[Bugfix] Fix hang with DP+EP on B200
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
This commit is contained in:
@ -488,7 +488,7 @@ class Worker(WorkerBase):
|
||||
sort_by="self_cuda_time_total"))
|
||||
|
||||
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:
|
||||
return self.model_runner.add_lora(lora_request)
|
||||
|
||||
Reference in New Issue
Block a user