Home
last modified time | relevance | path

Searched refs:WeightOnlyInt8QuantHandler (Results 1 – 5 of 5) sorted by relevance

/external/executorch/examples/models/llama/
Dmodel.py163 from ..source_transformation.quantize import WeightOnlyInt8QuantHandler
165 simple_quantizer = WeightOnlyInt8QuantHandler(self.model_)
/external/pytorch/benchmarks/gpt_fast/
Dquantize.py60 class WeightOnlyInt8QuantHandler: class
Dgenerate.py10 WeightOnlyInt8QuantHandler as MixtralMoEWeightOnlyInt8QuantHandler,
13 from quantize import WeightOnlyInt8QuantHandler as LLaMAWeightOnlyInt8QuantHandler
Dmixtral_moe_quantize.py73 class WeightOnlyInt8QuantHandler: class
/external/executorch/examples/models/llama/source_transformation/
Dquantize.py74 return WeightOnlyInt8QuantHandler(model).quantized_model()
316 class WeightOnlyInt8QuantHandler(QuantHandler): class