├── .flake8 ├── .github ├── ISSUE_TEMPLATE │ ├── bug.yml │ ├── config.yml │ ├── feature-request.yml │ └── rfc.yml └── workflows │ ├── intel-b580.yml │ ├── issue.yml │ ├── lint.yaml │ ├── nvidia-4090.yml │ ├── nvidia-a100.yml │ ├── nvidia-h100.yml │ ├── pytorch-ci.yml │ ├── release.yml │ ├── reusable-build-triton.yml │ ├── reusable-ci-tests.yml │ ├── triton-builder.yml │ └── triton-nightly.yml ├── .gitignore ├── .pre-commit-config.yaml ├── CITATION.cff ├── ENVs.md ├── FAQs.md ├── LICENSE ├── README.md ├── benchmarks ├── benchmark_generation.py ├── benchmark_training_throughput.py ├── modules │ ├── benchmark_activations.py │ ├── benchmark_conv.py │ ├── benchmark_cross_entropy.py │ ├── benchmark_l2norm.py │ ├── benchmark_layernorm.py │ └── benchmark_tokenshift.py └── ops │ ├── benchmark.py │ ├── benchmark_abc.py │ ├── benchmark_based.py │ ├── benchmark_delta_rule.py │ ├── benchmark_fla.py │ ├── benchmark_gla.py │ ├── benchmark_gsa.py │ ├── benchmark_hgrn.py │ ├── benchmark_kda.py │ ├── benchmark_nsa.py │ ├── benchmark_retention.py │ ├── benchmark_rwkv.py │ ├── benchmark_rwkv7_fused_addcmul.py │ ├── benchmark_rwkv7_k_update.py │ ├── benchmark_simple_gla_vs_mamba2.py │ ├── benchmark_solv_tril.py │ ├── benchmark_titans.py │ └── benchmark_ttt.py ├── evals ├── harness.py └── ppl.py ├── examples └── training.md ├── fla ├── __init__.py ├── layers │ ├── __init__.py │ ├── abc.py │ ├── attn.py │ ├── based.py │ ├── bitattn.py │ ├── comba.py │ ├── delta_net.py │ ├── deltaformer.py │ ├── forgetting_attn.py │ ├── gated_deltanet.py │ ├── gated_deltaproduct.py │ ├── gla.py │ ├── gsa.py │ ├── hgrn.py │ ├── hgrn2.py │ ├── kda.py │ ├── lightnet.py │ ├── linear_attn.py │ ├── log_linear_mamba2.py │ ├── mamba.py │ ├── mamba2.py │ ├── mesa_net.py │ ├── mla.py │ ├── mom.py │ ├── multiscale_retention.py │ ├── nsa.py │ ├── path_attn.py │ ├── rebased.py │ ├── rodimus.py │ ├── rwkv6.py │ ├── rwkv7.py │ ├── simple_gla.py │ └── utils.py ├── models │ ├── __init__.py │ ├── abc │ │ ├── __init__.py │ │ ├── configuration_abc.py │ │ └── modeling_abc.py │ ├── bitnet │ │ ├── __init__.py │ │ ├── configuration_bitnet.py │ │ └── modeling_bitnet.py │ ├── comba │ │ ├── __init__.py │ │ ├── configuration_comba.py │ │ └── modeling_comba.py │ ├── delta_net │ │ ├── __init__.py │ │ ├── configuration_delta_net.py │ │ └── modeling_delta_net.py │ ├── deltaformer │ │ ├── __init__.py │ │ ├── configuration_deltaformer.py │ │ └── modeling_deltaformer.py │ ├── forgetting_transformer │ │ ├── __init__.py │ │ ├── configuration_forgetting_transformer.py │ │ └── modeling_forgetting_transformer.py │ ├── gated_deltanet │ │ ├── __init__.py │ │ ├── configuration_gated_deltanet.py │ │ └── modeling_gated_deltanet.py │ ├── gated_deltaproduct │ │ ├── __init__.py │ │ ├── configuration_gated_deltaproduct.py │ │ └── modeling_gated_deltaproduct.py │ ├── gla │ │ ├── __init__.py │ │ ├── configuration_gla.py │ │ └── modeling_gla.py │ ├── gsa │ │ ├── __init__.py │ │ ├── configuration_gsa.py │ │ └── modeling_gsa.py │ ├── hgrn │ │ ├── __init__.py │ │ ├── configuration_hgrn.py │ │ └── modeling_hgrn.py │ ├── hgrn2 │ │ ├── __init__.py │ │ ├── configuration_hgrn2.py │ │ └── modeling_hgrn2.py │ ├── kda │ │ ├── __init__.py │ │ ├── configuration_kda.py │ │ └── modeling_kda.py │ ├── lightnet │ │ ├── __init__.py │ │ ├── configuration_lightnet.py │ │ └── modeling_lightnet.py │ ├── linear_attn │ │ ├── __init__.py │ │ ├── configuration_linear_attn.py │ │ └── modeling_linear_attn.py │ ├── log_linear_mamba2 │ │ ├── __init__.py │ │ ├── configuration_log_linear_mamba2.py │ │ └── modeling_log_linear_mamba2.py │ ├── mamba │ │ ├── __init__.py │ │ ├── configuration_mamba.py │ │ └── modeling_mamba.py │ ├── mamba2 │ │ ├── __init__.py │ │ ├── configuration_mamba2.py │ │ └── modeling_mamba2.py │ ├── mesa_net │ │ ├── __init__.py │ │ ├── configuration_mesa_net.py │ │ └── modeling_mesa_net.py │ ├── mla │ │ ├── __init__.py │ │ ├── configuration_mla.py │ │ └── modeling_mla.py │ ├── modeling_layers.py │ ├── mom │ │ ├── __init__.py │ │ ├── configuration_mom.py │ │ └── modeling_mom.py │ ├── nsa │ │ ├── __init__.py │ │ ├── configuration_nsa.py │ │ └── modeling_nsa.py │ ├── path_attn │ │ ├── __init__.py │ │ ├── configuration_path_attention.py │ │ └── modeling_path_attention.py │ ├── retnet │ │ ├── __init__.py │ │ ├── configuration_retnet.py │ │ └── modeling_retnet.py │ ├── rodimus │ │ ├── __init__.py │ │ ├── configuration_rodimus.py │ │ └── modeling_rodimus.py │ ├── rwkv6 │ │ ├── __init__.py │ │ ├── configuration_rwkv6.py │ │ └── modeling_rwkv6.py │ ├── rwkv7 │ │ ├── __init__.py │ │ ├── configuration_rwkv7.py │ │ └── modeling_rwkv7.py │ ├── samba │ │ ├── __init__.py │ │ ├── configuration_samba.py │ │ └── modeling_samba.py │ ├── transformer │ │ ├── __init__.py │ │ ├── configuration_transformer.py │ │ └── modeling_transformer.py │ └── utils.py ├── modules │ ├── __init__.py │ ├── activations.py │ ├── convolution.py │ ├── feature_map.py │ ├── fused_bitlinear.py │ ├── fused_cross_entropy.py │ ├── fused_kl_div.py │ ├── fused_linear_cross_entropy.py │ ├── fused_norm_gate.py │ ├── grpo.py │ ├── l2norm.py │ ├── l2warp.py │ ├── layernorm.py │ ├── layernorm_gated.py │ ├── mlp.py │ ├── parallel.py │ ├── rotary.py │ └── token_shift.py ├── ops │ ├── __init__.py │ ├── abc │ │ ├── __init__.py │ │ ├── chunk.py │ │ └── naive.py │ ├── attn │ │ ├── __init__.py │ │ ├── decoding.py │ │ └── parallel.py │ ├── based │ │ ├── __init__.py │ │ ├── fused_chunk.py │ │ ├── naive.py │ │ └── parallel.py │ ├── comba │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── fused_recurrent.py │ │ ├── utils.py │ │ └── wy_fast.py │ ├── common │ │ ├── __init__.py │ │ ├── chunk_delta_h.py │ │ ├── chunk_h.py │ │ ├── chunk_h_parallel.py │ │ ├── chunk_h_split.py │ │ ├── chunk_o.py │ │ ├── chunk_scaled_dot_kkt.py │ │ ├── fused_chunk.py │ │ └── fused_recurrent.py │ ├── delta_rule │ │ ├── README.md │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── fused_chunk.py │ │ ├── fused_recurrent.py │ │ ├── naive.py │ │ ├── parallel.py │ │ └── wy_fast.py │ ├── deltaformer │ │ ├── __init__.py │ │ ├── invcum.py │ │ ├── naive.py │ │ └── parallel.py │ ├── forgetting_attn │ │ ├── __init__.py │ │ └── parallel.py │ ├── gated_delta_product │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── chunk_deltaproduct_h.py │ │ ├── chunk_deltaproduct_o.py │ │ ├── chunk_ref.py │ │ └── naive.py │ ├── gated_delta_rule │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── fused_recurrent.py │ │ └── wy_fast.py │ ├── generalized_delta_rule │ │ ├── README.md │ │ ├── __init__.py │ │ ├── dplr │ │ │ ├── __init__.py │ │ │ ├── chunk.py │ │ │ ├── chunk_A_bwd.py │ │ │ ├── chunk_A_fwd.py │ │ │ ├── chunk_h_bwd.py │ │ │ ├── chunk_h_fwd.py │ │ │ ├── chunk_o_bwd.py │ │ │ ├── chunk_o_fwd.py │ │ │ ├── fused_recurrent.py │ │ │ ├── naive.py │ │ │ ├── wy_fast_bwd.py │ │ │ └── wy_fast_fwd.py │ │ └── iplr │ │ │ ├── __init__.py │ │ │ ├── chunk.py │ │ │ ├── fused_recurrent.py │ │ │ ├── naive.py │ │ │ └── wy_fast.py │ ├── gla │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── fused_chunk.py │ │ ├── fused_recurrent.py │ │ └── naive.py │ ├── gsa │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── fused_recurrent.py │ │ └── naive.py │ ├── hgrn │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── fused_recurrent.py │ │ └── naive.py │ ├── kda │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── chunk_inter.py │ │ ├── chunk_intra.py │ │ ├── chunk_intra_token_parallel.py │ │ ├── fused_recurrent.py │ │ ├── gate.py │ │ ├── naive.py │ │ └── wy_fast.py │ ├── lightning_attn │ │ ├── __init__.py │ │ ├── chunk.py │ │ └── fused_recurrent.py │ ├── linear_attn │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── fused_chunk.py │ │ ├── fused_recurrent.py │ │ ├── naive.py │ │ └── utils.py │ ├── log_linear_attn │ │ ├── __init__.py │ │ ├── chunk.py │ │ └── naive.py │ ├── mesa_net │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── chunk_cg_solver_bwd.py │ │ ├── chunk_cg_solver_fwd.py │ │ ├── chunk_h_fwd.py │ │ ├── chunk_h_kk_intra_bwd.py │ │ ├── chunk_h_kv_intra_bwd.py │ │ ├── chunk_h_kv_intra_bwd_separate.py │ │ ├── decoding_one_step.py │ │ └── naive.py │ ├── nsa │ │ ├── __init__.py │ │ ├── compression.py │ │ ├── naive.py │ │ ├── parallel.py │ │ └── utils.py │ ├── path_attn │ │ ├── __init__.py │ │ ├── cumprod_householder_bwd.py │ │ ├── cumprod_householder_fwd.py │ │ ├── intra_chunk_preprocess_bwd.py │ │ ├── intra_chunk_preprocess_bwd_prepare.py │ │ ├── intra_chunk_preprocess_fwd.py │ │ ├── parallel.py │ │ ├── parallel_path_bwd_inter_dkv.py │ │ ├── parallel_path_bwd_inter_dqh.py │ │ ├── parallel_path_bwd_intra.py │ │ ├── parallel_path_fwd.py │ │ ├── prepare_k_cache.py │ │ └── transform_q.py │ ├── rebased │ │ ├── __init__.py │ │ ├── naive.py │ │ └── parallel.py │ ├── retention │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── fused_chunk.py │ │ ├── fused_recurrent.py │ │ ├── naive.py │ │ └── parallel.py │ ├── rwkv4 │ │ ├── __init__.py │ │ └── fused_recurrent.py │ ├── rwkv6 │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── chunk_naive.py │ │ ├── fused_recurrent.py │ │ └── recurrent_naive.py │ ├── rwkv7 │ │ ├── RWKV7(Goose).md │ │ ├── __init__.py │ │ ├── channel_mixing.py │ │ ├── chunk.py │ │ ├── fused_addcmul.py │ │ ├── fused_k_update.py │ │ ├── fused_recurrent.py │ │ └── gate_output_correction.py │ ├── simple_gla │ │ ├── README.md │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── fused_chunk.py │ │ ├── fused_recurrent.py │ │ ├── naive.py │ │ └── parallel.py │ ├── titans │ │ ├── __init__.py │ │ ├── log_impl.py │ │ └── naive.py │ ├── ttt │ │ ├── __init__.py │ │ ├── chunk.py │ │ ├── fused_chunk.py │ │ └── naive.py │ └── utils │ │ ├── __init__.py │ │ ├── constant.py │ │ ├── cumsum.py │ │ ├── index.py │ │ ├── logcumsumexp.py │ │ ├── logsumexp.py │ │ ├── matmul.py │ │ ├── op.py │ │ ├── pack.py │ │ ├── pooling.py │ │ ├── softmax.py │ │ ├── softplus.py │ │ └── solve_tril.py └── utils.py ├── legacy └── training │ ├── README.md │ ├── configs │ ├── gla_1B.json │ ├── gla_340M.json │ ├── gla_7B.json │ └── transformer_340M.json │ ├── flame │ ├── __init__.py │ ├── data.py │ ├── logging.py │ └── parser.py │ ├── preprocess.py │ ├── run.py │ └── train.sh ├── pyproject.toml ├── scripts ├── build_packages.py ├── check_gpu.py └── find_dependent_tests.py ├── setup.py ├── tests ├── models │ ├── __init__.py │ ├── test_modeling_abc.py │ ├── test_modeling_base.py │ ├── test_modeling_bitnet.py │ ├── test_modeling_comba.py │ ├── test_modeling_deltaformer.py │ ├── test_modeling_deltanet.py │ ├── test_modeling_forgetting_transformer.py │ ├── test_modeling_gated_deltanet.py │ ├── test_modeling_gated_deltaproduct.py │ ├── test_modeling_gla.py │ ├── test_modeling_gsa.py │ ├── test_modeling_hgrn.py │ ├── test_modeling_hgrn2.py │ ├── test_modeling_kda.py │ ├── test_modeling_lightnet.py │ ├── test_modeling_linear_attn.py │ ├── test_modeling_log_linear_mamba2.py │ ├── test_modeling_mamba.py │ ├── test_modeling_mamba2.py │ ├── test_modeling_mesanet.py │ ├── test_modeling_mla.py │ ├── test_modeling_mom.py │ ├── test_modeling_nsa.py │ ├── test_modeling_path_attn.py │ ├── test_modeling_retnet.py │ ├── test_modeling_rodimus.py │ ├── test_modeling_rwkv6.py │ ├── test_modeling_rwkv7.py │ ├── test_modeling_samba.py │ ├── test_modeling_transformer.py │ └── test_modeling_utils.py ├── modules │ ├── test_activation.py │ ├── test_conv.py │ ├── test_cross_entropy.py │ ├── test_grpo.py │ ├── test_kl_div.py │ ├── test_l2norm.py │ ├── test_l2warp.py │ ├── test_layernorm.py │ ├── test_layernorm_gated.py │ ├── test_rotary.py │ └── test_token_shift.py └── ops │ ├── test_attn.py │ ├── test_based.py │ ├── test_comba.py │ ├── test_delta.py │ ├── test_delta_product.py │ ├── test_deltaformer.py │ ├── test_dplr_delta.py │ ├── test_forgetting_attn.py │ ├── test_gated_delta.py │ ├── test_gated_delta_product.py │ ├── test_gla.py │ ├── test_gsa.py │ ├── test_hgrn.py │ ├── test_iplr_delta.py │ ├── test_kda.py │ ├── test_linear_attn.py │ ├── test_log_linear_attn.py │ ├── test_mesa.py │ ├── test_nsa.py │ ├── test_path_attn.py │ ├── test_retention.py │ ├── test_rwkv6.py │ ├── test_rwkv7.py │ ├── test_simple_gla.py │ ├── test_solve_tril.py │ ├── test_titans.py │ ├── test_ttt.py │ └── test_utils.py └── utils ├── convert_from_llama.py ├── convert_from_rwkv6.py └── convert_from_rwkv7.py /.flake8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.flake8 -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/bug.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/ISSUE_TEMPLATE/bug.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/ISSUE_TEMPLATE/config.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature-request.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/ISSUE_TEMPLATE/feature-request.yml -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/rfc.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/ISSUE_TEMPLATE/rfc.yml -------------------------------------------------------------------------------- /.github/workflows/intel-b580.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/intel-b580.yml -------------------------------------------------------------------------------- /.github/workflows/issue.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/issue.yml -------------------------------------------------------------------------------- /.github/workflows/lint.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/lint.yaml -------------------------------------------------------------------------------- /.github/workflows/nvidia-4090.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/nvidia-4090.yml -------------------------------------------------------------------------------- /.github/workflows/nvidia-a100.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/nvidia-a100.yml -------------------------------------------------------------------------------- /.github/workflows/nvidia-h100.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/nvidia-h100.yml -------------------------------------------------------------------------------- /.github/workflows/pytorch-ci.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/pytorch-ci.yml -------------------------------------------------------------------------------- /.github/workflows/release.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/release.yml -------------------------------------------------------------------------------- /.github/workflows/reusable-build-triton.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/reusable-build-triton.yml -------------------------------------------------------------------------------- /.github/workflows/reusable-ci-tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/reusable-ci-tests.yml -------------------------------------------------------------------------------- /.github/workflows/triton-builder.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/triton-builder.yml -------------------------------------------------------------------------------- /.github/workflows/triton-nightly.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.github/workflows/triton-nightly.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.gitignore -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /CITATION.cff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/CITATION.cff -------------------------------------------------------------------------------- /ENVs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/ENVs.md -------------------------------------------------------------------------------- /FAQs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/FAQs.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/README.md -------------------------------------------------------------------------------- /benchmarks/benchmark_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/benchmark_generation.py -------------------------------------------------------------------------------- /benchmarks/benchmark_training_throughput.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/benchmark_training_throughput.py -------------------------------------------------------------------------------- /benchmarks/modules/benchmark_activations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/modules/benchmark_activations.py -------------------------------------------------------------------------------- /benchmarks/modules/benchmark_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/modules/benchmark_conv.py -------------------------------------------------------------------------------- /benchmarks/modules/benchmark_cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/modules/benchmark_cross_entropy.py -------------------------------------------------------------------------------- /benchmarks/modules/benchmark_l2norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/modules/benchmark_l2norm.py -------------------------------------------------------------------------------- /benchmarks/modules/benchmark_layernorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/modules/benchmark_layernorm.py -------------------------------------------------------------------------------- /benchmarks/modules/benchmark_tokenshift.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/modules/benchmark_tokenshift.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_abc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_abc.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_based.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_based.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_delta_rule.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_delta_rule.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_fla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_fla.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_gla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_gla.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_gsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_gsa.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_hgrn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_hgrn.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_kda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_kda.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_nsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_nsa.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_retention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_retention.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_rwkv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_rwkv.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_rwkv7_fused_addcmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_rwkv7_fused_addcmul.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_rwkv7_k_update.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_rwkv7_k_update.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_simple_gla_vs_mamba2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_simple_gla_vs_mamba2.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_solv_tril.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_solv_tril.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_titans.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_titans.py -------------------------------------------------------------------------------- /benchmarks/ops/benchmark_ttt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/benchmarks/ops/benchmark_ttt.py -------------------------------------------------------------------------------- /evals/harness.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/evals/harness.py -------------------------------------------------------------------------------- /evals/ppl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/evals/ppl.py -------------------------------------------------------------------------------- /examples/training.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/examples/training.md -------------------------------------------------------------------------------- /fla/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/__init__.py -------------------------------------------------------------------------------- /fla/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/__init__.py -------------------------------------------------------------------------------- /fla/layers/abc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/abc.py -------------------------------------------------------------------------------- /fla/layers/attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/attn.py -------------------------------------------------------------------------------- /fla/layers/based.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/based.py -------------------------------------------------------------------------------- /fla/layers/bitattn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/bitattn.py -------------------------------------------------------------------------------- /fla/layers/comba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/comba.py -------------------------------------------------------------------------------- /fla/layers/delta_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/delta_net.py -------------------------------------------------------------------------------- /fla/layers/deltaformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/deltaformer.py -------------------------------------------------------------------------------- /fla/layers/forgetting_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/forgetting_attn.py -------------------------------------------------------------------------------- /fla/layers/gated_deltanet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/gated_deltanet.py -------------------------------------------------------------------------------- /fla/layers/gated_deltaproduct.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/gated_deltaproduct.py -------------------------------------------------------------------------------- /fla/layers/gla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/gla.py -------------------------------------------------------------------------------- /fla/layers/gsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/gsa.py -------------------------------------------------------------------------------- /fla/layers/hgrn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/hgrn.py -------------------------------------------------------------------------------- /fla/layers/hgrn2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/hgrn2.py -------------------------------------------------------------------------------- /fla/layers/kda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/kda.py -------------------------------------------------------------------------------- /fla/layers/lightnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/lightnet.py -------------------------------------------------------------------------------- /fla/layers/linear_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/linear_attn.py -------------------------------------------------------------------------------- /fla/layers/log_linear_mamba2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/log_linear_mamba2.py -------------------------------------------------------------------------------- /fla/layers/mamba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/mamba.py -------------------------------------------------------------------------------- /fla/layers/mamba2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/mamba2.py -------------------------------------------------------------------------------- /fla/layers/mesa_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/mesa_net.py -------------------------------------------------------------------------------- /fla/layers/mla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/mla.py -------------------------------------------------------------------------------- /fla/layers/mom.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/mom.py -------------------------------------------------------------------------------- /fla/layers/multiscale_retention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/multiscale_retention.py -------------------------------------------------------------------------------- /fla/layers/nsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/nsa.py -------------------------------------------------------------------------------- /fla/layers/path_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/path_attn.py -------------------------------------------------------------------------------- /fla/layers/rebased.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/rebased.py -------------------------------------------------------------------------------- /fla/layers/rodimus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/rodimus.py -------------------------------------------------------------------------------- /fla/layers/rwkv6.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/rwkv6.py -------------------------------------------------------------------------------- /fla/layers/rwkv7.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/rwkv7.py -------------------------------------------------------------------------------- /fla/layers/simple_gla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/simple_gla.py -------------------------------------------------------------------------------- /fla/layers/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/layers/utils.py -------------------------------------------------------------------------------- /fla/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/__init__.py -------------------------------------------------------------------------------- /fla/models/abc/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/abc/__init__.py -------------------------------------------------------------------------------- /fla/models/abc/configuration_abc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/abc/configuration_abc.py -------------------------------------------------------------------------------- /fla/models/abc/modeling_abc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/abc/modeling_abc.py -------------------------------------------------------------------------------- /fla/models/bitnet/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/bitnet/__init__.py -------------------------------------------------------------------------------- /fla/models/bitnet/configuration_bitnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/bitnet/configuration_bitnet.py -------------------------------------------------------------------------------- /fla/models/bitnet/modeling_bitnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/bitnet/modeling_bitnet.py -------------------------------------------------------------------------------- /fla/models/comba/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/comba/__init__.py -------------------------------------------------------------------------------- /fla/models/comba/configuration_comba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/comba/configuration_comba.py -------------------------------------------------------------------------------- /fla/models/comba/modeling_comba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/comba/modeling_comba.py -------------------------------------------------------------------------------- /fla/models/delta_net/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/delta_net/__init__.py -------------------------------------------------------------------------------- /fla/models/delta_net/configuration_delta_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/delta_net/configuration_delta_net.py -------------------------------------------------------------------------------- /fla/models/delta_net/modeling_delta_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/delta_net/modeling_delta_net.py -------------------------------------------------------------------------------- /fla/models/deltaformer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/deltaformer/__init__.py -------------------------------------------------------------------------------- /fla/models/deltaformer/configuration_deltaformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/deltaformer/configuration_deltaformer.py -------------------------------------------------------------------------------- /fla/models/deltaformer/modeling_deltaformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/deltaformer/modeling_deltaformer.py -------------------------------------------------------------------------------- /fla/models/forgetting_transformer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/forgetting_transformer/__init__.py -------------------------------------------------------------------------------- /fla/models/forgetting_transformer/configuration_forgetting_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/forgetting_transformer/configuration_forgetting_transformer.py -------------------------------------------------------------------------------- /fla/models/forgetting_transformer/modeling_forgetting_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/forgetting_transformer/modeling_forgetting_transformer.py -------------------------------------------------------------------------------- /fla/models/gated_deltanet/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gated_deltanet/__init__.py -------------------------------------------------------------------------------- /fla/models/gated_deltanet/configuration_gated_deltanet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gated_deltanet/configuration_gated_deltanet.py -------------------------------------------------------------------------------- /fla/models/gated_deltanet/modeling_gated_deltanet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gated_deltanet/modeling_gated_deltanet.py -------------------------------------------------------------------------------- /fla/models/gated_deltaproduct/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gated_deltaproduct/__init__.py -------------------------------------------------------------------------------- /fla/models/gated_deltaproduct/configuration_gated_deltaproduct.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gated_deltaproduct/configuration_gated_deltaproduct.py -------------------------------------------------------------------------------- /fla/models/gated_deltaproduct/modeling_gated_deltaproduct.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gated_deltaproduct/modeling_gated_deltaproduct.py -------------------------------------------------------------------------------- /fla/models/gla/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gla/__init__.py -------------------------------------------------------------------------------- /fla/models/gla/configuration_gla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gla/configuration_gla.py -------------------------------------------------------------------------------- /fla/models/gla/modeling_gla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gla/modeling_gla.py -------------------------------------------------------------------------------- /fla/models/gsa/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gsa/__init__.py -------------------------------------------------------------------------------- /fla/models/gsa/configuration_gsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gsa/configuration_gsa.py -------------------------------------------------------------------------------- /fla/models/gsa/modeling_gsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/gsa/modeling_gsa.py -------------------------------------------------------------------------------- /fla/models/hgrn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/hgrn/__init__.py -------------------------------------------------------------------------------- /fla/models/hgrn/configuration_hgrn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/hgrn/configuration_hgrn.py -------------------------------------------------------------------------------- /fla/models/hgrn/modeling_hgrn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/hgrn/modeling_hgrn.py -------------------------------------------------------------------------------- /fla/models/hgrn2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/hgrn2/__init__.py -------------------------------------------------------------------------------- /fla/models/hgrn2/configuration_hgrn2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/hgrn2/configuration_hgrn2.py -------------------------------------------------------------------------------- /fla/models/hgrn2/modeling_hgrn2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/hgrn2/modeling_hgrn2.py -------------------------------------------------------------------------------- /fla/models/kda/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/kda/__init__.py -------------------------------------------------------------------------------- /fla/models/kda/configuration_kda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/kda/configuration_kda.py -------------------------------------------------------------------------------- /fla/models/kda/modeling_kda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/kda/modeling_kda.py -------------------------------------------------------------------------------- /fla/models/lightnet/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/lightnet/__init__.py -------------------------------------------------------------------------------- /fla/models/lightnet/configuration_lightnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/lightnet/configuration_lightnet.py -------------------------------------------------------------------------------- /fla/models/lightnet/modeling_lightnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/lightnet/modeling_lightnet.py -------------------------------------------------------------------------------- /fla/models/linear_attn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/linear_attn/__init__.py -------------------------------------------------------------------------------- /fla/models/linear_attn/configuration_linear_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/linear_attn/configuration_linear_attn.py -------------------------------------------------------------------------------- /fla/models/linear_attn/modeling_linear_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/linear_attn/modeling_linear_attn.py -------------------------------------------------------------------------------- /fla/models/log_linear_mamba2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/log_linear_mamba2/__init__.py -------------------------------------------------------------------------------- /fla/models/log_linear_mamba2/configuration_log_linear_mamba2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/log_linear_mamba2/configuration_log_linear_mamba2.py -------------------------------------------------------------------------------- /fla/models/log_linear_mamba2/modeling_log_linear_mamba2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/log_linear_mamba2/modeling_log_linear_mamba2.py -------------------------------------------------------------------------------- /fla/models/mamba/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mamba/__init__.py -------------------------------------------------------------------------------- /fla/models/mamba/configuration_mamba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mamba/configuration_mamba.py -------------------------------------------------------------------------------- /fla/models/mamba/modeling_mamba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mamba/modeling_mamba.py -------------------------------------------------------------------------------- /fla/models/mamba2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mamba2/__init__.py -------------------------------------------------------------------------------- /fla/models/mamba2/configuration_mamba2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mamba2/configuration_mamba2.py -------------------------------------------------------------------------------- /fla/models/mamba2/modeling_mamba2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mamba2/modeling_mamba2.py -------------------------------------------------------------------------------- /fla/models/mesa_net/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mesa_net/__init__.py -------------------------------------------------------------------------------- /fla/models/mesa_net/configuration_mesa_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mesa_net/configuration_mesa_net.py -------------------------------------------------------------------------------- /fla/models/mesa_net/modeling_mesa_net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mesa_net/modeling_mesa_net.py -------------------------------------------------------------------------------- /fla/models/mla/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mla/__init__.py -------------------------------------------------------------------------------- /fla/models/mla/configuration_mla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mla/configuration_mla.py -------------------------------------------------------------------------------- /fla/models/mla/modeling_mla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mla/modeling_mla.py -------------------------------------------------------------------------------- /fla/models/modeling_layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/modeling_layers.py -------------------------------------------------------------------------------- /fla/models/mom/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mom/__init__.py -------------------------------------------------------------------------------- /fla/models/mom/configuration_mom.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mom/configuration_mom.py -------------------------------------------------------------------------------- /fla/models/mom/modeling_mom.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/mom/modeling_mom.py -------------------------------------------------------------------------------- /fla/models/nsa/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/nsa/__init__.py -------------------------------------------------------------------------------- /fla/models/nsa/configuration_nsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/nsa/configuration_nsa.py -------------------------------------------------------------------------------- /fla/models/nsa/modeling_nsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/nsa/modeling_nsa.py -------------------------------------------------------------------------------- /fla/models/path_attn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/path_attn/__init__.py -------------------------------------------------------------------------------- /fla/models/path_attn/configuration_path_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/path_attn/configuration_path_attention.py -------------------------------------------------------------------------------- /fla/models/path_attn/modeling_path_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/path_attn/modeling_path_attention.py -------------------------------------------------------------------------------- /fla/models/retnet/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/retnet/__init__.py -------------------------------------------------------------------------------- /fla/models/retnet/configuration_retnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/retnet/configuration_retnet.py -------------------------------------------------------------------------------- /fla/models/retnet/modeling_retnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/retnet/modeling_retnet.py -------------------------------------------------------------------------------- /fla/models/rodimus/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/rodimus/__init__.py -------------------------------------------------------------------------------- /fla/models/rodimus/configuration_rodimus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/rodimus/configuration_rodimus.py -------------------------------------------------------------------------------- /fla/models/rodimus/modeling_rodimus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/rodimus/modeling_rodimus.py -------------------------------------------------------------------------------- /fla/models/rwkv6/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/rwkv6/__init__.py -------------------------------------------------------------------------------- /fla/models/rwkv6/configuration_rwkv6.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/rwkv6/configuration_rwkv6.py -------------------------------------------------------------------------------- /fla/models/rwkv6/modeling_rwkv6.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/rwkv6/modeling_rwkv6.py -------------------------------------------------------------------------------- /fla/models/rwkv7/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/rwkv7/__init__.py -------------------------------------------------------------------------------- /fla/models/rwkv7/configuration_rwkv7.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/rwkv7/configuration_rwkv7.py -------------------------------------------------------------------------------- /fla/models/rwkv7/modeling_rwkv7.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/rwkv7/modeling_rwkv7.py -------------------------------------------------------------------------------- /fla/models/samba/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/samba/__init__.py -------------------------------------------------------------------------------- /fla/models/samba/configuration_samba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/samba/configuration_samba.py -------------------------------------------------------------------------------- /fla/models/samba/modeling_samba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/samba/modeling_samba.py -------------------------------------------------------------------------------- /fla/models/transformer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/transformer/__init__.py -------------------------------------------------------------------------------- /fla/models/transformer/configuration_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/transformer/configuration_transformer.py -------------------------------------------------------------------------------- /fla/models/transformer/modeling_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/transformer/modeling_transformer.py -------------------------------------------------------------------------------- /fla/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/models/utils.py -------------------------------------------------------------------------------- /fla/modules/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/__init__.py -------------------------------------------------------------------------------- /fla/modules/activations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/activations.py -------------------------------------------------------------------------------- /fla/modules/convolution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/convolution.py -------------------------------------------------------------------------------- /fla/modules/feature_map.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/feature_map.py -------------------------------------------------------------------------------- /fla/modules/fused_bitlinear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/fused_bitlinear.py -------------------------------------------------------------------------------- /fla/modules/fused_cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/fused_cross_entropy.py -------------------------------------------------------------------------------- /fla/modules/fused_kl_div.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/fused_kl_div.py -------------------------------------------------------------------------------- /fla/modules/fused_linear_cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/fused_linear_cross_entropy.py -------------------------------------------------------------------------------- /fla/modules/fused_norm_gate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/fused_norm_gate.py -------------------------------------------------------------------------------- /fla/modules/grpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/grpo.py -------------------------------------------------------------------------------- /fla/modules/l2norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/l2norm.py -------------------------------------------------------------------------------- /fla/modules/l2warp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/l2warp.py -------------------------------------------------------------------------------- /fla/modules/layernorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/layernorm.py -------------------------------------------------------------------------------- /fla/modules/layernorm_gated.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/layernorm_gated.py -------------------------------------------------------------------------------- /fla/modules/mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/mlp.py -------------------------------------------------------------------------------- /fla/modules/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/parallel.py -------------------------------------------------------------------------------- /fla/modules/rotary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/rotary.py -------------------------------------------------------------------------------- /fla/modules/token_shift.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/modules/token_shift.py -------------------------------------------------------------------------------- /fla/ops/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/__init__.py -------------------------------------------------------------------------------- /fla/ops/abc/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/abc/__init__.py -------------------------------------------------------------------------------- /fla/ops/abc/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/abc/chunk.py -------------------------------------------------------------------------------- /fla/ops/abc/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/abc/naive.py -------------------------------------------------------------------------------- /fla/ops/attn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/attn/__init__.py -------------------------------------------------------------------------------- /fla/ops/attn/decoding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/attn/decoding.py -------------------------------------------------------------------------------- /fla/ops/attn/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/attn/parallel.py -------------------------------------------------------------------------------- /fla/ops/based/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/based/__init__.py -------------------------------------------------------------------------------- /fla/ops/based/fused_chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/based/fused_chunk.py -------------------------------------------------------------------------------- /fla/ops/based/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/based/naive.py -------------------------------------------------------------------------------- /fla/ops/based/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/based/parallel.py -------------------------------------------------------------------------------- /fla/ops/comba/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/comba/__init__.py -------------------------------------------------------------------------------- /fla/ops/comba/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/comba/chunk.py -------------------------------------------------------------------------------- /fla/ops/comba/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/comba/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/comba/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/comba/utils.py -------------------------------------------------------------------------------- /fla/ops/comba/wy_fast.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/comba/wy_fast.py -------------------------------------------------------------------------------- /fla/ops/common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /fla/ops/common/chunk_delta_h.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/common/chunk_delta_h.py -------------------------------------------------------------------------------- /fla/ops/common/chunk_h.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/common/chunk_h.py -------------------------------------------------------------------------------- /fla/ops/common/chunk_h_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/common/chunk_h_parallel.py -------------------------------------------------------------------------------- /fla/ops/common/chunk_h_split.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/common/chunk_h_split.py -------------------------------------------------------------------------------- /fla/ops/common/chunk_o.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/common/chunk_o.py -------------------------------------------------------------------------------- /fla/ops/common/chunk_scaled_dot_kkt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/common/chunk_scaled_dot_kkt.py -------------------------------------------------------------------------------- /fla/ops/common/fused_chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/common/fused_chunk.py -------------------------------------------------------------------------------- /fla/ops/common/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/common/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/delta_rule/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/delta_rule/README.md -------------------------------------------------------------------------------- /fla/ops/delta_rule/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/delta_rule/__init__.py -------------------------------------------------------------------------------- /fla/ops/delta_rule/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/delta_rule/chunk.py -------------------------------------------------------------------------------- /fla/ops/delta_rule/fused_chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/delta_rule/fused_chunk.py -------------------------------------------------------------------------------- /fla/ops/delta_rule/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/delta_rule/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/delta_rule/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/delta_rule/naive.py -------------------------------------------------------------------------------- /fla/ops/delta_rule/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/delta_rule/parallel.py -------------------------------------------------------------------------------- /fla/ops/delta_rule/wy_fast.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/delta_rule/wy_fast.py -------------------------------------------------------------------------------- /fla/ops/deltaformer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/deltaformer/__init__.py -------------------------------------------------------------------------------- /fla/ops/deltaformer/invcum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/deltaformer/invcum.py -------------------------------------------------------------------------------- /fla/ops/deltaformer/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/deltaformer/naive.py -------------------------------------------------------------------------------- /fla/ops/deltaformer/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/deltaformer/parallel.py -------------------------------------------------------------------------------- /fla/ops/forgetting_attn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/forgetting_attn/__init__.py -------------------------------------------------------------------------------- /fla/ops/forgetting_attn/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/forgetting_attn/parallel.py -------------------------------------------------------------------------------- /fla/ops/gated_delta_product/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gated_delta_product/__init__.py -------------------------------------------------------------------------------- /fla/ops/gated_delta_product/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gated_delta_product/chunk.py -------------------------------------------------------------------------------- /fla/ops/gated_delta_product/chunk_deltaproduct_h.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gated_delta_product/chunk_deltaproduct_h.py -------------------------------------------------------------------------------- /fla/ops/gated_delta_product/chunk_deltaproduct_o.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gated_delta_product/chunk_deltaproduct_o.py -------------------------------------------------------------------------------- /fla/ops/gated_delta_product/chunk_ref.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gated_delta_product/chunk_ref.py -------------------------------------------------------------------------------- /fla/ops/gated_delta_product/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gated_delta_product/naive.py -------------------------------------------------------------------------------- /fla/ops/gated_delta_rule/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gated_delta_rule/__init__.py -------------------------------------------------------------------------------- /fla/ops/gated_delta_rule/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gated_delta_rule/chunk.py -------------------------------------------------------------------------------- /fla/ops/gated_delta_rule/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gated_delta_rule/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/gated_delta_rule/wy_fast.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gated_delta_rule/wy_fast.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/README.md -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/__init__.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/__init__.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/chunk.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/chunk_A_bwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/chunk_A_bwd.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/chunk_A_fwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/chunk_A_fwd.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/chunk_h_bwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/chunk_h_bwd.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/chunk_h_fwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/chunk_h_fwd.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/chunk_o_bwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/chunk_o_bwd.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/chunk_o_fwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/chunk_o_fwd.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/naive.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/wy_fast_bwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/wy_fast_bwd.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/dplr/wy_fast_fwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/dplr/wy_fast_fwd.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/iplr/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/iplr/__init__.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/iplr/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/iplr/chunk.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/iplr/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/iplr/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/iplr/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/iplr/naive.py -------------------------------------------------------------------------------- /fla/ops/generalized_delta_rule/iplr/wy_fast.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/generalized_delta_rule/iplr/wy_fast.py -------------------------------------------------------------------------------- /fla/ops/gla/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gla/__init__.py -------------------------------------------------------------------------------- /fla/ops/gla/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gla/chunk.py -------------------------------------------------------------------------------- /fla/ops/gla/fused_chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gla/fused_chunk.py -------------------------------------------------------------------------------- /fla/ops/gla/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gla/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/gla/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gla/naive.py -------------------------------------------------------------------------------- /fla/ops/gsa/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gsa/__init__.py -------------------------------------------------------------------------------- /fla/ops/gsa/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gsa/chunk.py -------------------------------------------------------------------------------- /fla/ops/gsa/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gsa/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/gsa/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/gsa/naive.py -------------------------------------------------------------------------------- /fla/ops/hgrn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/hgrn/__init__.py -------------------------------------------------------------------------------- /fla/ops/hgrn/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/hgrn/chunk.py -------------------------------------------------------------------------------- /fla/ops/hgrn/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/hgrn/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/hgrn/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/hgrn/naive.py -------------------------------------------------------------------------------- /fla/ops/kda/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/kda/__init__.py -------------------------------------------------------------------------------- /fla/ops/kda/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/kda/chunk.py -------------------------------------------------------------------------------- /fla/ops/kda/chunk_inter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/kda/chunk_inter.py -------------------------------------------------------------------------------- /fla/ops/kda/chunk_intra.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/kda/chunk_intra.py -------------------------------------------------------------------------------- /fla/ops/kda/chunk_intra_token_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/kda/chunk_intra_token_parallel.py -------------------------------------------------------------------------------- /fla/ops/kda/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/kda/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/kda/gate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/kda/gate.py -------------------------------------------------------------------------------- /fla/ops/kda/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/kda/naive.py -------------------------------------------------------------------------------- /fla/ops/kda/wy_fast.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/kda/wy_fast.py -------------------------------------------------------------------------------- /fla/ops/lightning_attn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/lightning_attn/__init__.py -------------------------------------------------------------------------------- /fla/ops/lightning_attn/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/lightning_attn/chunk.py -------------------------------------------------------------------------------- /fla/ops/lightning_attn/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/lightning_attn/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/linear_attn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/linear_attn/__init__.py -------------------------------------------------------------------------------- /fla/ops/linear_attn/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/linear_attn/chunk.py -------------------------------------------------------------------------------- /fla/ops/linear_attn/fused_chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/linear_attn/fused_chunk.py -------------------------------------------------------------------------------- /fla/ops/linear_attn/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/linear_attn/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/linear_attn/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/linear_attn/naive.py -------------------------------------------------------------------------------- /fla/ops/linear_attn/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/linear_attn/utils.py -------------------------------------------------------------------------------- /fla/ops/log_linear_attn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/log_linear_attn/__init__.py -------------------------------------------------------------------------------- /fla/ops/log_linear_attn/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/log_linear_attn/chunk.py -------------------------------------------------------------------------------- /fla/ops/log_linear_attn/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/log_linear_attn/naive.py -------------------------------------------------------------------------------- /fla/ops/mesa_net/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/mesa_net/__init__.py -------------------------------------------------------------------------------- /fla/ops/mesa_net/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/mesa_net/chunk.py -------------------------------------------------------------------------------- /fla/ops/mesa_net/chunk_cg_solver_bwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/mesa_net/chunk_cg_solver_bwd.py -------------------------------------------------------------------------------- /fla/ops/mesa_net/chunk_cg_solver_fwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/mesa_net/chunk_cg_solver_fwd.py -------------------------------------------------------------------------------- /fla/ops/mesa_net/chunk_h_fwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/mesa_net/chunk_h_fwd.py -------------------------------------------------------------------------------- /fla/ops/mesa_net/chunk_h_kk_intra_bwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/mesa_net/chunk_h_kk_intra_bwd.py -------------------------------------------------------------------------------- /fla/ops/mesa_net/chunk_h_kv_intra_bwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/mesa_net/chunk_h_kv_intra_bwd.py -------------------------------------------------------------------------------- /fla/ops/mesa_net/chunk_h_kv_intra_bwd_separate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/mesa_net/chunk_h_kv_intra_bwd_separate.py -------------------------------------------------------------------------------- /fla/ops/mesa_net/decoding_one_step.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/mesa_net/decoding_one_step.py -------------------------------------------------------------------------------- /fla/ops/mesa_net/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/mesa_net/naive.py -------------------------------------------------------------------------------- /fla/ops/nsa/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/nsa/__init__.py -------------------------------------------------------------------------------- /fla/ops/nsa/compression.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/nsa/compression.py -------------------------------------------------------------------------------- /fla/ops/nsa/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/nsa/naive.py -------------------------------------------------------------------------------- /fla/ops/nsa/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/nsa/parallel.py -------------------------------------------------------------------------------- /fla/ops/nsa/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/nsa/utils.py -------------------------------------------------------------------------------- /fla/ops/path_attn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/__init__.py -------------------------------------------------------------------------------- /fla/ops/path_attn/cumprod_householder_bwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/cumprod_householder_bwd.py -------------------------------------------------------------------------------- /fla/ops/path_attn/cumprod_householder_fwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/cumprod_householder_fwd.py -------------------------------------------------------------------------------- /fla/ops/path_attn/intra_chunk_preprocess_bwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/intra_chunk_preprocess_bwd.py -------------------------------------------------------------------------------- /fla/ops/path_attn/intra_chunk_preprocess_bwd_prepare.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/intra_chunk_preprocess_bwd_prepare.py -------------------------------------------------------------------------------- /fla/ops/path_attn/intra_chunk_preprocess_fwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/intra_chunk_preprocess_fwd.py -------------------------------------------------------------------------------- /fla/ops/path_attn/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/parallel.py -------------------------------------------------------------------------------- /fla/ops/path_attn/parallel_path_bwd_inter_dkv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/parallel_path_bwd_inter_dkv.py -------------------------------------------------------------------------------- /fla/ops/path_attn/parallel_path_bwd_inter_dqh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/parallel_path_bwd_inter_dqh.py -------------------------------------------------------------------------------- /fla/ops/path_attn/parallel_path_bwd_intra.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/parallel_path_bwd_intra.py -------------------------------------------------------------------------------- /fla/ops/path_attn/parallel_path_fwd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/parallel_path_fwd.py -------------------------------------------------------------------------------- /fla/ops/path_attn/prepare_k_cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/prepare_k_cache.py -------------------------------------------------------------------------------- /fla/ops/path_attn/transform_q.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/path_attn/transform_q.py -------------------------------------------------------------------------------- /fla/ops/rebased/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rebased/__init__.py -------------------------------------------------------------------------------- /fla/ops/rebased/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rebased/naive.py -------------------------------------------------------------------------------- /fla/ops/rebased/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rebased/parallel.py -------------------------------------------------------------------------------- /fla/ops/retention/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/retention/__init__.py -------------------------------------------------------------------------------- /fla/ops/retention/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/retention/chunk.py -------------------------------------------------------------------------------- /fla/ops/retention/fused_chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/retention/fused_chunk.py -------------------------------------------------------------------------------- /fla/ops/retention/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/retention/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/retention/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/retention/naive.py -------------------------------------------------------------------------------- /fla/ops/retention/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/retention/parallel.py -------------------------------------------------------------------------------- /fla/ops/rwkv4/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv4/__init__.py -------------------------------------------------------------------------------- /fla/ops/rwkv4/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv4/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/rwkv6/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv6/__init__.py -------------------------------------------------------------------------------- /fla/ops/rwkv6/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv6/chunk.py -------------------------------------------------------------------------------- /fla/ops/rwkv6/chunk_naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv6/chunk_naive.py -------------------------------------------------------------------------------- /fla/ops/rwkv6/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv6/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/rwkv6/recurrent_naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv6/recurrent_naive.py -------------------------------------------------------------------------------- /fla/ops/rwkv7/RWKV7(Goose).md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv7/RWKV7(Goose).md -------------------------------------------------------------------------------- /fla/ops/rwkv7/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv7/__init__.py -------------------------------------------------------------------------------- /fla/ops/rwkv7/channel_mixing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv7/channel_mixing.py -------------------------------------------------------------------------------- /fla/ops/rwkv7/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv7/chunk.py -------------------------------------------------------------------------------- /fla/ops/rwkv7/fused_addcmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv7/fused_addcmul.py -------------------------------------------------------------------------------- /fla/ops/rwkv7/fused_k_update.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv7/fused_k_update.py -------------------------------------------------------------------------------- /fla/ops/rwkv7/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv7/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/rwkv7/gate_output_correction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/rwkv7/gate_output_correction.py -------------------------------------------------------------------------------- /fla/ops/simple_gla/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/simple_gla/README.md -------------------------------------------------------------------------------- /fla/ops/simple_gla/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/simple_gla/__init__.py -------------------------------------------------------------------------------- /fla/ops/simple_gla/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/simple_gla/chunk.py -------------------------------------------------------------------------------- /fla/ops/simple_gla/fused_chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/simple_gla/fused_chunk.py -------------------------------------------------------------------------------- /fla/ops/simple_gla/fused_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/simple_gla/fused_recurrent.py -------------------------------------------------------------------------------- /fla/ops/simple_gla/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/simple_gla/naive.py -------------------------------------------------------------------------------- /fla/ops/simple_gla/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/simple_gla/parallel.py -------------------------------------------------------------------------------- /fla/ops/titans/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/titans/__init__.py -------------------------------------------------------------------------------- /fla/ops/titans/log_impl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/titans/log_impl.py -------------------------------------------------------------------------------- /fla/ops/titans/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/titans/naive.py -------------------------------------------------------------------------------- /fla/ops/ttt/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/ttt/__init__.py -------------------------------------------------------------------------------- /fla/ops/ttt/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/ttt/chunk.py -------------------------------------------------------------------------------- /fla/ops/ttt/fused_chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/ttt/fused_chunk.py -------------------------------------------------------------------------------- /fla/ops/ttt/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/ttt/naive.py -------------------------------------------------------------------------------- /fla/ops/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/__init__.py -------------------------------------------------------------------------------- /fla/ops/utils/constant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/constant.py -------------------------------------------------------------------------------- /fla/ops/utils/cumsum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/cumsum.py -------------------------------------------------------------------------------- /fla/ops/utils/index.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/index.py -------------------------------------------------------------------------------- /fla/ops/utils/logcumsumexp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/logcumsumexp.py -------------------------------------------------------------------------------- /fla/ops/utils/logsumexp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/logsumexp.py -------------------------------------------------------------------------------- /fla/ops/utils/matmul.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/matmul.py -------------------------------------------------------------------------------- /fla/ops/utils/op.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/op.py -------------------------------------------------------------------------------- /fla/ops/utils/pack.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/pack.py -------------------------------------------------------------------------------- /fla/ops/utils/pooling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/pooling.py -------------------------------------------------------------------------------- /fla/ops/utils/softmax.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/softmax.py -------------------------------------------------------------------------------- /fla/ops/utils/softplus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/softplus.py -------------------------------------------------------------------------------- /fla/ops/utils/solve_tril.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/ops/utils/solve_tril.py -------------------------------------------------------------------------------- /fla/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/fla/utils.py -------------------------------------------------------------------------------- /legacy/training/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/legacy/training/README.md -------------------------------------------------------------------------------- /legacy/training/configs/gla_1B.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/legacy/training/configs/gla_1B.json -------------------------------------------------------------------------------- /legacy/training/configs/gla_340M.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/legacy/training/configs/gla_340M.json -------------------------------------------------------------------------------- /legacy/training/configs/gla_7B.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/legacy/training/configs/gla_7B.json -------------------------------------------------------------------------------- /legacy/training/configs/transformer_340M.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/legacy/training/configs/transformer_340M.json -------------------------------------------------------------------------------- /legacy/training/flame/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /legacy/training/flame/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/legacy/training/flame/data.py -------------------------------------------------------------------------------- /legacy/training/flame/logging.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/legacy/training/flame/logging.py -------------------------------------------------------------------------------- /legacy/training/flame/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/legacy/training/flame/parser.py -------------------------------------------------------------------------------- /legacy/training/preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/legacy/training/preprocess.py -------------------------------------------------------------------------------- /legacy/training/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/legacy/training/run.py -------------------------------------------------------------------------------- /legacy/training/train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/legacy/training/train.sh -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/pyproject.toml -------------------------------------------------------------------------------- /scripts/build_packages.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/scripts/build_packages.py -------------------------------------------------------------------------------- /scripts/check_gpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/scripts/check_gpu.py -------------------------------------------------------------------------------- /scripts/find_dependent_tests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/scripts/find_dependent_tests.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/setup.py -------------------------------------------------------------------------------- /tests/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/models/test_modeling_abc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_abc.py -------------------------------------------------------------------------------- /tests/models/test_modeling_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_base.py -------------------------------------------------------------------------------- /tests/models/test_modeling_bitnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_bitnet.py -------------------------------------------------------------------------------- /tests/models/test_modeling_comba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_comba.py -------------------------------------------------------------------------------- /tests/models/test_modeling_deltaformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_deltaformer.py -------------------------------------------------------------------------------- /tests/models/test_modeling_deltanet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_deltanet.py -------------------------------------------------------------------------------- /tests/models/test_modeling_forgetting_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_forgetting_transformer.py -------------------------------------------------------------------------------- /tests/models/test_modeling_gated_deltanet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_gated_deltanet.py -------------------------------------------------------------------------------- /tests/models/test_modeling_gated_deltaproduct.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_gated_deltaproduct.py -------------------------------------------------------------------------------- /tests/models/test_modeling_gla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_gla.py -------------------------------------------------------------------------------- /tests/models/test_modeling_gsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_gsa.py -------------------------------------------------------------------------------- /tests/models/test_modeling_hgrn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_hgrn.py -------------------------------------------------------------------------------- /tests/models/test_modeling_hgrn2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_hgrn2.py -------------------------------------------------------------------------------- /tests/models/test_modeling_kda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_kda.py -------------------------------------------------------------------------------- /tests/models/test_modeling_lightnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_lightnet.py -------------------------------------------------------------------------------- /tests/models/test_modeling_linear_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_linear_attn.py -------------------------------------------------------------------------------- /tests/models/test_modeling_log_linear_mamba2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_log_linear_mamba2.py -------------------------------------------------------------------------------- /tests/models/test_modeling_mamba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_mamba.py -------------------------------------------------------------------------------- /tests/models/test_modeling_mamba2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_mamba2.py -------------------------------------------------------------------------------- /tests/models/test_modeling_mesanet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_mesanet.py -------------------------------------------------------------------------------- /tests/models/test_modeling_mla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_mla.py -------------------------------------------------------------------------------- /tests/models/test_modeling_mom.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_mom.py -------------------------------------------------------------------------------- /tests/models/test_modeling_nsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_nsa.py -------------------------------------------------------------------------------- /tests/models/test_modeling_path_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_path_attn.py -------------------------------------------------------------------------------- /tests/models/test_modeling_retnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_retnet.py -------------------------------------------------------------------------------- /tests/models/test_modeling_rodimus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_rodimus.py -------------------------------------------------------------------------------- /tests/models/test_modeling_rwkv6.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_rwkv6.py -------------------------------------------------------------------------------- /tests/models/test_modeling_rwkv7.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_rwkv7.py -------------------------------------------------------------------------------- /tests/models/test_modeling_samba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_samba.py -------------------------------------------------------------------------------- /tests/models/test_modeling_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_transformer.py -------------------------------------------------------------------------------- /tests/models/test_modeling_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/models/test_modeling_utils.py -------------------------------------------------------------------------------- /tests/modules/test_activation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/modules/test_activation.py -------------------------------------------------------------------------------- /tests/modules/test_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/modules/test_conv.py -------------------------------------------------------------------------------- /tests/modules/test_cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/modules/test_cross_entropy.py -------------------------------------------------------------------------------- /tests/modules/test_grpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/modules/test_grpo.py -------------------------------------------------------------------------------- /tests/modules/test_kl_div.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/modules/test_kl_div.py -------------------------------------------------------------------------------- /tests/modules/test_l2norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/modules/test_l2norm.py -------------------------------------------------------------------------------- /tests/modules/test_l2warp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/modules/test_l2warp.py -------------------------------------------------------------------------------- /tests/modules/test_layernorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/modules/test_layernorm.py -------------------------------------------------------------------------------- /tests/modules/test_layernorm_gated.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/modules/test_layernorm_gated.py -------------------------------------------------------------------------------- /tests/modules/test_rotary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/modules/test_rotary.py -------------------------------------------------------------------------------- /tests/modules/test_token_shift.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/modules/test_token_shift.py -------------------------------------------------------------------------------- /tests/ops/test_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_attn.py -------------------------------------------------------------------------------- /tests/ops/test_based.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_based.py -------------------------------------------------------------------------------- /tests/ops/test_comba.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_comba.py -------------------------------------------------------------------------------- /tests/ops/test_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_delta.py -------------------------------------------------------------------------------- /tests/ops/test_delta_product.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_delta_product.py -------------------------------------------------------------------------------- /tests/ops/test_deltaformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_deltaformer.py -------------------------------------------------------------------------------- /tests/ops/test_dplr_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_dplr_delta.py -------------------------------------------------------------------------------- /tests/ops/test_forgetting_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_forgetting_attn.py -------------------------------------------------------------------------------- /tests/ops/test_gated_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_gated_delta.py -------------------------------------------------------------------------------- /tests/ops/test_gated_delta_product.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_gated_delta_product.py -------------------------------------------------------------------------------- /tests/ops/test_gla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_gla.py -------------------------------------------------------------------------------- /tests/ops/test_gsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_gsa.py -------------------------------------------------------------------------------- /tests/ops/test_hgrn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_hgrn.py -------------------------------------------------------------------------------- /tests/ops/test_iplr_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_iplr_delta.py -------------------------------------------------------------------------------- /tests/ops/test_kda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_kda.py -------------------------------------------------------------------------------- /tests/ops/test_linear_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_linear_attn.py -------------------------------------------------------------------------------- /tests/ops/test_log_linear_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_log_linear_attn.py -------------------------------------------------------------------------------- /tests/ops/test_mesa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_mesa.py -------------------------------------------------------------------------------- /tests/ops/test_nsa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_nsa.py -------------------------------------------------------------------------------- /tests/ops/test_path_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_path_attn.py -------------------------------------------------------------------------------- /tests/ops/test_retention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_retention.py -------------------------------------------------------------------------------- /tests/ops/test_rwkv6.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_rwkv6.py -------------------------------------------------------------------------------- /tests/ops/test_rwkv7.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_rwkv7.py -------------------------------------------------------------------------------- /tests/ops/test_simple_gla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_simple_gla.py -------------------------------------------------------------------------------- /tests/ops/test_solve_tril.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_solve_tril.py -------------------------------------------------------------------------------- /tests/ops/test_titans.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_titans.py -------------------------------------------------------------------------------- /tests/ops/test_ttt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_ttt.py -------------------------------------------------------------------------------- /tests/ops/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/tests/ops/test_utils.py -------------------------------------------------------------------------------- /utils/convert_from_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/utils/convert_from_llama.py -------------------------------------------------------------------------------- /utils/convert_from_rwkv6.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/utils/convert_from_rwkv6.py -------------------------------------------------------------------------------- /utils/convert_from_rwkv7.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/fla-org/flash-linear-attention/HEAD/utils/convert_from_rwkv7.py --------------------------------------------------------------------------------