remove attn output view kernel (#26680)

Signed-off-by: Boyuan Feng <boyuan@meta.com> Signed-off-by: Boyuan Feng <fby.1994@gmail.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-10-14 15:53:10 -07:00
parent ff4810ba73
commit a86b4c58e8
10 changed files with 12 additions and 12 deletions
--- a/vllm/v1/attention/backends/rocm_aiter_fa.py
+++ b/vllm/v1/attention/backends/rocm_aiter_fa.py
@@ -485,7 +485,7 @@ class AiterFlashAttentionImpl(AttentionImpl):

        if attn_metadata is None:
            # Profiling run.
-            return output
+            return output.fill_(0)

        # IMPORTANT!
        # NOTE(woosuk): With piece-wise CUDA graphs, this method is executed in