PyTorch
- 安装指南
- 快速开始
- 功能样例
- API 文档
torch_npu._npu_dropout()
torch_npu.copy_memory_()
torch_npu.empty_with_format()
torch_npu.fast_gelu()
torch_npu.npu_alloc_float_status()
torch_npu.npu_anchor_response_flags()
torch_npu.npu_apply_adam()
torch_npu.npu_batch_nms()
torch_npu.npu_bert_apply_adam()
torch_npu.npu_bmmV2()
torch_npu.npu_bounding_box_decode()
torch_npu.npu_bounding_box_encode()
torch_npu.npu_broadcast()
torch_npu.npu_ciou()
torch_npu.npu_clear_float_status()
torch_npu.npu_confusion_transpose()
torch_npu.npu_conv2d()
torch_npu.npu_conv3d()
torch_npu.npu_conv_transpose2d()
torch_npu.npu_convolution()
torch_npu.npu_convolution_transpose()
torch_npu.npu_deformable_conv2d()
torch_npu.npu_diou()
torch_npu.npu_dropout_with_add_softmax()
torch_npu.npu_dtype_cast()
torch_npu.npu_format_cast()
torch_npu.npu_format_cast_()
torch_npu.npu_fused_attention_score()
torch_npu.npu_fusion_attention()
torch_npu.npu_geglu()
torch_npu.npu_get_float_status()
torch_npu.npu_giou()
torch_npu.npu_grid_assign_positive()
torch_npu.npu_gru()
torch_npu.npu_ifmr()
torch_npu.npu_indexing()
torch_npu.npu_iou()
torch_npu.npu_layer_norm_eval()
torch_npu.npu_linear()
torch_npu.npu_lstm()
torch_npu.npu_masked_fill_range()
torch_npu.npu_max()
torch_npu.npu_min()
torch_npu.npu_mish()
torch_npu.npu_multi_head_attention()
torch_npu.npu_nms_rotated()
torch_npu.npu_nms_v4()
torch_npu.npu_nms_with_mask()
torch_npu.npu_normalize_batch()
torch_npu.npu_one_hot()
torch_npu.npu_pad()
torch_npu.npu_ps_roi_pooling()
torch_npu.npu_ptiou()
torch_npu.npu_random_choice_with_mask()
torch_npu.npu_reshape()
torch_npu.npu_rms_norm()
torch_npu.npu_roi_align()
torch_npu.npu_rotary_mul()
torch_npu.npu_rotated_box_decode()
torch_npu.npu_rotated_box_encode()
torch_npu.npu_rotated_iou()
torch_npu.npu_rotated_overlaps()
torch_npu.npu_scaled_masked_softmax()
torch_npu.npu_scatter()
torch_npu.npu_sign_bits_pack()
torch_npu.npu_sign_bits_unpack()
torch_npu.npu_silu()
torch_npu.npu_slice()
torch_npu.npu_softmax_cross_entropy_with_logits()
torch_npu.npu_sort_v2()
torch_npu.npu_stride_add()
torch_npu.npu_transpose()
torch_npu.npu_yolo_boxes_encode()
torch_npu.one_()
torch_npu.npu_swiglu()
torch_npu.npu_trans_quant_param()
torch_npu.npu_quant_matmul()
torch_npu.npu_weight_quant_batchmatmul()
torch_npu.npu_convert_weight_to_int4pack()
torch_npu.npu_grouped_matmul()
torch_npu.npu_quant_scatter()
torch_npu.npu_quant_scatter_()
torch_npu.npu_scatter_nd_update()
torch_npu.npu_scatter_nd_update_()
torch_npu.npu_anti_quant()
torch_npu.npu_mm_all_reduce_base()
torch_npu.npu_ffn()
torch_npu.npu_incre_flash_attention()
torch_npu.npu_prompt_flash_attention()
torch_npu.npu_fused_infer_attention_score()
- FAQ