quark.torch.quantization.graph.optimization.replace_linear_to_qtlinear

Module Contents

Functions

quark.torch.quantization.graph.optimization.replace_linear_to_qtlinear.replace_linear_qtlinear(m: torch.fx.GraphModule) → None

replace [ops.aten.linear] to QuantLinear ops.aten.linear:

args: (Tensor input, Tensor weight, Tensor? bias=None) -> Tensor required: [input, weight] optional: [bias=None]