Int4WeightOnlyQATQuantizer

class torchao.quantization.qat.Int4WeightOnlyQATQuantizer(groupsize: int = 256, inner_k_tiles: Optional[int] = 8, precision: dtype = torch.bfloat16, scales_precision: dtype = torch.bfloat16)

用于在模型上执行 QAT 的量化器，其中线性层具有 int4 假量化的逐通道权重。