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

[Hardware][XPU] AWQ/GPTQ support for xpu backend (#10107)

Browse Source 
Signed-off-by: yan ma <yan.ma@intel.com>
This commit is contained in:
Yan Ma
2024-11-19 02:18:05 +08:00
committed by GitHub
parent 281cc4b3cd
commit 6b2d25efc7
7 changed files with 146 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/linear.py
View File

@@ -27,7 +27,7 @@ WEIGHT_LOADER_V2_SUPPORTED = [
"AWQLinearMethod", "GPTQMarlinLinearMethod", "Fp8LinearMethod",
"MarlinLinearMethod", "QQQLinearMethod", "GPTQMarlin24LinearMethod",
"TPUInt8LinearMethod", "GPTQLinearMethod", "FBGEMMFp8LinearMethod",
"ModelOptFp8LinearMethod", "IPEXAWQLinearMethod"
"ModelOptFp8LinearMethod", "IPEXAWQLinearMethod", "IPEXGPTQLinearMethod"
]