diff --git a/modules/flash_attn_triton_amd/fwd_prefill.py b/modules/flash_attn_triton_amd/fwd_prefill.py index cf78cd0ee..123242694 100644 --- a/modules/flash_attn_triton_amd/fwd_prefill.py +++ b/modules/flash_attn_triton_amd/fwd_prefill.py @@ -218,8 +218,7 @@ autotune_configs, autotune_keys = get_autotune_configs() @triton.autotune( configs=autotune_configs, - key=autotune_keys, - use_cuda_graph=True, + key=autotune_keys ) @triton.jit def attn_fwd(Q, K, V, bias, Cache_seqlens, Cache_batch_idx, # pylint: disable=unused-argument