fix: gptq marlin weight loading failure (#23066)

2025-08-17 15:56:07 -07:00
parent 21e39436c8
commit 0fc8fa751a
1 changed files with 1 additions and 1 deletions
--- a/vllm/model_executor/layers/quantization/gptq_marlin.py
+++ b/vllm/model_executor/layers/quantization/gptq_marlin.py
@@ -56,7 +56,7 @@ def get_moe_quant_method(
            # Dynamic per module/layer rules may override base config
            override_config(cloned_config, prefix=prefix)

-        return moe_method_cls(cloned_config)
+        return moe_method_cls(cloned_config, layer.moe_config)
    return None