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
__init__
(self, config: MLAConfig)
fla/models/mla/modeling_mla.py:221
Method
__init__
(self, config: MLAConfig)
fla/models/mla/modeling_mla.py:332
Method
__init__
( self, hidden_size: int = 2048, num_hidden_layers: int = 24, num_heads: int =
fla/models/mla/configuration_mla.py:18
Method
__init__
( self, hidden_size: int = 2048, gate_low_rank_dim: int = 16, clamp_min: float
fla/models/abc/configuration_abc.py:18
Method
__init__
(self, *inputs, **kwargs)
fla/models/abc/modeling_abc.py:183
Method
__init__
(self, config: ABCConfig)
fla/models/abc/modeling_abc.py:235
Method
__init__
(self, config)
fla/models/abc/modeling_abc.py:346
Method
__init__
(self, *inputs, **kwargs)
fla/models/wall_transformer/modeling_wall_transformer.py:183
Method
__init__
( self, config: WallTransformerConfig, )
fla/models/wall_transformer/modeling_wall_transformer.py:236
Method
__init__
(self, config)
fla/models/wall_transformer/modeling_wall_transformer.py:364
Method
__init__
( self, hidden_size: int = 2048, num_hidden_layers: int = 24, num_heads: int =
fla/models/wall_transformer/configuration_wall_transformer.py:20
Method
__init__
(self, *inputs, **kwargs)
fla/models/moba/modeling_moba.py:169
Method
__init__
(self, config: MoBAConfig)
fla/models/moba/modeling_moba.py:209
Method
__init__
(self, config)
fla/models/moba/modeling_moba.py:316
Method
__init__
( self, hidden_size: int = 2048, num_hidden_layers: int = 24, num_heads: int =
fla/models/moba/configuration_moba.py:18
Method
__init__
(self, *inputs, **kwargs)
fla/models/linear_attn/modeling_linear_attn.py:183
Method
__init__
(self, config: LinearAttentionConfig)
fla/models/linear_attn/modeling_linear_attn.py:235
Method
__init__
(self, config)
fla/models/linear_attn/modeling_linear_attn.py:348
Method
__init__
( self, attn_mode: str = "fused_chunk", hidden_size: int = 2048, expand_k: flo
fla/models/linear_attn/configuration_linear_attn.py:18
Method
__init__
(self, *inputs, **kwargs)
fla/models/mom/modeling_mom.py:274
Method
__init__
(self, config: MomConfig)
fla/models/mom/modeling_mom.py:325
Method
__init__
(self, config)
fla/models/mom/modeling_mom.py:451
Method
__init__
( self, attn_mode: str = "chunk", hidden_size: int = 2048, conv_size: int = 4,
fla/models/mom/configuration_mom.py:15
Method
__init__
(self, *inputs, **kwargs)
fla/models/delta_net/modeling_delta_net.py:183
Method
__init__
(self, config: DeltaNetConfig)
fla/models/delta_net/modeling_delta_net.py:235
Method
__init__
(self, config)
fla/models/delta_net/modeling_delta_net.py:346
Method
__init__
( self, attn_mode: str = "chunk", hidden_size: int = 2048, expand_k: float = 1
fla/models/delta_net/configuration_delta_net.py:18
Method
__init__
( self, hidden_size: int = 2048, num_self_decoder_layers: int = 10, self_decod
fla/models/yoco/configuration_yoco.py:16
Method
__init__
(self, config: YOCOConfig, layer_idx: int)
fla/models/yoco/modeling_yoco.py:56
Method
__init__
(self, config: YOCOConfig, layer_idx: int)
fla/models/yoco/modeling_yoco.py:199
Method
__init__
(self, *inputs, **kwargs)
fla/models/yoco/modeling_yoco.py:316
Method
__init__
(self, config)
fla/models/yoco/modeling_yoco.py:598
Method
__init__
( self, hidden_size: int = 2048, num_hidden_layers: int = 24, attn_mode: str =
fla/models/hgrn2/configuration_hgrn2.py:18
Method
__init__
(self, *inputs, **kwargs)
fla/models/hgrn2/modeling_hgrn2.py:180
Method
__init__
(self, config: HGRN2Config)
fla/models/hgrn2/modeling_hgrn2.py:232
Method
__init__
(self, config)
fla/models/hgrn2/modeling_hgrn2.py:351
Method
__init__
( self, attn_mode: str = "chunk", hidden_size: int = 2048, use_output_gate: bo
fla/models/mesa_net/configuration_mesa_net.py:17
Method
__init__
(self, *inputs, **kwargs)
fla/models/mesa_net/modeling_mesa_net.py:181
Method
__init__
(self, config: MesaNetConfig)
fla/models/mesa_net/modeling_mesa_net.py:233
Method
__init__
(self, config)
fla/models/mesa_net/modeling_mesa_net.py:344
Method
__init__
( self, attn_mode: str = "chunk", conv_size: int = 4, head_dim: int = 256,
fla/models/gated_deltaproduct/configuration_gated_deltaproduct.py:17
Method
__init__
(self, *inputs, **kwargs)
fla/models/gated_deltaproduct/modeling_gated_deltaproduct.py:182
Method
__init__
(self, config: GatedDeltaProductConfig)
fla/models/gated_deltaproduct/modeling_gated_deltaproduct.py:234
Method
__init__
(self, config)
fla/models/gated_deltaproduct/modeling_gated_deltaproduct.py:348
Method
__init__
(self, config)
fla/models/mamba2/modeling_mamba2.py:247
Method
__init__
(self, config)
fla/models/mamba2/modeling_mamba2.py:336
Method
__init__
( self, head_dim: int = 64, vocab_size: int = 32000, hidden_size: int = 2048,
fla/models/mamba2/configuration_mamba2.py:100
Method
__init__
( self, block_type: str = 'rodimus_plus', hidden_size: int = 2048, num_hidden_
fla/models/rodimus/configuration_rodimus.py:18
Method
__init__
(self, *inputs, **kwargs)
fla/models/rodimus/modeling_rodimus.py:251
Method
__init__
(self, config: RodimusConfig)
fla/models/rodimus/modeling_rodimus.py:338
Method
__init__
(self, config)
fla/models/rodimus/modeling_rodimus.py:458
Method
__init__
( self, hidden_size: int, hidden_ratio: int | None = None, intermediate_size:
fla/models/rwkv7/modeling_rwkv7.py:44
Method
__init__
(self, *inputs, **kwargs)
fla/models/rwkv7/modeling_rwkv7.py:230
Method
__init__
(self, config: RWKV7Config)
fla/models/rwkv7/modeling_rwkv7.py:290
Method
__init__
(self, config)
fla/models/rwkv7/modeling_rwkv7.py:439
Method
__init__
( self, attn_mode: str = "chunk", hidden_size: int = 2048, hidden_ratio: int |
fla/models/rwkv7/configuration_rwkv7.py:18
Method
__init__
(self, config: BitNetConfig, layer_idx: int)
fla/models/bitnet/modeling_bitnet.py:85
Method
__init__
(self, *inputs, **kwargs)
fla/models/bitnet/modeling_bitnet.py:220
Method
__init__
( self, config: BitNetConfig, )
fla/models/bitnet/modeling_bitnet.py:269
Method
__init__
(self, config)
fla/models/bitnet/modeling_bitnet.py:394
Method
__init__
( self, hidden_size: int = 2048, num_hidden_layers: int = 24, num_heads: int =
fla/models/bitnet/configuration_bitnet.py:18
Method
__init__
( self, hidden_size: int = 2048, hidden_ratio: int | None = 4, intermediate_si
fla/models/deltaformer/configuration_deltaformer.py:19
Method
__init__
(self, *inputs, **kwargs)
fla/models/deltaformer/modeling_deltaformer.py:161
Method
__init__
(self, config: DeltaFormerConfig)
fla/models/deltaformer/modeling_deltaformer.py:185
Method
__init__
(self, config: DeltaFormerConfig)
fla/models/deltaformer/modeling_deltaformer.py:297
Method
__init__
(self, *inputs, **kwargs)
fla/models/hgrn/modeling_hgrn.py:179
Method
__init__
(self, config: HGRNConfig)
fla/models/hgrn/modeling_hgrn.py:231
Method
__init__
(self, config)
fla/models/hgrn/modeling_hgrn.py:350
Method
__init__
( self, attn_mode: str = "fused_recurrent", hidden_size: int = 2048, num_hidde
fla/models/hgrn/configuration_hgrn.py:18
Method
__init__
( self, attn_mode: str = "chunk", hidden_size: int = 2048, expand_v: float = 2
fla/models/gated_deltanet/configuration_gated_deltanet.py:17
Method
__init__
(self, *inputs, **kwargs)
fla/models/gated_deltanet/modeling_gated_deltanet.py:181
Method
__init__
(self, config: GatedDeltaNetConfig)
fla/models/gated_deltanet/modeling_gated_deltanet.py:247
Method
__init__
(self, config)
fla/models/gated_deltanet/modeling_gated_deltanet.py:358
Method
__init__
(self, *inputs, **kwargs)
fla/models/retnet/modeling_retnet.py:183
Method
__init__
(self, config: RetNetConfig)
fla/models/retnet/modeling_retnet.py:235
Method
__init__
(self, config)
fla/models/retnet/modeling_retnet.py:350
Method
__init__
( self, attn_mode: str = "chunk", hidden_size: int = 2048, expand_k: float = 1
fla/models/retnet/configuration_retnet.py:20
Method
__init__
(self, config)
fla/models/mamba/modeling_mamba.py:172
Method
__init__
(self, config)
fla/models/mamba/modeling_mamba.py:267
Method
__init__
( self, vocab_size: int = 32000, hidden_size: int = 2048, state_size: int = 16
fla/models/mamba/configuration_mamba.py:109
Method
__init__
(self, *inputs, **kwargs)
fla/models/path_attn/modeling_path_attention.py:178
Method
__init__
( self, config: PaTHAttentionConfig, )
fla/models/path_attn/modeling_path_attention.py:227
Method
__init__
(self, config)
fla/models/path_attn/modeling_path_attention.py:356
Method
__init__
( self, hidden_size: int = 2048, num_hidden_layers: int = 24, num_heads: int =
fla/models/path_attn/configuration_path_attention.py:18
Method
__init__
(self, config)
fla/models/samba/modeling_samba.py:243
Method
__init__
(self, config)
fla/models/samba/modeling_samba.py:359
Method
__init__
( self, hidden_size: int = 2304, state_size: int = 16, num_hidden_layers: int
fla/models/samba/configuration_samba.py:18
Method
__init__
(self, *inputs, **kwargs)
fla/models/raven/modeling_raven.py:195
Method
__init__
(self, config: RavenConfig)
fla/models/raven/modeling_raven.py:247
Method
__init__
(self, config)
fla/models/raven/modeling_raven.py:358
Method
__init__
( self, hidden_size: int = 2048, gate_logit_normalizer: int | None = 8, hidden
fla/models/raven/configuration_raven.py:21
Method
__init__
(self, *inputs, **kwargs)
fla/models/forgetting_transformer/modeling_forgetting_transformer.py:179
Method
__init__
( self, config: ForgettingTransformerConfig, )
fla/models/forgetting_transformer/modeling_forgetting_transformer.py:228
Method
__init__
(self, config)
fla/models/forgetting_transformer/modeling_forgetting_transformer.py:357
Method
__init__
( self, hidden_size: int = 2048, num_hidden_layers: int = 24, num_heads: int =
fla/models/forgetting_transformer/configuration_forgetting_transformer.py:18
Method
__init__
(self, *inputs, **kwargs)
fla/models/parallax/modeling_parallax.py:167
Method
__init__
(self, config: ParallaxConfig)
fla/models/parallax/modeling_parallax.py:216
Method
__init__
(self, config)
fla/models/parallax/modeling_parallax.py:334
Method
__init__
( self, hidden_size: int = 2048, num_hidden_layers: int = 24, num_heads: int =
fla/models/parallax/configuration_parallax.py:21
Method
__init__
( self, hidden_size: int, hidden_ratio: int | None = None, intermediate_size:
fla/models/rwkv6/modeling_rwkv6.py:44
← previous
next →
1,101–1,200 of 2,989, ranked by callers