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 6, 23:00 UTC
[Misc][Attention] Clean up unused method in `CPU_ATTN` (#36673)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Matthew Bonanni committed
Mar 11, 2026 at 00:27 UTC
5f77ef15aedc53950b20a684e645dbb6be4e654a
1 file changed
-4
vllm/v1/attention/backends/cpu_attn.py
-4
@@ -36,10 +36,6 @@ class CPUAttentionBackend(AttentionBackend):
36
torch.float32,
37
]
38
39
- @classmethod
40
- def get_supported_dtypes(cls) -> list[torch.dtype]:
41
- return [torch.float16, torch.bfloat16, torch.float32]
42
-
39
@classmethod
40
def get_supported_head_sizes(cls) -> list[int]:
41
return [32, 64, 80, 96, 112, 128, 160, 192, 224, 256]