youngkingdom/vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[Bugfix] fix an illegal memory access was encountered of marlin kernel + act_order (#18245)

Browse Source
This commit is contained in:
Jinzhen Lin
2025-05-17 07:02:44 +08:00
committed by GitHub
parent 7fdfa01530
commit e73b7dfd69
3 changed files with 29 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/weight_loading/models.txt
View File

@ -2,7 +2,7 @@ gptq_marlin, robertgshaw2/zephyr-7b-beta-channelwise-gptq, main
gptq_marlin, TheBloke/Llama-2-7B-GPTQ, main
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, main
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit--1g-actorder_True
#gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit-32g-actorder_True
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit-32g-actorder_True
gptq_marlin, TechxGenus/gemma-1.1-2b-it-GPTQ, main
gptq, robertgshaw2/zephyr-7b-beta-channelwise-gptq, main
gptq, TheBloke/Llama-2-7B-GPTQ, main