not catched, which will cause the whole async
loop keep waiting results and hang.

this pr fix the this issue by send the picked error by zeromq, and raise
if received.




| before | after |
| --- | --- |
| <img width="2148" height="1308" alt="image"
src="https://github.com/user-attachments/assets/68f565ab-ffa5-4d52-84d6-3e7a2a7cf16a"
/>| <img width="2278" height="1278" alt="image"
src="https://github.com/user-attachments/assets/ce2a647d-3d18-4f57-ad40-054ea97e87d7"
/> |


### Checklist Before Starting

- [ ] Search for similar PRs. Paste at least one query link here: ...
- [ ] Format the PR title as `[{modules}] {type}: {description}` (This
will be checked by the CI)
- `{modules}` include `fsdp`, `megatron`, `sglang`, `vllm`, `rollout`,
`trainer`, `ci`, `training_utils`, `recipe`, `hardware`, `deployment`,
`ray`, `worker`, `single_controller`, `misc`, `perf`, `model`, `algo`,
`env`, `tool`, `ckpt`, `doc`, `data`
- If this PR involves multiple modules, separate them with `,` like
`[megatron, fsdp, doc]`
  - `{type}` is in `feat`, `fix`, `refactor`, `chore`, `test`
- If this PR breaks any API (CLI arguments, config, function signature,
etc.), add `[BREAKING]` to the beginning of the title.
  - Example: `[BREAKING][fsdp, megatron] feat: dynamic batching`

### Test

> For changes that can not be tested by CI (e.g., algorithm
implementation, new model support), validate by experiment(s) and show
results like training curve plots, evaluation results, etc.

### API and Usage Example

> Demonstrate how the API changes if any, and provide usage example(s)
if possible.

```python
# Add code snippet or script demonstrating how to use this
```

### Design & Code Changes

> Demonstrate the high-level design if this PR is complex, and list the
specific changes.

### Checklist Before Submitting

> [!IMPORTANT]
> Please check all the following items before requesting a review,
otherwise the reviewer might deprioritize this PR for review.

- [ ] Read the [Contribute
Guide](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md).
- [ ] Apply [pre-commit
checks](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md#code-linting-and-formatting):
`pre-commit install && pre-commit run --all-files --show-diff-on-failure
--color=always`
- [ ] Add / Update [the
documentation](https://github.com/volcengine/verl/tree/main/docs).
- [ ] Add unit or end-to-end test(s) to [the CI
workflow](https://github.com/volcengine/verl/tree/main/.github/workflows)
to cover all the code. If not feasible, explain why: ...
- [ ] Once your PR is ready for CI, send a message in [the `ci-request`
channel](https://verl-project.slack.com/archives/C091TCESWB1) in [the
`verl` Slack
workspace](https://join.slack.com/t/verl-project/shared_invite/zt-3855yhg8g-CTkqXu~hKojPCmo7k_yXTQ).
(If not accessible, please try [the Feishu group
(飞书群)](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=772jd4f1-cd91-441e-a820-498c6614126a).)

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
杨睿
2025-10-17 09:50:34 +08:00
committed by GitHub
parent 4abae2d77a
commit 9078a533c6
2 changed files with 6 additions and 1 deletions

View File

@ -100,6 +100,10 @@ class ExternalZeroMQDistributedExecutor(Executor):
outputs = []
for socket in self.sockets:
outputs.append(pickle.loads(socket.recv()))
for output in outputs:
if isinstance(output, Exception):
raise output
return outputs
def check_health(self):

View File

@ -536,7 +536,8 @@ class vLLMAsyncRollout(BaseRollout):
await self.socket.send(pickle.dumps(result))
except Exception as e:
logger.exception(f"vLLMAsyncRollout _loop_forever error: {e}")
os._exit(-1)
await self.socket.send(pickle.dumps(e))
break
def _init_worker(self, all_kwargs: list[dict[str, Any]]):
"""Initialize worker engine."""