From 37367da6390fa4a5c440102d9fce29b6afaefefb Mon Sep 17 00:00:00 2001 From: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com> Date: Thu, 11 Sep 2025 14:54:09 +0800 Subject: [PATCH] [fix CI] Fix logical condition in fused MoE layer for compressed tensor quantization (#10299) --- python/sglang/srt/layers/moe/fused_moe_triton/layer.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/python/sglang/srt/layers/moe/fused_moe_triton/layer.py b/python/sglang/srt/layers/moe/fused_moe_triton/layer.py index 5f219739c..0ea1fa1eb 100644 --- a/python/sglang/srt/layers/moe/fused_moe_triton/layer.py +++ b/python/sglang/srt/layers/moe/fused_moe_triton/layer.py @@ -613,8 +613,10 @@ class FusedMoE(torch.nn.Module): loaded_weight = loaded_weight.to(param.data.device) if ( - "compressed" in self.quant_method.__class__.__name__.lower() - or "w4afp8" in self.quant_config.get_name() + ( + "compressed" in self.quant_method.__class__.__name__.lower() + or "w4afp8" in self.quant_config.get_name() + ) and (param.data[expert_id] != 1).any() and ((param.data[expert_id] - loaded_weight).abs() > 1e-5).any() ):