[Quantization][w8a8_int8] Fix weight loading issue for w8a8_int8 path with "ignore" layer list in quantization config (#7820)

2025-07-18 13:03:56 +08:00
parent 48c1fa7bb6
commit 7891bac16b
2 changed files with 22 additions and 16 deletions
--- a/python/sglang/srt/layers/quantization/unquant.py
+++ b/python/sglang/srt/layers/quantization/unquant.py
@@ -347,8 +347,8 @@ class UnquantizedFusedMoEMethod(FusedMoEMethodBase, CustomOp):
        if use_intel_amx_backend(layer):

            from sglang.srt.layers.moe.topk import (
-                select_experts,
                apply_topk_weights_cpu,
+                select_experts,
            )

            topk_weights, topk_ids = select_experts(