From 2c9b169c0ea426a3dcc3555ad0ba92dce12dce14 Mon Sep 17 00:00:00 2001 From: ltd0924 <32387785+ltd0924@users.noreply.github.com> Date: Tue, 2 Sep 2025 20:28:51 +0800 Subject: [PATCH] [BugFix] fix scheduler invalid (#3803) * [BugFix] fix max streaming tokens invalid * fix scheduler bug * fix scheduler bug --- fastdeploy/entrypoints/openai/api_server.py | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fastdeploy/entrypoints/openai/api_server.py b/fastdeploy/entrypoints/openai/api_server.py index 16d6e735b..f31cf32d4 100644 --- a/fastdeploy/entrypoints/openai/api_server.py +++ b/fastdeploy/entrypoints/openai/api_server.py @@ -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) @@ -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, )