quark.onnx.finetuning.create_torch.quant_gemm_ops

Contents

`quark.onnx.finetuning.create_torch.quant_gemm_ops`#

Module Contents#

Classes#

class quark.onnx.finetuning.create_torch.quant_gemm_ops.QGemm(transA: int = 0, transB: int = 0, **kwargs: Any)#: A wrapper for torch layer’s input/weight/bias quantization