Int4WeightOnlyQATEmbedding¶
- class torchao.quantization.qat.embedding.Int4WeightOnlyQATEmbedding(num_embeddings: int, embedding_dim: int, padding_idx: Optional[int] = None, max_norm: Optional[float] = None, norm_type: float = 2.0, scale_grad_by_freq: bool = False, sparse: bool = False, group_size: int = 32, scale_precision: dtype = torch.float32, zero_point_precision: dtype = torch.int32, *args, **kwargs)[原始碼]¶
此模組實現了一個具有 int4 逐通道權重假量化的嵌入層。
- 引數:
group_size – 權重的每個量化組中的元素數量
scale_precision – 每組尺度的精度
zero_point_precision – 每組零點的精度
