MCPcopy Create free account

hub / github.com/fla-org/flash-linear-attention / functions

Functions2,989 in github.com/fla-org/flash-linear-attention

Methodget_output_embeddings
(self)
fla/models/abc/modeling_abc.py:362
Methodget_output_embeddings
(self)
fla/models/wall_transformer/modeling_wall_transformer.py:380
Methodget_output_embeddings
(self)
fla/models/moba/modeling_moba.py:331
Methodget_output_embeddings
(self)
fla/models/linear_attn/modeling_linear_attn.py:364
Methodget_output_embeddings
(self)
fla/models/mom/modeling_mom.py:469
Methodget_output_embeddings
(self)
fla/models/delta_net/modeling_delta_net.py:362
Methodget_output_embeddings
(self)
fla/models/yoco/modeling_yoco.py:612
Methodget_output_embeddings
(self)
fla/models/hgrn2/modeling_hgrn2.py:367
Methodget_output_embeddings
(self)
fla/models/mesa_net/modeling_mesa_net.py:360
Methodget_output_embeddings
(self)
fla/models/gated_deltaproduct/modeling_gated_deltaproduct.py:364
Methodget_output_embeddings
(self)
fla/models/mamba2/modeling_mamba2.py:345
Methodget_output_embeddings
(self)
fla/models/rodimus/modeling_rodimus.py:474
Methodget_output_embeddings
(self)
fla/models/rwkv7/modeling_rwkv7.py:455
Methodget_output_embeddings
(self)
fla/models/bitnet/modeling_bitnet.py:410
Methodget_output_embeddings
(self)
fla/models/deltaformer/modeling_deltaformer.py:320
Methodget_output_embeddings
(self)
fla/models/hgrn/modeling_hgrn.py:366
Methodget_output_embeddings
(self)
fla/models/gated_deltanet/modeling_gated_deltanet.py:374
Methodget_output_embeddings
(self)
fla/models/retnet/modeling_retnet.py:366
Methodget_output_embeddings
(self)
fla/models/mamba/modeling_mamba.py:276
Methodget_output_embeddings
(self)
fla/models/path_attn/modeling_path_attention.py:372
Methodget_output_embeddings
(self)
fla/models/samba/modeling_samba.py:368
Methodget_output_embeddings
(self)
fla/models/raven/modeling_raven.py:375
Methodget_output_embeddings
(self)
fla/models/forgetting_transformer/modeling_forgetting_transformer.py:373
Methodget_output_embeddings
(self)
fla/models/parallax/modeling_parallax.py:350
Methodget_output_embeddings
(self)
fla/models/rwkv6/modeling_rwkv6.py:361
Methodget_output_embeddings
(self)
fla/models/gla/modeling_gla.py:364
Methodget_output_embeddings
(self)
fla/models/log_linear_mamba2/modeling_log_linear_mamba2.py:421
Methodget_output_embeddings
(self)
fla/models/mamba3/modeling_mamba3.py:260
Methodget_output_embeddings
(self)
fla/models/lightnet/modeling_lightnet.py:357
Methodget_output_embeddings
(self)
fla/models/transformer/modeling_transformer.py:366
Methodget_output_embeddings
(self)
fla/models/comba/modeling_comba.py:373
Methodget_output_embeddings
(self)
fla/models/nsa/modeling_nsa.py:366
Methodget_output_embeddings
(self)
fla/models/kda/modeling_kda.py:391
Methodget_output_embeddings
(self)
fla/models/gsa/modeling_gsa.py:366
Functionget_xpu_memory_usage
Run `xpu-smi stats -d 0` and parse its output.
scripts/check_gpu.py:14
Functiongrid
(meta)
fla/ops/utils/pooling.py:123
Functiongrid
(meta)
fla/ops/utils/matmul.py:199
Functiongrid
(meta)
fla/ops/utils/cumsum.py:309
Functiongrid
(meta)
fla/ops/mesa_net/chunk_h_fwd.py:150
Functiongrid
(meta)
fla/ops/cp/chunk_delta_h.py:798
Functiongrid
(meta)
fla/ops/rwkv7/gate_output_correction.py:201
Functiongrid
(meta)
fla/ops/rwkv7/fused_recurrent.py:158
Functiongrid
(meta)
fla/ops/rwkv7/fused_k_update.py:254
Functiongrid
(meta)
fla/ops/rwkv7/fused_addcmul.py:183
Functiongrid
(meta)
fla/ops/rwkv7/channel_mixing.py:128
Functiongrid
(META)
fla/ops/deltaformer/parallel.py:61
Functiongrid
(meta)
fla/ops/hgrn/fused_recurrent.py:172
Functiongrid
(meta)
fla/ops/wall_attn/decode.py:224
Functiongrid
(meta)
fla/ops/wall_attn/parallel.py:638
Functiongrid
(meta)
fla/ops/gdn2/chunk_intra_token_parallel.py:153
Functiongrid
(meta)
fla/ops/generalized_delta_rule/iplr/chunk.py:231
Functiongrid
(meta)
fla/ops/generalized_delta_rule/dplr/fused_recurrent.py:132
Functiongrid
(meta)
fla/ops/generalized_delta_rule/dplr/chunk_o_bwd.py:315
Functiongrid
(meta)
fla/ops/generalized_delta_rule/dplr/chunk_A_bwd.py:534
Functiongrid
(meta)
fla/ops/generalized_delta_rule/dplr/chunk_o_fwd.py:113
Functiongrid
(meta)
fla/ops/rwkv6/fused_recurrent.py:483
Functiongrid
(meta)
fla/ops/rwkv6/chunk.py:103
Functiongrid
(meta)
fla/ops/gated_delta_product/chunk_deltaproduct_h.py:436
Functiongrid
(meta)
fla/ops/gated_delta_product/chunk_deltaproduct_o.py:141
Functiongrid
(meta: dict[str, Any])
fla/ops/rwkv4/fused_recurrent.py:132
Functiongrid
(meta)
fla/ops/common/intracard_cp.py:113
Functiongrid
(meta)
fla/ops/common/chunk_h_parallel.py:437
Functiongrid
(meta)
fla/ops/common/chunk_delta_h.py:635
Functiongrid
(meta)
fla/ops/common/chunk_h_split.py:466
Functiongrid
(meta)
fla/ops/common/fused_chunk.py:433
Functiongrid
(meta)
fla/ops/common/chunk_o.py:527
Functiongrid
(meta)
fla/ops/common/chunk_h.py:324
Functiongrid
(meta)
fla/ops/gla/chunk.py:904
Functiongrid
(meta)
fla/ops/gated_delta_rule/gate.py:271
Functiongrid
(meta)
fla/ops/gated_oja_rule/chunk_o.py:209
Functiongrid
(meta)
fla/ops/gated_oja_rule/chunk_h.py:227
Functiongrid
(meta)
fla/ops/attnres/fused.py:419
Functiongrid
(meta)
fla/ops/kda/chunk_intra_token_parallel.py:160
Functiongrid
(meta)
fla/ops/kda/gate.py:222
Functiongrid
(meta)
fla/ops/gsa/chunk.py:588
Functiongrid
(meta)
fla/modules/layernorm.py:580
Functiongrid
(meta)
fla/modules/token_shift.py:430
Functiongrid
(meta)
fla/modules/l2norm.py:165
Functiongrid
(meta)
fla/modules/fused_norm_gate.py:485
Functiongrid
(META)
fla/modules/backends/triton_ascend/fused_cross_entropy.py:254
Functiongrid
(meta)
fla/modules/conv/triton/ops.py:66
Functiongrid
(meta)
fla/modules/conv/triton/kernels.py:665
Methodgrid
(meta)
fla/ops/rwkv7/gate_output_correction.py:231
Methodgrid
(meta)
fla/ops/rwkv7/fused_addcmul.py:243
Methodgrid
(meta)
fla/ops/hgrn/chunk.py:230
Methodgrid
(meta)
fla/ops/generalized_delta_rule/iplr/fused_recurrent.py:308
Methodgrid
(meta)
fla/ops/log_linear_attn/chunk.py:1633
Methodgrid
(META)
fla/modules/fused_cross_entropy.py:302
Functiongrid_bp
(META)
fla/ops/deltaformer/parallel.py:84
Methodgrid_f
(meta)
fla/ops/log_linear_attn/chunk.py:1757
Functiongroup_norm_linear
( x: torch.Tensor, norm_weight: torch.Tensor, norm_bias: torch.Tensor, linear_weight: torch.Te
fla/modules/layernorm.py:942
Functiongrpo_bwd_kernel
( dloss_ptr, dlogits_ptr, logits_ptr, ref_logp_ptr, input_ids_ptr, advantages_ptr,
fla/modules/grpo.py:157
Functiongrpo_bwd_kernel
( dloss_ptr, dlogits_ptr, logits_ptr, ref_logp_ptr, input_ids_ptr, advantages_ptr,
fla/modules/backends/triton_ascend/grpo.py:96
Functiongrpo_fwd_kernel
( logits_ptr, ref_logp_ptr, input_ids_ptr, advantages_ptr, completion_mask_ptr, loss_p
fla/modules/grpo.py:81
Functiongrpo_fwd_kernel
( logits_ptr, ref_logp_ptr, input_ids_ptr, advantages_ptr, completion_mask_ptr, loss_p
fla/modules/backends/triton_ascend/grpo.py:30
Functiongrpo_loss_with_old_logps
Compute the GRPO (Group Relative Policy Optimization) loss. Args: logps (torch.Tensor): [Batch, Token_length] Log probabilities of t
fla/modules/grpo.py:360
Functionhmamba_split_conv1d_scan_combined
Argument: zxbcdtdl: (batch, seqlen, 2 * dim + 2 * ngroups * dstate + nheads) where dim == nheads * headdim conv1d_weight: (dim +
fla/layers/log_linear_mamba2.py:130
Functionidentity_decorator
(fn)
fla/ops/rwkv7/fused_addcmul.py:25
Functioninit_weights_recursively
(module)
tests/models/test_modeling_utils.py:88
Functioninitialize_chunked_param
(B, H, T, BT, dtype=torch.float32)
tests/ops/test_titans.py:16
← previousnext →2,101–2,200 of 2,989, ranked by callers