fix: gptq marlin weight loading failure (#23066)

0fc8fa75 · Simon Mo · GitHub · 21e39436 · 0fc8fa75
Unverified Commit 0fc8fa75 authored Aug 17, 2025 by Simon Mo Committed by GitHub Aug 17, 2025
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

vllm/model_executor/layers/quantization/gptq_marlin.py vllm/model_executor/layers/quantization/gptq_marlin.py +1 -1

No files found.
--- 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