From a0256414e9769ef9412fe0e77e8bfb4adbffeba9 Mon Sep 17 00:00:00 2001 From: Alexander Matveev Date: Fri, 26 Sep 2025 15:25:58 -0700 Subject: [PATCH] [Bugfix] Fix hang with DP+EP on B200 Signed-off-by: Alexander Matveev --- vllm/v1/worker/gpu_worker.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/v1/worker/gpu_worker.py b/vllm/v1/worker/gpu_worker.py index 8c75e8914857b..c9a7d2009ebe2 100644 --- a/vllm/v1/worker/gpu_worker.py +++ b/vllm/v1/worker/gpu_worker.py @@ -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)