[Quantization] Add ModelOpt NVFP4 W4A16 (4-bit weights, fp16/bf16 activations) support (#41769)
Signed-off-by: Juhi Mittal <juhim@nvidia.com>
This commit is contained in:
@@ -60,6 +60,7 @@ WEIGHT_LOADER_V2_SUPPORTED = [
|
||||
"ModelOptFp8PbWoLinearMethod",
|
||||
"QuarkLinearMethod",
|
||||
"ModelOptNvFp4LinearMethod",
|
||||
"ModelOptNvFp4W4A16LinearMethod",
|
||||
"HummingLinearMethod",
|
||||
]
|
||||
|
||||
|
||||
Reference in New Issue
Block a user