Home
last modified time | relevance | path

Searched refs:WeightOnlyInt8Linear (Results 1 – 3 of 3) sorted by relevance

/external/pytorch/benchmarks/gpt_fast/
Dquantize.py54 WeightOnlyInt8Linear(child.in_features, child.out_features),
82 class WeightOnlyInt8Linear(torch.nn.Module): class
Dmixtral_moe_quantize.py56 WeightOnlyInt8Linear(
119 class WeightOnlyInt8Linear(torch.nn.Module): class
/external/executorch/examples/models/llama/source_transformation/
Dquantize.py310 WeightOnlyInt8Linear("cpu", child.in_features, child.out_features),
393 class WeightOnlyInt8Linear(torch.nn.Module): class