[V1] Fix non-cudagraph op name (#10166)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

[V1] Fix non-cudagraph op name (#10166)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
b5815c84 · Woosuk Kwon · GitHub · 6b304715 · b5815c84
Unverified Commit b5815c84 authored Nov 08, 2024 by Woosuk Kwon Committed by GitHub Nov 08, 2024
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

vllm/v1/worker/gpu_model_runner.py vllm/v1/worker/gpu_model_runner.py +1 -1

No files found.
--- 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,
                ))