From b5815c8413b4e09ba6ccd9c41ea3f9fb2d057aa8 Mon Sep 17 00:00:00 2001 From: Woosuk Kwon Date: Fri, 8 Nov 2024 10:23:04 -0800 Subject: [PATCH] [V1] Fix non-cudagraph op name (#10166) Signed-off-by: Woosuk Kwon --- vllm/v1/worker/gpu_model_runner.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py index 9bb49a21..24690485 100644 --- a/vllm/v1/worker/gpu_model_runner.py +++ b/vllm/v1/worker/gpu_model_runner.py @@ -411,7 +411,7 @@ class GPUModelRunner: set_compilation_config( CompilationConfig( use_cudagraph=True, - non_cudagraph_ops=["vllm.unified_flash_attention"], + non_cudagraph_ops=["vllm.unified_v1_flash_attention"], use_inductor=True, ))