[ModelOpt] Redesign the LinearMethod classes using the generic QuantKey-driven method (#49381)
Signed-off-by: Juhi Mittal <juhim@nvidia.com> Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
co-authored by
Claude Opus 4.8
mgoin
parent
4bf06be985
commit
7a977c0699
@@ -55,13 +55,10 @@ WEIGHT_LOADER_V2_SUPPORTED = [
|
||||
"AutoGPTQLinearMethod",
|
||||
"Fp8LinearMethod",
|
||||
"FBGEMMFp8LinearMethod",
|
||||
"ModelOptFp8LinearMethod",
|
||||
"ModelOptFp8PcPtLinearMethod",
|
||||
"ModelOptFp8PbWoLinearMethod",
|
||||
"QuarkLinearMethod",
|
||||
"ModelOptNvFp4LinearMethod",
|
||||
"ModelOptNvFp4W4A16LinearMethod",
|
||||
"HummingLinearMethod",
|
||||
# ModelOptLinearMethod self-registers via
|
||||
# register_weight_loader_v2_supported_method (see modelopt.py).
|
||||
]
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user