[Bugfix] Add missing VIT backend dispatch on CPU (#24623)

Signed-off-by: jiang1.li <jiang1.li@intel.com>

[Bugfix] Add missing VIT backend dispatch on CPU (#24623)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
29799dda · Li, Jiang · GitHub · f17a6aa4 · 29799dda
Unverified Commit 29799dda authored Sep 11, 2025 by Li, Jiang Committed by GitHub Sep 10, 2025
Show whitespace changes
Inline Side-by-side

Showing with 2 additions and 1 deletion

vllm/attention/layer.py vllm/attention/layer.py +2 -1

No files found.
--- a/vllm/attention/layer.py
+++ b/vllm/attention/layer.py
@@ -399,7 +399,8 @@ class MultiHeadAttention(nn.Module):
                                                          key,
                                                          value,
                                                          scale=self.scale)
-        elif self.attn_backend == _Backend.TORCH_SDPA:
+        elif (self.attn_backend == _Backend.TORCH_SDPA
+              or self.attn_backend == _Backend.TORCH_SDPA_VLLM_V1):
            query, key, value = (x.transpose(1, 2)
                                 for x in (query, key, value))
            out = F.scaled_dot_product_attention(query,