A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 13, 02:00 UTC
[Bugfix] Safeguard against missing backend in AttentionBackendEnum (#28846)
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>
Song Zhixin committed
Nov 18, 2025 at 18:53 UTC
285eaa42857ba2a8f377fdd0dcd84120260d8f65
1 file changed
+2
-1
vllm/attention/layer.py
+2
-1
@@ -310,7 +310,8 @@ class Attention(nn.Module, AttentionLayerBase):
310
kv_sharing_target_layer_name,
311
**extra_impl_args,
312
)
313
- self.backend = AttentionBackendEnum[self.attn_backend.get_name()]
313
+ backend_name = self.attn_backend.get_name()
314
+ self.backend = AttentionBackendEnum.__members__.get(backend_name)
315
self.dtype = dtype
316
317
# For cuda-alike (CUDA and ROCM) and cpu platforms, we control how