Int8DynActInt4WeightQATQuantizer

class torchao.quantization.qat.Int8DynActInt4WeightQATQuantizer(groupsize: int = 256, padding_allowed: bool = False, precision: dtype = torch.float32, scales_precision: dtype = torch.float32)

執行 QAT 的量化器，其中線性層具有 int8 動態每 token 假量化啟用和 int4 假量化每通道分組權重。