Skip to content

GitLab

Unverified Commit 81992474 authored by HAI's avatar HAI Committed by GitHub
Browse files

Fix refactor error - fp8.py (#5106) 


Co-authored-by: default avatarLianmin Zheng <lianminzheng@gmail.com>
parent f04c80dc
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
python/sglang/srt/layers/quantization/fp8.py
View file @ 81992474
...@@ -860,7 +860,7 @@ class Fp8MoEMethod: ...@@ -860,7 +860,7 @@ class Fp8MoEMethod:
layer.w13_weight_scale1[expert_id] *= max_w13_scales[expert_id] layer.w13_weight_scale1[expert_id] *= max_w13_scales[expert_id]
layer.w2_weight_scale1[expert_id] *= layer.w2_weight_scale[expert_id] layer.w2_weight_scale1[expert_id] *= layer.w2_weight_scale[expert_id]
def process_weights_hip_scale_padding(self, layer: Module, padding_size: int): def process_weights_hip_scale_padding(self, layer: Module):
from sglang.srt.layers.moe.fused_moe_triton.fused_moe import ( from sglang.srt.layers.moe.fused_moe_triton.fused_moe import (
padding_size, # Avoid circular import padding_size, # Avoid circular import
) )
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment