xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-06 02:09:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: gptq marlin weight loading failure (#23066)

Browse Source
This commit is contained in:
Simon Mo 2025-08-17 15:56:07 -07:00 committed by GitHub
parent 21e39436c8
commit 0fc8fa751a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
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/gptq_marlin.py
View File

@ -56,7 +56,7 @@ def get_moe_quant_method(
# Dynamic per module/layer rules may override base config # Dynamic per module/layer rules may override base config
override_config(cloned_config, prefix=prefix) override_config(cloned_config, prefix=prefix)
return moe_method_cls(cloned_config) return moe_method_cls(cloned_config, layer.moe_config)
return None return None