[Quant] Enable humming w[2-7]a[4,8] inference with compressed-tensors (#46390)
Signed-off-by: HDCharles <charlesdavidhernandez@gmail.com>
This commit is contained in:
@@ -45,7 +45,10 @@ class HummingLinearKernel(MPLinearKernel):
|
||||
quant_config["has_zero_point"] = True
|
||||
|
||||
convert_linear_layer_to_humming_standard(layer=layer, name_map=name_map)
|
||||
prepare_humming_layer(layer, quant_config)
|
||||
input_quant_config = getattr(layer, "_humming_input_quant_config", None)
|
||||
prepare_humming_layer(
|
||||
layer, quant_config, input_quant_config=input_quant_config
|
||||
)
|
||||
|
||||
def apply_weights(
|
||||
self,
|
||||
|
||||
Reference in New Issue
Block a user