xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-25 00:05:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py

Browse Source 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye 2025-09-19 18:38:37 -04:00 committed by yewentao256
parent ae36150ec2
commit abb448b457
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py
View File

@ -89,7 +89,7 @@ class CutlassScaledMMLinearKernel(ScaledMMLinearKernel):
# It does not depend on scales or azp, so it is the same for
# static and dynamic quantization.
# For more details, see csrc/quantization/w8a8/cutlass/Epilogues.md
# https://github.com/vllm-project/vllm/blob/8d59dbb00044a588cab96bcdc028006ed922eb06/csrc/quantization/w8a8/cutlass/Epilogues.md
# https://github.com/vllm-project/vllm/blob/main/csrc/quantization/w8a8/cutlass/Epilogues.md
if not self.config.input_symmetric:
weight = getattr(layer, self.w_q_name)
azp_adj = weight.sum(dim=0, keepdim=True, dtype=torch.int32)