fix amd triton mla path (#17871)

eea22a56 · Shiyan Deng · GitHub · 91121552 · eea22a56
Unverified Commit eea22a56 authored May 11, 2025 by Shiyan Deng Committed by GitHub May 11, 2025
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

vllm/attention/backends/mla/common.py vllm/attention/backends/mla/common.py +1 -1

No files found.
--- a/vllm/attention/backends/mla/common.py
+++ b/vllm/attention/backends/mla/common.py
@@ -1063,7 +1063,7 @@ class MLACommonImpl(MLAAttentionImpl[T], Generic[T]):
                softmax_scale,
                None,  # bias
            )
-        if is_vllm_fa:
+        elif is_vllm_fa:
            attn_out = self.flash_attn_varlen_func(
                q=q,
                k=k,