Skip to content

[BugFix] fix scheduler invalid #3803

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Jiang-Jia-Jun merged 4 commits into from
Sep 2, 2025
+6 −4
Merged

[BugFix] fix scheduler invalid #3803

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
55deb9d
[BugFix] fix max streaming tokens invalid
ltd0924 Sep 2, 2025
e1e2731
fix scheduler bug
ltd0924 Sep 2, 2025
80858b0
Merge branch 'PaddlePaddle:develop' into bug
ltd0924 Sep 2, 2025
d2e0094
fix scheduler bug
ltd0924 Sep 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions fastdeploy/entrypoints/openai/api_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -487,7 +487,7 @@ def reset_scheduler():

if llm_engine is None:
return Response("Engine not loaded", status_code=500)
llm_engine.scheduler.reset()
llm_engine.engine.scheduler.reset()
return Response("Scheduler Reset Successfully", status_code=200)


Expand All @@ -505,11 +505,13 @@ def control_scheduler(request: ControlSchedulerRequest):
return JSONResponse(content=content.model_dump(), status_code=500)

if request.reset:
llm_engine.scheduler.reset()
llm_engine.engine.scheduler.reset()

if request.load_shards_num or request.reallocate_shard:
if hasattr(llm_engine.scheduler, "update_config") and callable(llm_engine.scheduler.update_config):
llm_engine.scheduler.update_config(
if hasattr(llm_engine.engine.scheduler, "update_config") and callable(
llm_engine.engine.scheduler.update_config
):
llm_engine.engine.scheduler.update_config(
load_shards_num=request.load_shards_num,
reallocate=request.reallocate_shard,
)
Expand Down
Loading