We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 82d034d commit 3cdd398Copy full SHA for 3cdd398
python/sglang/srt/layers/quantization/fp8.py
@@ -860,7 +860,7 @@ def process_weights_hip_int4(self, layer: Module):
860
layer.w13_weight_scale1[expert_id] *= max_w13_scales[expert_id]
861
layer.w2_weight_scale1[expert_id] *= layer.w2_weight_scale[expert_id]
862
863
- def process_weights_hip_scale_padding(self, layer: Module, padding_size: int):
+ def process_weights_hip_scale_padding(self, layer: Module):
864
from sglang.srt.layers.moe.fused_moe_triton.fused_moe import (
865
padding_size, # Avoid circular import
866
)
0 commit comments