Fix regression from #246 (#332)

ROCm · Dec 16, 2024 · d09f1ce · d09f1ce
1 parent 1f0f4c6
commit d09f1ce
Showing 1 changed file with 0 additions and 1 deletion.
diff --git a/vllm/attention/ops/triton_flash_attention.py b/vllm/attention/ops/triton_flash_attention.py
@@ -394,7 +394,6 @@ def get_autotune_configs():
 @triton.autotune(
     configs=autotune_configs,
     key=autotune_keys,
-    use_cuda_graph=True,
 )
 @triton.jit
 def attn_fwd(