Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/fla-org/flash-linear-attention
/ functions
Functions
2,989 in github.com/fla-org/flash-linear-attention
⨍
Functions
2,989
◇
Types & classes
403
↳
Endpoints
219
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/layers/rwkv6.py:114
Method
forward
(self, x: torch.Tensor)
fla/layers/rwkv6.py:294
Method
forward
(self, x: torch.Tensor, delta: torch.Tensor | None = None, cu_seqlens: torch.LongTensor | None
fla/layers/rwkv6.py:326
Method
forward
(self, x: torch.Tensor, mu: torch.Tensor, delta: torch.Tensor | None = None, c
fla/layers/rwkv6.py:360
Method
forward
(self, hidden_states: torch.Tensor, **kwargs)
fla/layers/rebased.py:66
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/layers/kda.py:194
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/layers/comba.py:212
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/layers/gated_deltanet.py:201
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/layers/hgrn.py:84
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/mla/modeling_mla.py:86
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/mla/modeling_mla.py:246
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/mla/modeling_mla.py:376
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/abc/modeling_abc.py:100
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/abc/modeling_abc.py:260
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/abc/modeling_abc.py:390
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/wall_transformer/modeling_wall_transformer.py:93
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/wall_transformer/modeling_wall_transformer.py:268
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/wall_transformer/modeling_wall_transformer.py:393
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/moba/modeling_moba.py:86
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/moba/modeling_moba.py:234
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/moba/modeling_moba.py:359
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/linear_attn/modeling_linear_attn.py:100
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/linear_attn/modeling_linear_attn.py:260
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/linear_attn/modeling_linear_attn.py:392
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/mom/modeling_mom.py:188
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/mom/modeling_mom.py:351
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/mom/modeling_mom.py:496
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/delta_net/modeling_delta_net.py:100
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/delta_net/modeling_delta_net.py:260
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/delta_net/modeling_delta_net.py:390
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/yoco/modeling_yoco.py:127
Method
forward
( self, hidden_states: torch.Tensor, shared_k: torch.Tensor, shared_v: torch.T
fla/models/yoco/modeling_yoco.py:238
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/yoco/modeling_yoco.py:457
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/yoco/modeling_yoco.py:677
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/hgrn2/modeling_hgrn2.py:95
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/hgrn2/modeling_hgrn2.py:259
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/hgrn2/modeling_hgrn2.py:395
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/mesa_net/modeling_mesa_net.py:98
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/mesa_net/modeling_mesa_net.py:258
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/mesa_net/modeling_mesa_net.py:388
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/gated_deltaproduct/modeling_gated_deltaproduct.py:99
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/gated_deltaproduct/modeling_gated_deltaproduct.py:262
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/gated_deltaproduct/modeling_gated_deltaproduct.py:392
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/mamba2/modeling_mamba2.py:106
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/mamba2/modeling_mamba2.py:271
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/mamba2/modeling_mamba2.py:358
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/rodimus/modeling_rodimus.py:128
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/rodimus/modeling_rodimus.py:371
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/rodimus/modeling_rodimus.py:502
Method
forward
( self, x: torch.Tensor, attention_mask: torch.Tensor | None = None, state: Ca
fla/models/rwkv7/modeling_rwkv7.py:98
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/rwkv7/modeling_rwkv7.py:182
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/rwkv7/modeling_rwkv7.py:363
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/rwkv7/modeling_rwkv7.py:483
Method
forward
( self, x: torch.Tensor, **kwargs: Unpack[Any], )
fla/models/bitnet/modeling_bitnet.py:74
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/bitnet/modeling_bitnet.py:130
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/bitnet/modeling_bitnet.py:298
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/bitnet/modeling_bitnet.py:423
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/deltaformer/modeling_deltaformer.py:79
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/deltaformer/modeling_deltaformer.py:210
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/deltaformer/modeling_deltaformer.py:348
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/hgrn/modeling_hgrn.py:94
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/hgrn/modeling_hgrn.py:258
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/hgrn/modeling_hgrn.py:394
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/gated_deltanet/modeling_gated_deltanet.py:98
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/gated_deltanet/modeling_gated_deltanet.py:272
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/gated_deltanet/modeling_gated_deltanet.py:402
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/retnet/modeling_retnet.py:99
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/retnet/modeling_retnet.py:262
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/retnet/modeling_retnet.py:395
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/mamba/modeling_mamba.py:70
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/mamba/modeling_mamba.py:196
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/mamba/modeling_mamba.py:289
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/path_attn/modeling_path_attention.py:88
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/path_attn/modeling_path_attention.py:259
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/path_attn/modeling_path_attention.py:385
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/samba/modeling_samba.py:98
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/samba/modeling_samba.py:268
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/samba/modeling_samba.py:381
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/raven/modeling_raven.py:112
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/raven/modeling_raven.py:272
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/raven/modeling_raven.py:403
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/forgetting_transformer/modeling_forgetting_transformer.py:89
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/forgetting_transformer/modeling_forgetting_transformer.py:260
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/forgetting_transformer/modeling_forgetting_transformer.py:386
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/parallax/modeling_parallax.py:87
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/parallax/modeling_parallax.py:244
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/parallax/modeling_parallax.py:363
Method
forward
( self, x: torch.Tensor, attention_mask: torch.Tensor | None = None, state: Ca
fla/models/rwkv6/modeling_rwkv6.py:72
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/rwkv6/modeling_rwkv6.py:158
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/rwkv6/modeling_rwkv6.py:272
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/rwkv6/modeling_rwkv6.py:389
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/gla/modeling_gla.py:102
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: Optional[torch.Tens
fla/models/gla/modeling_gla.py:262
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None
fla/models/gla/modeling_gla.py:392
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/log_linear_mamba2/modeling_log_linear_mamba2.py:76
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/log_linear_mamba2/modeling_log_linear_mamba2.py:300
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/log_linear_mamba2/modeling_log_linear_mamba2.py:434
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None,
fla/models/mamba3/modeling_mamba3.py:60
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/mamba3/modeling_mamba3.py:187
Method
forward
( self, input_ids: torch.LongTensor | None = None, attention_mask: torch.Tensor | None
fla/models/mamba3/modeling_mamba3.py:273
← previous
next →
1,801–1,900 of 2,989, ranked by callers