MCPcopy Create free account

hub / github.com/bilibili/Index-anisora / functions

Functions18,851 in github.com/bilibili/Index-anisora

⨍ Functions 18,851◇ Types & classes 4,392↳ Endpoints 34
↓ 7 callersMethodselect
(index: number)
reward/character/samurai/sam2/demo/frontend/src/common/components/video/filmstrip/SelectedFrameHelper.ts:34
↓ 7 callersMethodset_input_embeddings
(self, new_embeddings)
anisoraV1_infer/fastercache/models/vchitect/modeling_t5.py:967
↓ 7 callersFunctionset_pab_manager
(config: PABConfig)
anisoraV1_infer/videosys/core/pab_mgr.py:183
↓ 7 callersMethodset_timesteps
Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`):
anisoraV3.2/wan/utils/fm_solvers.py:228
↓ 7 callersMethodstate_dict
(self)
anisoraV1_infer/sat/examples/yolos/util/scheduler.py:60
↓ 7 callersMethodstep
(self, model_output, timestep, sample, to_final=False)
anisoraV2_gpu/fastvideo/train.py:56
↓ 7 callersMethodstep
Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned m
anisoraV1_infer/videosys/schedulers/scheduling_dpm_cogvideox.py:324
↓ 7 callersFunctiontimestep_embedding
Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be
anisora_rl/sat/sgm/modules/diffusionmodules/util.py:180
↓ 7 callersFunctiontimestep_embedding
Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be
anisoraV1_train_npu/sgm/modules/diffusionmodules/util.py:207
↓ 7 callersFunctiontimestep_embedding
Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be
anisoraV1_train_npu/sat/sgm/modules/diffusionmodules/util.py:180
↓ 7 callersFunctiontimestep_embedding
Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be
anisoraV1_train_gpu/sgm/modules/diffusionmodules/util.py:207
↓ 7 callersFunctiontimestep_embedding
Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be
anisoraV1_train_gpu/sat/sgm/modules/diffusionmodules/util.py:180
↓ 7 callersMethodtokenize
(self, text)
anisoraV1_infer/sat/tokenization/glm/tokenization.py:193
↓ 7 callersMethodtranspose_for_scores
(self, x)
reward/character/BLIP/blip_models/med.py:138
↓ 7 callersMethodtranspose_for_scores
(self, x)
reward/models/nlvr_encoder.py:128
↓ 7 callersMethodtranspose_for_scores
(self, x)
reward/models/med.py:138
↓ 7 callersMethodupload_file
上传本地文件到BOSS @param filename: 本地文件路径 @param object_name: 远程对象相对路径，默认使用本地文件名称
anisoraV2_npu/fastvideo/bili_space/boss/tmp.py:204
↓ 7 callersFunctionuseVideoEffect
()
reward/character/samurai/sam2/demo/frontend/src/common/components/video/editor/useVideoEffect.ts:27
↓ 7 callersMethodwarning
(self, msg)
anisora_rl/SwissArmyTransformer-main/sat/ops/ops_builder/builder.py:416
↓ 7 callersMethodwarning
(self, msg)
anisoraV1_train_npu/swissarmytransformer-npu_t_sp/sat/ops/ops_builder/builder.py:416
↓ 7 callersMethodwarning
(self, msg)
anisoraV1_infer/sat/sat/ops/ops_builder/builder.py:416
↓ 7 callersMethodwarning
(self, msg)
anisoraV1_train_gpu/swissarmytransformer-npu_t_sp/sat/ops/ops_builder/builder.py:416
↓ 6 callersMethodEncodeAsIds
(self, text, process_fn=None)
anisora_rl/SwissArmyTransformer-main/sat/tokenization/cogview/unified_tokenizer.py:80
↓ 6 callersMethodEncodeAsIds
(self, text, process_fn=None)
anisoraV1_train_npu/swissarmytransformer-npu_t_sp/sat/tokenization/cogview/unified_tokenizer.py:80
↓ 6 callersMethodEncodeAsIds
(self, text, process_fn=None)
anisoraV1_infer/sat/tokenization/cogview/unified_tokenizer.py:80
↓ 6 callersMethodEncodeAsIds
(self, text, process_fn=None)
anisoraV1_infer/sat/sat/tokenization/cogview/unified_tokenizer.py:80
↓ 6 callersMethodEncodeAsIds
(self, text, process_fn=None)
anisoraV1_train_gpu/swissarmytransformer-npu_t_sp/sat/tokenization/cogview/unified_tokenizer.py:80
↓ 6 callersMethod__get_rle_mask_list
Return a list of data values, i.e. list of object/mask combos.
reward/character/samurai/sam2/demo/backend/server/inference/predictor.py:364
↓ 6 callersMethod__init__
( self, width, height, hidden_size, num_layers, time_embed_dim
anisora_rl/sat/dit_video_concat.py:539
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisora_rl/sat/sgm/modules/cp_enc_dec.py:434
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisora_rl/sat/vae_modules_infer/cp_enc_dec.py:532
↓ 6 callersMethod__init__
(self, **kwargs)
anisora_rl/sat/vae_modules_infer/autoencoder.py:503
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisora_rl/sat/vae_modules/cp_enc_dec-fix-fail.py:591
↓ 6 callersMethod__init__
(self, **kwargs)
anisora_rl/sat/vae_modules/autoencoder41failed.py:504
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisora_rl/sat/vae_modules/cp_enc_dec41failed.py:621
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisora_rl/sat/vae_modules/cp_enc_dec0.py:561
↓ 6 callersMethod__init__
(self, dim, mid_dim)
anisora_anymask/wan/modules/clip.py:96
↓ 6 callersMethod__init__
(self, dim, mid_dim)
anisoraV3/wan/modules/clip.py:96
↓ 6 callersMethod__init__
( self, width, height, hidden_size, num_layers,
anisoraV1_train_npu/cogvideox.py:428
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisoraV1_train_npu/sgm/modules/cp_enc_dec.py:428
↓ 6 callersMethod__init__
( self, width, height, hidden_size, num_layers, time_embed_dim
anisoraV1_train_npu/sat/dit_video_concat.py:536
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisoraV1_train_npu/sat/sgm/modules/cp_enc_dec.py:434
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisoraV1_train_npu/sat/vae_modules/cp_enc_dec.py:532
↓ 6 callersMethod__init__
(self, **kwargs)
anisoraV1_train_npu/sat/vae_modules/autoencoder.py:503
↓ 6 callersMethod__init__
(self, dim, mid_dim)
anisoraV2_gpu/wan/modules/clip.py:96
↓ 6 callersMethod__init__
( self, chan_in, chan_out, kernel_size: Union[int, Tuple[int, int, int]],
anisoraV2_gpu/fastvideo/models/hunyuan/vae/unet_causal_3d_blocks.py:56
↓ 6 callersMethod__init__
(self, gated_cross_attn_layer: nn.Module, decoder_layer: nn.Module)
reward/mantis/mllm_tools/model_utils/otter/models/otter/modeling_otter.py:399
↓ 6 callersMethod__init__
(self, gated_cross_attn_layer: nn.Module, decoder_layer: nn.Module)
reward/mantis/mllm_tools/model_utils/otter/models/flamingo/modeling_flamingo.py:353
↓ 6 callersMethod__init__
(self, hidden_dim=128, input_dim=192+128)
data_pipeline/core/update.py:17
↓ 6 callersMethod__init__
( self, width, height, hidden_size, num_layers, time_embed_dim
anisoraV1_infer/fastercache/models/cogvideox/dit_video_concat.py:498
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisoraV1_infer/fastercache/models/cogvideox/sgm/modules/cp_enc_dec.py:434
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisoraV1_infer/fastercache/models/cogvideox/vae_modules/cp_enc_dec_fake.py:539
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisoraV1_infer/fastercache/models/cogvideox/vae_modules/cp_enc_dec.py:509
↓ 6 callersMethod__init__
(self, **kwargs)
anisoraV1_infer/fastercache/models/cogvideox/vae_modules/autoencoder.py:537
↓ 6 callersMethod__init__
( self, from_pretrained="DeepFloyd/t5-v1_1-xxl", model_max_length=120, device=
anisoraV1_infer/fastercache/models/opensora/embed.py:257
↓ 6 callersMethod__init__
( self, width, height, hidden_size, num_layers,
anisoraV1_train_gpu/cogvideox.py:428
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisoraV1_train_gpu/sgm/modules/cp_enc_dec.py:428
↓ 6 callersMethod__init__
( self, width, height, hidden_size, num_layers, time_embed_dim
anisoraV1_train_gpu/sat/dit_video_concat.py:536
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisoraV1_train_gpu/sat/sgm/modules/cp_enc_dec.py:434
↓ 6 callersMethod__init__
( self, in_channels, with_conv, compress_time=False, )
anisoraV1_train_gpu/sat/vae_modules/cp_enc_dec.py:532
↓ 6 callersMethod__init__
(self, **kwargs)
anisoraV1_train_gpu/sat/vae_modules/autoencoder.py:503
↓ 6 callersMethod__init__
(self, dim, mid_dim)
anisoraV2_npu/fastvideo/bili_space/wan/modules/clip.py:96
↓ 6 callersMethod__init__
( self, chan_in, chan_out, kernel_size: Union[int, Tuple[int, int, int]],
anisoraV2_npu/fastvideo/models/hunyuan/vae/unet_causal_3d_blocks.py:56
↓ 6 callersMethod__setattr__
(self, __name, __value)
anisoraV1_train_npu/swissarmytransformer-npu_t_sp/sat/model/registry.py:37
↓ 6 callersMethod__setattr__
(self, __name, __value)
anisoraV1_infer/sat/sat/model/registry.py:37
↓ 6 callersMethod__setattr__
(self, __name, __value)
anisoraV1_train_gpu/swissarmytransformer-npu_t_sp/sat/model/registry.py:37
↓ 6 callersFunction_conv_gather
(input_, dim, kernel_size)
anisora_rl/sat/vae_modules/cp_enc_dec.py:212
↓ 6 callersMethod_get_decoder_layers
(self)
reward/mantis/mllm_tools/model_utils/otter/models/otter/modeling_otter.py:453
↓ 6 callersMethod_save_checkpoint
Save a checkpoint while guarding against the job being killed in the middle of checkpoint saving (which corrupts the checkpoint file
reward/character/samurai/sam2/training/trainer.py:363
↓ 6 callersMethod_separate_heads
(self, x: Tensor, num_heads: int)
reward/character/samurai/sam2/sam2/modeling/sam/transformer.py:245
↓ 6 callersFunction_to_tuple
(x, dim=2)
anisoraV2_gpu/fastvideo/models/hunyuan/modules/posemb_layers.py:5
↓ 6 callersFunction_to_tuple
(x, dim=2)
anisoraV2_npu/fastvideo/models/hunyuan/modules/posemb_layers.py:5
↓ 6 callersFunctionall_to_all_comm
(input_, process_group=None, scatter_dim=2, gather_dim=1)
anisoraV1_infer/videosys/core/comm.py:243
↓ 6 callersFunctionapply_fsdp_checkpointing
apply activation checkpointing to model returns None as model is updated directly
anisoraV2_gpu/fastvideo/utils/fsdp_util.py:38
↓ 6 callersFunctionapply_fsdp_checkpointing
apply activation checkpointing to model returns None as model is updated directly
anisoraV2_npu/fastvideo/utils/fsdp_util.py:38
↓ 6 callersFunctionassert_eq
(x, y, msg=None)
anisoraV1_infer/fastercache/models/genmo/mochi_preview/pipelines.py:325
↓ 6 callersMethodattention
(self, h_: torch.Tensor)
anisoraV1_train_npu/sat/sgm/modules/diffusionmodules/model.py:155
↓ 6 callersMethodattention
(self, h_: torch.Tensor)
anisoraV1_train_gpu/sat/sgm/modules/diffusionmodules/model.py:155
↓ 6 callersFunctionauto_create
(name, *, path=None, url=None)
anisoraV1_infer/sat/resources/download.py:42
↓ 6 callersFunctionauto_grad_checkpoint
(module, *args, **kwargs)
anisoraV1_infer/fastercache/models/opensora/utils.py:173
↓ 6 callersFunctioncache_video
(tensor, save_file=None, fps=30, suffix='.mp4',
anisoraV2_gpu/wan/utils/utils.py:23
↓ 6 callersFunctioncompute_packed_indices
Based on https://github.com/Dao-AILab/flash-attention/blob/765741c1eeb86c96ee71a3291ad6968cfbf4e4a1/flash_attn/bert_padding.py#L60-L80 Args:
anisoraV1_infer/fastercache/models/genmo/mochi_preview/pipelines.py:289
↓ 6 callersFunctioncopy_layer_param
in-place copy from src to dst src and dst should be the same layer type, e.g., both are LayerNorm or both are Linear. Or at least, bo
anisoraV1_infer/sat/examples/eva2/transform_param.py:77
↓ 6 callersFunctioncopy_layer_param
in-place copy from src to dst src and dst should be the same layer type, e.g., both are LayerNorm or both are Linear. Or at least, bo
anisoraV1_infer/sat/examples/eva2clip/transform_param.py:64
↓ 6 callersFunctioncopy_layer_param
in-place copy from src to dst src and dst should be the same layer type, e.g., both are LayerNorm or both are Linear. Or at least, bo
anisoraV1_infer/sat/examples/yolos/transform_param.py:22
↓ 6 callersFunctioncopy_layer_param
in-place copy from src to dst src and dst should be the same layer type, e.g., both are LayerNorm or both are Linear. Or at least, bo
anisoraV1_infer/sat/examples/mae/transform_param.py:25
↓ 6 callersFunctioncreate_dataset_function
(path, args)
anisoraV1_infer/sat/tests/test_train.py:105
↓ 6 callersFunctioncustom
(start, end, kw_args_index, cross_layer_index)
anisoraV1_infer/scripts/cogvideox/fastercache_sample_cogvideox.py:198
↓ 6 callersMethoddecode
(self, z: torch.Tensor, **kwargs)
anisoraV1_train_npu/sat/sgm/models/autoencoder.py:217
↓ 6 callersMethoddecode
(self, zs)
anisoraV2_gpu/wan/modules/vae.py:657
↓ 6 callersMethoddecode
This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this
reward/mantis/mllm_tools/model_utils/otter/models/fuyu/processing_fuyu.py:758
↓ 6 callersMethoddecode
(self, z: torch.Tensor, **kwargs)
anisoraV1_train_gpu/sat/sgm/models/autoencoder.py:217
↓ 6 callersMethoddecode
Decode a batch of images/videos. Args: z (`torch.FloatTensor`): Input batch of latent vectors. return_d
anisoraV2_npu/fastvideo/models/hunyuan/vae/autoencoder_kl_causal_3d.py:353
↓ 6 callersMethodenable_tiling
r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and
anisoraV2_gpu/fastvideo/models/hunyuan/vae/autoencoder_kl_causal_3d.py:164
↓ 6 callersMethodenable_tiling
r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and
anisoraV2_npu/fastvideo/models/hunyuan/vae/autoencoder_kl_causal_3d.py:164
↓ 6 callersMethodencode
(self, input_ids, position_ids, attention_mask=None, **kw_args)
anisora_rl/SwissArmyTransformer-main/sat/model/official/mae_model.py:150
↓ 6 callersMethodencode
(self, input_ids, position_ids, attention_mask=None, **kw_args)
anisoraV1_train_npu/swissarmytransformer-npu_t_sp/sat/model/official/mae_model.py:150
↓ 6 callersMethodencode
(self, x)
anisoraV1_infer/fastercache/models/opensora/vae.py:444
↓ 6 callersMethodencode
(self, input_ids, position_ids, attention_mask=None, **kw_args)
anisoraV1_train_gpu/swissarmytransformer-npu_t_sp/sat/model/official/mae_model.py:150
↓ 6 callersMethodencode_first_stage
(self, x, batch)
anisora_rl/sat/diffusion_video.py:167
← previousnext →701–800 of 18,851, ranked by callers