xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-21 03:36:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

correct minimum capability req for channelwise torch

Browse Source 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
This commit is contained in:
vllmellm 2025-11-04 12:22:49 +00:00
parent a76f7bb90c
commit f10171cb3d
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/layers/quantization/kernels/scaled_mm/pytorch.py
View File

@ -230,9 +230,6 @@ class RowWiseTorchScaledMMLinearKernel(TorchScaledMMLinearKernel):
class ChannelWiseTorchScaledMMLinearKernel(TorchScaledMMLinearKernel): class ChannelWiseTorchScaledMMLinearKernel(TorchScaledMMLinearKernel):
@classmethod
def get_min_capability(cls) -> int:
return 94
@classmethod @classmethod
def can_implement(cls, c: FP8ScaledMMLinearLayerConfig) -> tuple[bool, str | None]: def can_implement(cls, c: FP8ScaledMMLinearLayerConfig) -> tuple[bool, str | None]: