squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[BugFix]: fix engine timeout due to request abort (#6255)

Browse Source 
Signed-off-by: yatta zhang <ytzhang01@foxmail.com>
Signed-off-by: zhangyuntao.dev <zhangyuntao.dev@bytedance.com>
Co-authored-by: zhangyuntao.dev <zhangyuntao.dev@bytedance.com>
This commit is contained in:
pushan 2024-07-11 21:46:31 +08:00 committed by GitHub
parent 3963a5335b
commit 546b101fa0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/engine/async_llm_engine.py
View File

@ -553,11 +553,13 @@ class AsyncLLMEngine:
request_outputs = await self.engine.step_async(virtual_engine) request_outputs = await self.engine.step_async(virtual_engine)
# Put the outputs into the corresponding streams. # Put the outputs into the corresponding streams.
finished = True
for request_output in request_outputs: for request_output in request_outputs:
self._request_tracker.process_request_output( self._request_tracker.process_request_output(
request_output, verbose=self.log_requests) request_output, verbose=self.log_requests)
finished = finished and request_output.finished
return len(request_outputs) > 0 return not finished
async def _engine_abort(self, request_ids: Iterable[str]): async def _engine_abort(self, request_ids: Iterable[str]):
if self.engine_use_ray: if self.engine_use_ray: