[Refactor][Quantization] Make FP8 and MLA weight transforms reusable pure functions (#57732)
Signed-off-by: aoshen02 <aoshen@inferact.ai> Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
This commit is contained in:
@@ -416,7 +416,6 @@ class Fp8LinearMethod(LinearMethodBase):
|
||||
if self.act_q_static:
|
||||
assert input_scale is not None
|
||||
input_scale = input_scale.max()
|
||||
weight = weight.t()
|
||||
|
||||
# Update layer with new values.
|
||||
replace_parameter(layer, "weight", weight.data)
|
||||
|
||||
Reference in New Issue
Block a user