Int8DynActInt4WeightQATQuantizer

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

用于在模型上执行 QAT 的量化器，其中线性层具有 int8 动态每 token 伪量化激活和 int4 每通道分组伪量化权重。