[ROCM] fix native attention function call (#13650)

68d630a0 · Gordon Wong · GitHub · 68d535ef · 68d630a0
Unverified Commit 68d630a0 authored Feb 22, 2025 by Gordon Wong Committed by GitHub Feb 21, 2025
Hide whitespace changes
Inline Side-by-side

Showing with 0 additions and 1 deletion

vllm/attention/backends/rocm_flash_attn.py vllm/attention/backends/rocm_flash_attn.py +0 -1

No files found.
--- a/vllm/attention/backends/rocm_flash_attn.py
+++ b/vllm/attention/backends/rocm_flash_attn.py
@@ -717,7 +717,6 @@ class ROCmFlashAttentionImpl(AttentionImpl):
                        self.num_heads,
                        self.head_size,
                        self.scale,
-                        causal_mask,
                        attn_masks,
                    )
                else: