From 1d5e397aa4d94d0ccc1c9dbad533afa5cb60bb69 Mon Sep 17 00:00:00 2001 From: William Lin Date: Tue, 10 Sep 2024 16:46:08 -0700 Subject: [PATCH] [Core/Bugfix] pass VLLM_ATTENTION_BACKEND to ray workers (#8172) --- vllm/executor/ray_gpu_executor.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/vllm/executor/ray_gpu_executor.py b/vllm/executor/ray_gpu_executor.py index 1359a0d3..b124fe2e 100644 --- a/vllm/executor/ray_gpu_executor.py +++ b/vllm/executor/ray_gpu_executor.py @@ -242,6 +242,9 @@ class RayGPUExecutor(DistributedGPUExecutor): VLLM_INSTANCE_ID, "VLLM_TRACE_FUNCTION": str(envs.VLLM_TRACE_FUNCTION), + **({ + "VLLM_ATTENTION_BACKEND": envs.VLLM_ATTENTION_BACKEND + } if envs.VLLM_ATTENTION_BACKEND is not None else {}) }, ) for (node_id, _) in worker_node_and_gpu_ids] self._env_vars_for_all_workers = (