A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
fix: gptq marlin weight loading failure (#23066)
Simon Mo committed
Aug 17, 2025 at 15:56 UTC
0fc8fa751a4321d6531467537ff77cf3c1c70260
1 file changed
+1
-1
vllm/model_executor/layers/quantization/gptq_marlin.py
+1
-1
@@ -56,7 +56,7 @@ def get_moe_quant_method(
56
# Dynamic per module/layer rules may override base config
57
override_config(cloned_config, prefix=prefix)
58
59
- return moe_method_cls(cloned_config)
59
+ return moe_method_cls(cloned_config, layer.moe_config)
60
return None
61
62