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

[Kernel] Add ModelOpt FP4 Checkpoint Support (#12520)

Browse Source 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
This commit is contained in:
Pavani Majety
2025-03-11 22:13:11 -07:00
committed by GitHub
parent 5c538c37b2
commit debd6bbf09
10 changed files with 388 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
vllm/model_executor/layers/linear.py
View File

@@ -30,12 +30,23 @@ from vllm.model_executor.utils import set_weight_attrs
logger = init_logger(__name__)
WEIGHT_LOADER_V2_SUPPORTED = [
"CompressedTensorsLinearMethod", "AWQMarlinLinearMethod",
"AWQLinearMethod", "GPTQMarlinLinearMethod", "Fp8LinearMethod",
"MarlinLinearMethod", "QQQLinearMethod", "GPTQMarlin24LinearMethod",
"TPUInt8LinearMethod", "GPTQLinearMethod", "FBGEMMFp8LinearMethod",
"ModelOptFp8LinearMethod", "IPEXAWQLinearMethod", "IPEXGPTQLinearMethod",
"HQQMarlinMethod", "QuarkLinearMethod"
"CompressedTensorsLinearMethod",
"AWQMarlinLinearMethod",
"AWQLinearMethod",
"GPTQMarlinLinearMethod",
"Fp8LinearMethod",
"MarlinLinearMethod",
"QQQLinearMethod",
"GPTQMarlin24LinearMethod",
"TPUInt8LinearMethod",
"GPTQLinearMethod",
"FBGEMMFp8LinearMethod",
"ModelOptFp8LinearMethod",
"IPEXAWQLinearMethod",
"IPEXGPTQLinearMethod",
"HQQMarlinMethod",
"QuarkLinearMethod",
"ModelOptNvFp4LinearMethod",
]