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

[Misc] Update gptq_marlin_24 to use vLLMParameters (#7762)

Browse Source 
Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
Dipika Sikka
2024-08-26 17:44:54 -04:00
committed by GitHub
parent 665304092d
commit dd9857f5fa
2 changed files with 50 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -23,7 +23,7 @@ logger = init_logger(__name__)
WEIGHT_LOADER_V2_SUPPORTED = [
"CompressedTensorsLinearMethod", "AWQMarlinLinearMethod",
"AWQLinearMethod", "GPTQMarlinLinearMethod", "Fp8LinearMethod",
"MarlinLinearMethod", "QQQLinearMethod"
"MarlinLinearMethod", "QQQLinearMethod", "GPTQMarlin24LinearMethod"
]