biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[v1] Support multiple KV cache groups in GPU model runner (#17945)

Browse Source 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
This commit is contained in:
Chen Zhang
2025-05-15 09:54:54 +08:00
committed by GitHub
parent f25e0d1125
commit e60f550b38
16 changed files with 482 additions and 215 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