xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-20 09:23:31 +08:00
Code Issues Packages Projects Releases Wiki Activity

[moe][quant] add weight name case for offset (#15515)

Browse Source 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao 2025-03-27 12:50:29 +08:00 committed by GitHub
parent 7f301dd8ef
commit fb22be5817
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/layers/fused_moe/layer.py
View File

@ -699,8 +699,9 @@ class FusedMoE(torch.nn.Module):
tp_rank=self.tp_rank)
return
# Case weight scales and zero_points
if ("scale" in weight_name or "zero" in weight_name):
# Case weight scales, zero_points and offset
if ("scale" in weight_name or "zero" in weight_name
or "offset" in weight_name):
# load the weight scales and zp based on the quantization scheme
# supported weight scales/zp can be found in
# FusedMoeWeightScaleSupported