xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-23 05:50:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix hang with DP+EP on B200

Browse Source 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
This commit is contained in:
Alexander Matveev 2025-09-26 15:25:58 -07:00
parent cf89202855
commit a0256414e9
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/worker/gpu_worker.py
View File

@ -488,7 +488,7 @@ class Worker(WorkerBase):
sort_by="self_cuda_time_total")) sort_by="self_cuda_time_total"))
def execute_dummy_batch(self) -> None: def execute_dummy_batch(self) -> None:
self.model_runner._dummy_run(1, uniform_decode=True) self.model_runner._dummy_run(16, uniform_decode=True)
def add_lora(self, lora_request: LoRARequest) -> bool: def add_lora(self, lora_request: LoRARequest) -> bool:
return self.model_runner.add_lora(lora_request) return self.model_runner.add_lora(lora_request)