[Feature][Quantization] MXFP4 support for MOE models (#17888)
Signed-off-by: Felix Marty <felmarty@amd.com> Signed-off-by: Bowen Bao <bowenbao@amd.com> Signed-off-by: Felix Marty <Felix.Marty@amd.com> Co-authored-by: Bowen Bao <bowenbao@amd.com>
This commit is contained in:
@@ -237,12 +237,6 @@ class QuarkConfig(QuantizationConfig):
|
||||
"Quark model is not in MX-FP4 format: not group_size=32")
|
||||
return False
|
||||
|
||||
# Weights need to use static quantization.
|
||||
if weight_quant.get("is_dynamic") is True:
|
||||
logger.debug(
|
||||
"Quark model is not in MX-FP4 format: not weight static")
|
||||
return False
|
||||
|
||||
# Activations need to use dynamic quantization.
|
||||
if input_quant.get("is_dynamic") is False:
|
||||
logger.debug(
|
||||
|
||||
Reference in New Issue
Block a user