[Refactor] Remove dead code for quantization (#52221)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
@@ -53,7 +53,6 @@ class INCConfig(QuantizationConfig):
|
||||
MXFP8_GROUP_SIZE = 32
|
||||
MXFP8_DATA_TYPE = "mx_fp"
|
||||
MXFP8_PACKING_FORMAT = "auto_round:llm_compressor"
|
||||
MXFP8_SUPPORTED_ACT_DTYPES = {"mx_fp", "mx_fp_rceil"}
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
|
||||
@@ -458,7 +458,3 @@ class INCARKLinearMethod(INCXPULinearBase):
|
||||
layer.ark_scale_type,
|
||||
not self.sym,
|
||||
)
|
||||
|
||||
|
||||
class INCXPUW4A16LinearScheme(INCXPULinearMethod):
|
||||
pass
|
||||
|
||||
Reference in New Issue
Block a user