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

[Misc] Update fbgemmfp8 to use vLLMParameters (#7972)

Browse Source 
Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
Dipika Sikka
2024-09-03 22:12:41 -04:00
committed by GitHub
parent 61f4a93d14
commit e16fa99a6a
3 changed files with 22 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

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