Skip to content

GitLab

Commit 6f1beee6 authored by zhuwenwen's avatar zhuwenwen
Browse files

Update modelopt.py

parent eefa41c1
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/layers/quantization/modelopt.py
View file @ 6f1beee6
...@@ -2209,7 +2209,7 @@ class ModelOptMixedPrecisionConfig(ModelOptQuantConfigBase): ...@@ -2209,7 +2209,7 @@ class ModelOptMixedPrecisionConfig(ModelOptQuantConfigBase):
return ModelOptFp8LinearMethod(self.fp8_config) return ModelOptFp8LinearMethod(self.fp8_config)
if quant_algo == "NVFP4": if quant_algo == "NVFP4":
return ModelOptNvFp4LinearMethod(self.nvfp4_config) return ModelOptNvFp4LinearMethod(self.nvfp4_config)
# Layer not in quantized_layers 鈥?leave unquantized # Layer not in quantized_layers — leave unquantized
return UnquantizedLinearMethod() return UnquantizedLinearMethod()
if isinstance(layer, FusedMoE): if isinstance(layer, FusedMoE):
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment