[Feature][NPU]: add runtime support for AutoRound quantized models (#16699)
Co-authored-by: root <root@localhost.localdomain> Co-authored-by: ronnie_zheng <zl19940307@163.com>
This commit is contained in:
co-authored by
root
ronnie_zheng
parent
fd79cd8d9c
commit
13bdc7bf4a
@@ -64,10 +64,9 @@ WEIGHT_LOADER_V2_SUPPORTED = [
|
||||
"GPTQMarlin24LinearMethod",
|
||||
"TPUInt8LinearMethod",
|
||||
"GPTQLinearMethod",
|
||||
"GPTQLinearAscendMethod",
|
||||
"GPTQMoEAscendMethod",
|
||||
"FBGEMMFp8LinearMethod",
|
||||
"GPTQLinearAscendMethod",
|
||||
"GPTQMoEAscendMethod",
|
||||
"ModelOptFp8LinearMethod",
|
||||
"ModelOptFp4LinearMethod",
|
||||
"IPEXAWQLinearMethod",
|
||||
|
||||
Reference in New Issue
Block a user