biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix] Safeguard against missing backend in AttentionBackendEnum (#28846)

Browse Source 
Signed-off-by: jesse <szxfml@gmail.com>
Signed-off-by: Song Zhixin <szxfml@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Song Zhixin
2025-11-18 18:53:44 +08:00
committed by GitHub
parent 439368496d
commit 285eaa4285
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/attention/layer.py
View File

@@ -310,7 +310,8 @@ class Attention(nn.Module, AttentionLayerBase):
kv_sharing_target_layer_name, kv_sharing_target_layer_name,
**extra_impl_args, **extra_impl_args,
) )
self.backend = AttentionBackendEnum[self.attn_backend.get_name()] backend_name = self.attn_backend.get_name()
self.backend = AttentionBackendEnum.__members__.get(backend_name)
self.dtype = dtype self.dtype = dtype
# For cuda-alike (CUDA and ROCM) and cpu platforms, we control how # For cuda-alike (CUDA and ROCM) and cpu platforms, we control how