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 14, 05:30 UTC
Remove duplicate entry in vllm.attention.__all__ (#23296)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Russell Bryant committed
Aug 20, 2025 at 20:14 UTC
f5aa307d7795b8400d3719087c502c2a227030c7
1 file changed
-1
vllm/attention/__init__.py
-1
@@ -14,7 +14,6 @@ __all__ = [
14
"AttentionMetadata",
15
"AttentionType",
16
"AttentionMetadataBuilder",
17
- "Attention",
17
"AttentionState",
18
"get_attn_backend",
19
]