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

[Hardware][NV] Add support for ModelOpt static scaling checkpoints. (#6112)

Browse Source
This commit is contained in:
Pavani Majety
2024-09-10 21:38:40 -07:00
committed by GitHub
parent 1230263e16
commit efcf946a15
7 changed files with 258 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/layers/linear.py
View File

@@ -26,7 +26,8 @@ WEIGHT_LOADER_V2_SUPPORTED = [
"CompressedTensorsLinearMethod", "AWQMarlinLinearMethod",
"AWQLinearMethod", "GPTQMarlinLinearMethod", "Fp8LinearMethod",
"MarlinLinearMethod", "QQQLinearMethod", "GPTQMarlin24LinearMethod",
"TPUInt8LinearMethod", "GPTQLinearMethod", "FBGEMMFp8LinearMethod"
"TPUInt8LinearMethod", "GPTQLinearMethod", "FBGEMMFp8LinearMethod",
"ModelOptFp8LinearMethod"
]