Int4WeightOnlyQATQuantizer

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

用於對模型執行 QAT 的量化器，其中線性層具有按通道分組的 int4 偽量化權重。