.gitignore
LICENSE
MANIFEST.in
README.md
logo_dark.svg
logo_light.svg
pyproject.toml
requirements.txt
.github/workflows/workflow.yml
docs/custom_blocks.md
docs/darts.md
docs/fourier.md
docs/moe.md
docs/preprocessor.md
docs/transformer.md
docs/wavelets.md
docs/imgs/darts_module.svg
docs/imgs/darts_module_logo.svg
docs/imgs/foreblocks_inkscape_compatible.svg
docs/imgs/forecasting_model_diagram.svg
docs/imgs/fourier_blocks_diagram.svg
docs/imgs/moe_architecture_diagram.svg
docs/imgs/multi_attention_diagram.svg
docs/imgs/preprocessing_module.svg
docs/imgs/time_series_forecasting_concept.svg
docs/imgs/timeseriespreprocessor_logo.svg
docs/imgs/transformer_diagram_fixed.svg
examples/explainability.ipynb
examples/fourier_block.ipynb
examples/nha_block.ipynb
examples/other_blocks.ipynb
examples/pipeline.ipynb
examples/preprocessing.ipynb
examples/rodrigo.py
examples/rodrigo2.py
examples/seq2seq.ipynb
examples/times_block.ipynb
flash-attention/setup.py
flash-attention/benchmarks/benchmark_alibi.py
flash-attention/benchmarks/benchmark_causal.py
flash-attention/benchmarks/benchmark_flash_attention.py
flash-attention/benchmarks/benchmark_gemm.py
flash-attention/csrc/composable_kernel/docs/conf.py
flash-attention/csrc/composable_kernel/example/ck_tile/remod.py
flash-attention/csrc/composable_kernel/example/ck_tile/01_fmha/generate.py
flash-attention/csrc/composable_kernel/example/ck_tile/01_fmha/codegen/__init__.py
flash-attention/csrc/composable_kernel/example/ck_tile/01_fmha/codegen/cmake_config.py
flash-attention/csrc/composable_kernel/example/ck_tile/01_fmha/codegen/cpp_symbol_map.py
flash-attention/csrc/composable_kernel/example/ck_tile/01_fmha/codegen/ops/__init__.py
flash-attention/csrc/composable_kernel/example/ck_tile/01_fmha/codegen/ops/fmha_bwd.py
flash-attention/csrc/composable_kernel/example/ck_tile/01_fmha/codegen/ops/fmha_fwd.py
flash-attention/csrc/composable_kernel/example/ck_tile/01_fmha/codegen/ops/fmha_fwd_appendkv.py
flash-attention/csrc/composable_kernel/example/ck_tile/01_fmha/codegen/ops/fmha_fwd_splitkv.py
flash-attention/csrc/composable_kernel/example/ck_tile/02_layernorm2d/generate.py
flash-attention/csrc/composable_kernel/example/ck_tile/10_rmsnorm2d/generate.py
flash-attention/csrc/composable_kernel/include/ck_tile/remod.py
flash-attention/csrc/composable_kernel/python/ck4inductor/__init__.py
flash-attention/csrc/composable_kernel/python/ck4inductor/util.py
flash-attention/csrc/composable_kernel/python/ck4inductor/batched_universal_gemm/gen_instances.py
flash-attention/csrc/composable_kernel/python/ck4inductor/batched_universal_gemm/op.py
flash-attention/csrc/composable_kernel/python/ck4inductor/grouped_conv_fwd/gen_instances.py
flash-attention/csrc/composable_kernel/python/ck4inductor/grouped_conv_fwd/op.py
flash-attention/csrc/composable_kernel/python/ck4inductor/universal_gemm/gen_instances.py
flash-attention/csrc/composable_kernel/python/ck4inductor/universal_gemm/op.py
flash-attention/csrc/composable_kernel/python/test/test_gen_instances.py
flash-attention/csrc/composable_kernel/script/convert_miopen_driver_to_profiler.py
flash-attention/csrc/composable_kernel/script/process_perf_data.py
flash-attention/csrc/composable_kernel/tile_engine/ops/gemm/gemm_instance_builder.py
flash-attention/csrc/cutlass/examples/40_cutlass_py/conv2d.py
flash-attention/csrc/cutlass/examples/40_cutlass_py/gemm.py
flash-attention/csrc/cutlass/examples/40_cutlass_py/gemm_grouped.py
flash-attention/csrc/cutlass/examples/40_cutlass_py/customizable/conv2d.py
flash-attention/csrc/cutlass/examples/40_cutlass_py/customizable/gemm.py
flash-attention/csrc/cutlass/examples/40_cutlass_py/customizable/gemm_grouped.py
flash-attention/csrc/cutlass/examples/41_fused_multi_head_attention/fmha_backward_test.py
flash-attention/csrc/cutlass/examples/41_fused_multi_head_attention/piped_subprocess.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_all_code.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_cmake.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_customized_epilogue.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_device.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_ir.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_kernel.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_sample.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_threadblock.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_turing_and_volta.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_verify.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/helper.py
flash-attention/csrc/cutlass/examples/44_multi_gemm_ir_and_codegen/ir_gen/replace_fix_impl_header.py
flash-attention/csrc/cutlass/python/setup_cutlass.py
flash-attention/csrc/cutlass/python/setup_library.py
flash-attention/csrc/cutlass/python/setup_pycute.py
flash-attention/csrc/cutlass/python/cutlass/__init__.py
flash-attention/csrc/cutlass/python/cutlass/library_defaults.py
flash-attention/csrc/cutlass/python/cutlass/shape.py
flash-attention/csrc/cutlass/python/cutlass/swizzle.py
flash-attention/csrc/cutlass/python/cutlass/backend/__init__.py
flash-attention/csrc/cutlass/python/cutlass/backend/arguments.py
flash-attention/csrc/cutlass/python/cutlass/backend/c_types.py
flash-attention/csrc/cutlass/python/cutlass/backend/compiler.py
flash-attention/csrc/cutlass/python/cutlass/backend/conv2d_operation.py
flash-attention/csrc/cutlass/python/cutlass/backend/epilogue.py
flash-attention/csrc/cutlass/python/cutlass/backend/frontend.py
flash-attention/csrc/cutlass/python/cutlass/backend/gemm_operation.py
flash-attention/csrc/cutlass/python/cutlass/backend/library.py
flash-attention/csrc/cutlass/python/cutlass/backend/memory_manager.py
flash-attention/csrc/cutlass/python/cutlass/backend/operation.py
flash-attention/csrc/cutlass/python/cutlass/backend/reduction_operation.py
flash-attention/csrc/cutlass/python/cutlass/backend/type_hint.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/__init__.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/epilogue.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/backend/__init__.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/backend/emitter_base.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/backend/sm80_emitter.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/backend/sm80_nodes.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/backend/sm90_emitter.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/backend/sm90_nodes.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/frontend/__init__.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/frontend/frontend_base.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/frontend/python_ast.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/ir/__init__.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/ir/compute_nodes.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/ir/dag_ir.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/ir/layout_algorithm.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/ir/layout_nodes.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/ir/load_nodes.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/ir/node.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/ir/store_nodes.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/ir/tensor.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/__init__.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/graph_drawer.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/pass_argument_type.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/pass_dag_2_tree.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/pass_fix_element_d.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/pass_get_impl.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/pass_layout_elimination.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/pass_manager.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/pass_no_op_elimination.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/pass_preprocess_red.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/pass_shape_type_propagation.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/smem_size_calculator.py
flash-attention/csrc/cutlass/python/cutlass/backend/evt/passes/util.py
flash-attention/csrc/cutlass/python/cutlass/backend/utils/__init__.py
flash-attention/csrc/cutlass/python/cutlass/backend/utils/device.py
flash-attention/csrc/cutlass/python/cutlass/emit/__init__.py
flash-attention/csrc/cutlass/python/cutlass/emit/common.py
flash-attention/csrc/cutlass/python/cutlass/emit/pytorch.py
flash-attention/csrc/cutlass/python/cutlass/epilogue/__init__.py
flash-attention/csrc/cutlass/python/cutlass/epilogue/epilogue.py
flash-attention/csrc/cutlass/python/cutlass/epilogue/evt_ops.py
flash-attention/csrc/cutlass/python/cutlass/op/__init__.py
flash-attention/csrc/cutlass/python/cutlass/op/conv.py
flash-attention/csrc/cutlass/python/cutlass/op/gemm.py
flash-attention/csrc/cutlass/python/cutlass/op/gemm_grouped.py
flash-attention/csrc/cutlass/python/cutlass/op/op.py
flash-attention/csrc/cutlass/python/cutlass/utils/__init__.py
flash-attention/csrc/cutlass/python/cutlass/utils/check.py
flash-attention/csrc/cutlass/python/cutlass/utils/datatypes.py
flash-attention/csrc/cutlass/python/cutlass/utils/profiler.py
flash-attention/csrc/cutlass/python/cutlass_library/__init__.py
flash-attention/csrc/cutlass/python/cutlass_library/conv2d_operation.py
flash-attention/csrc/cutlass/python/cutlass_library/conv3d_operation.py
flash-attention/csrc/cutlass/python/cutlass_library/conv3x_emitter.py
flash-attention/csrc/cutlass/python/cutlass_library/emit_kernel_listing.py
flash-attention/csrc/cutlass/python/cutlass_library/gemm_operation.py
flash-attention/csrc/cutlass/python/cutlass_library/generator.py
flash-attention/csrc/cutlass/python/cutlass_library/library.py
flash-attention/csrc/cutlass/python/cutlass_library/manifest.py
flash-attention/csrc/cutlass/python/cutlass_library/rank_2k_operation.py
flash-attention/csrc/cutlass/python/cutlass_library/rank_k_operation.py
flash-attention/csrc/cutlass/python/cutlass_library/sm90_shapes.py
flash-attention/csrc/cutlass/python/cutlass_library/sm90_utils.py
flash-attention/csrc/cutlass/python/cutlass_library/symm_operation.py
flash-attention/csrc/cutlass/python/cutlass_library/trmm_operation.py
flash-attention/csrc/cutlass/python/docs_src/source/conf.py
flash-attention/csrc/cutlass/python/pycute/__init__.py
flash-attention/csrc/cutlass/python/pycute/int_tuple.py
flash-attention/csrc/cutlass/python/pycute/layout.py
flash-attention/csrc/cutlass/python/pycute/swizzle.py
flash-attention/csrc/cutlass/python/pycute/typing.py
flash-attention/csrc/cutlass/test/python/cutlass/installation.py
flash-attention/csrc/cutlass/test/python/cutlass/conv2d/conv2d_problem_sizes.py
flash-attention/csrc/cutlass/test/python/cutlass/conv2d/conv2d_sm80.py
flash-attention/csrc/cutlass/test/python/cutlass/conv2d/conv2d_test_utils.py
flash-attention/csrc/cutlass/test/python/cutlass/conv2d/run_all_tests.py
flash-attention/csrc/cutlass/test/python/cutlass/emit/pytorch.py
flash-attention/csrc/cutlass/test/python/cutlass/evt/evt_compute_sm80_90.py
flash-attention/csrc/cutlass/test/python/cutlass/evt/evt_layout_sm80_90.py
flash-attention/csrc/cutlass/test/python/cutlass/evt/evt_load_sm80_90.py
flash-attention/csrc/cutlass/test/python/cutlass/evt/evt_mixed_sm80_90.py
flash-attention/csrc/cutlass/test/python/cutlass/evt/evt_store_sm80_90.py
flash-attention/csrc/cutlass/test/python/cutlass/evt/run_all_tests.py
flash-attention/csrc/cutlass/test/python/cutlass/evt/utils/evt_testbed.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/gemm_batched.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/gemm_f16_sm80.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/gemm_f16_sm90.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/gemm_f32_sm80.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/gemm_f64_sm80.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/gemm_f64_sm90.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/gemm_f8_sm90.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/gemm_mixed_sm80.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/gemm_s8_sm80.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/gemm_s8_sm90.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/gemm_testbed.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/run_all_tests.py
flash-attention/csrc/cutlass/test/python/cutlass/gemm/utils.py
flash-attention/csrc/cutlass/test/python/cutlass/interface/conv2d_interface.py
flash-attention/csrc/cutlass/test/python/cutlass/interface/evt_interface.py
flash-attention/csrc/cutlass/test/python/cutlass/interface/gemm_interface.py
flash-attention/csrc/cutlass/test/python/cutlass/interface/utils.py
flash-attention/csrc/cutlass/test/python/pycute/run_all_tests.py
flash-attention/csrc/cutlass/test/python/pycute/test_coalesce.py
flash-attention/csrc/cutlass/test/python/pycute/test_complement.py
flash-attention/csrc/cutlass/test/python/pycute/test_composition.py
flash-attention/csrc/cutlass/test/python/pycute/test_int_tuple.py
flash-attention/csrc/cutlass/test/python/pycute/test_left_inverse.py
flash-attention/csrc/cutlass/test/python/pycute/test_right_inverse.py
flash-attention/csrc/cutlass/test/python/pycute/test_typing.py
flash-attention/csrc/cutlass/test/unit/gemm/device/simt_sm50.py
flash-attention/csrc/flash_attn/src/generate_kernels.py
flash-attention/csrc/ft_attention/setup.py
flash-attention/csrc/fused_dense_lib/setup.py
flash-attention/csrc/fused_softmax/setup.py
flash-attention/csrc/layer_norm/setup.py
flash-attention/csrc/rotary/setup.py
flash-attention/csrc/xentropy/setup.py
flash-attention/flash_attn/__init__.py
flash-attention/flash_attn/bert_padding.py
flash-attention/flash_attn/flash_attn_interface.py
flash-attention/flash_attn/flash_attn_triton.py
flash-attention/flash_attn/flash_attn_triton_og.py
flash-attention/flash_attn/flash_blocksparse_attention.py
flash-attention/flash_attn/flash_blocksparse_attn_interface.py
flash-attention/flash_attn/fused_softmax.py
flash-attention/flash_attn/flash_attn_triton_amd/__init__.py
flash-attention/flash_attn/flash_attn_triton_amd/bench.py
flash-attention/flash_attn/flash_attn_triton_amd/bwd_prefill.py
flash-attention/flash_attn/flash_attn_triton_amd/bwd_prefill_fused.py
flash-attention/flash_attn/flash_attn_triton_amd/bwd_prefill_onekernel.py
flash-attention/flash_attn/flash_attn_triton_amd/bwd_prefill_split.py
flash-attention/flash_attn/flash_attn_triton_amd/bwd_ref.py
flash-attention/flash_attn/flash_attn_triton_amd/fp8.py
flash-attention/flash_attn/flash_attn_triton_amd/fwd_decode.py
flash-attention/flash_attn/flash_attn_triton_amd/fwd_prefill.py
flash-attention/flash_attn/flash_attn_triton_amd/fwd_ref.py
flash-attention/flash_attn/flash_attn_triton_amd/interface_fa.py
flash-attention/flash_attn/flash_attn_triton_amd/test.py
flash-attention/flash_attn/flash_attn_triton_amd/train.py
flash-attention/flash_attn/flash_attn_triton_amd/utils.py
flash-attention/flash_attn/layers/__init__.py
flash-attention/flash_attn/layers/patch_embed.py
flash-attention/flash_attn/layers/rotary.py
flash-attention/flash_attn/losses/__init__.py
flash-attention/flash_attn/losses/cross_entropy.py
flash-attention/flash_attn/models/__init__.py
flash-attention/flash_attn/models/baichuan.py
flash-attention/flash_attn/models/bert.py
flash-attention/flash_attn/models/bigcode.py
flash-attention/flash_attn/models/btlm.py
flash-attention/flash_attn/models/falcon.py
flash-attention/flash_attn/models/gpt.py
flash-attention/flash_attn/models/gpt_neox.py
flash-attention/flash_attn/models/gptj.py
flash-attention/flash_attn/models/llama.py
flash-attention/flash_attn/models/opt.py
flash-attention/flash_attn/models/vit.py
flash-attention/flash_attn/modules/__init__.py
flash-attention/flash_attn/modules/block.py
flash-attention/flash_attn/modules/embedding.py
flash-attention/flash_attn/modules/mha.py
flash-attention/flash_attn/modules/mlp.py
flash-attention/flash_attn/ops/__init__.py
flash-attention/flash_attn/ops/activations.py
flash-attention/flash_attn/ops/fused_dense.py
flash-attention/flash_attn/ops/layer_norm.py
flash-attention/flash_attn/ops/rms_norm.py
flash-attention/flash_attn/ops/triton/__init__.py
flash-attention/flash_attn/ops/triton/cross_entropy.py
flash-attention/flash_attn/ops/triton/k_activations.py
flash-attention/flash_attn/ops/triton/layer_norm.py
flash-attention/flash_attn/ops/triton/linear.py
flash-attention/flash_attn/ops/triton/mlp.py
flash-attention/flash_attn/ops/triton/rotary.py
flash-attention/flash_attn/utils/__init__.py
flash-attention/flash_attn/utils/benchmark.py
flash-attention/flash_attn/utils/distributed.py
flash-attention/flash_attn/utils/generation.py
flash-attention/flash_attn/utils/library.py
flash-attention/flash_attn/utils/pretrained.py
flash-attention/flash_attn/utils/torch.py
flash-attention/hopper/__init__.py
flash-attention/hopper/benchmark_attn.py
flash-attention/hopper/benchmark_flash_attention_fp8.py
flash-attention/hopper/benchmark_mla_decode.py
flash-attention/hopper/benchmark_split_kv.py
flash-attention/hopper/flash_attn_interface.py
flash-attention/hopper/generate_kernels.py
flash-attention/hopper/padding.py
flash-attention/hopper/setup.py
flash-attention/hopper/test_attn_kvcache.py
flash-attention/hopper/test_flash_attn.py
flash-attention/hopper/test_kvcache.py
flash-attention/hopper/test_util.py
flash-attention/tests/test_flash_attn.py
flash-attention/tests/test_flash_attn_ck.py
flash-attention/tests/test_flash_attn_triton_amd.py
flash-attention/tests/test_rotary.py
flash-attention/tests/test_util.py
flash-attention/tests/layers/test_rotary.py
flash-attention/tests/losses/test_cross_entropy.py
flash-attention/tests/losses/test_cross_entropy_parallel.py
flash-attention/tests/models/test_baichuan.py
flash-attention/tests/models/test_bert.py
flash-attention/tests/models/test_bigcode.py
flash-attention/tests/models/test_btlm.py
flash-attention/tests/models/test_falcon.py
flash-attention/tests/models/test_gpt.py
flash-attention/tests/models/test_gpt_generation_parallel.py
flash-attention/tests/models/test_gpt_neox.py
flash-attention/tests/models/test_gpt_parallel.py
flash-attention/tests/models/test_gptj.py
flash-attention/tests/models/test_llama.py
flash-attention/tests/models/test_opt.py
flash-attention/tests/models/test_vit.py
flash-attention/tests/modules/test_block_parallel.py
flash-attention/tests/modules/test_embedding_parallel.py
flash-attention/tests/modules/test_mha_parallel.py
flash-attention/tests/modules/test_mlp_parallel.py
flash-attention/tests/ops/test_dropout_layer_norm.py
flash-attention/tests/ops/test_fused_dense.py
flash-attention/tests/ops/test_fused_dense_parallel.py
flash-attention/tests/ops/triton/test_layer_norm.py
flash-attention/training/run.py
flash-attention/training/src/eval.py
flash-attention/training/src/train.py
flash-attention/training/src/callbacks/__init__.py
flash-attention/training/src/callbacks/causality_monitor.py
flash-attention/training/src/callbacks/ema.py
flash-attention/training/src/callbacks/flop_count.py
flash-attention/training/src/callbacks/gpu_affinity.py
flash-attention/training/src/callbacks/loss_scale_monitor.py
flash-attention/training/src/callbacks/model_checkpoint.py
flash-attention/training/src/callbacks/norm_monitor.py
flash-attention/training/src/callbacks/params_log.py
flash-attention/training/src/callbacks/speed_monitor.py
flash-attention/training/src/callbacks/wandb_callbacks.py
flash-attention/training/src/datamodules/fault_tolerant_sampler.py
flash-attention/training/src/datamodules/imagenet.py
flash-attention/training/src/datamodules/language_modeling_hf.py
flash-attention/training/src/datamodules/timm_mixup.py
flash-attention/training/src/datamodules/datasets/detokenizer.py
flash-attention/training/src/datamodules/datasets/lm_dataset.py
flash-attention/training/src/distributed/ddp_comm_hooks.py
flash-attention/training/src/metrics/accuracy.py
flash-attention/training/src/metrics/num_tokens.py
flash-attention/training/src/metrics/perplexity.py
flash-attention/training/src/models/modules/seq_common.py
flash-attention/training/src/optim/param_grouping.py
flash-attention/training/src/optim/timm_lr_scheduler.py
flash-attention/training/src/tasks/seq.py
flash-attention/training/src/utils/checkpoint.py
flash-attention/training/src/utils/ddp_zero1.py
flash-attention/training/src/utils/ddp_zero2.py
flash-attention/training/src/utils/distributed.py
flash-attention/training/src/utils/ema.py
flash-attention/training/src/utils/flops.py
flash-attention/training/src/utils/gpu_affinity.py
flash-attention/training/src/utils/utils.py
flash-attention/training/tests/datamodules/test_language_modeling_hf.py
foreblocks/__init__.py
foreblocks/att.py
foreblocks/aux.py
foreblocks/core.py
foreblocks/enc_dec.py
foreblocks/fengine.py
foreblocks/pipeline.py
foreblocks/preprocessing.py
foreblocks/quantization.py
foreblocks/utils.py
foreblocks.egg-info/PKG-INFO
foreblocks.egg-info/SOURCES.txt
foreblocks.egg-info/dependency_links.txt
foreblocks.egg-info/requires.txt
foreblocks.egg-info/top_level.txt
foreblocks/blocks/__init__.py
foreblocks/blocks/attention.py
foreblocks/blocks/famous.py
foreblocks/blocks/fourier.py
foreblocks/blocks/graph.py
foreblocks/blocks/mamba.py
foreblocks/blocks/multiscale.py
foreblocks/blocks/nha.py
foreblocks/blocks/ode.py
foreblocks/blocks/simple.py
foreblocks/blocks/wavelets.py
foreblocks/darts/__init__.py
foreblocks/darts/darts.py
foreblocks/darts/darts_base.py
foreblocks/darts/darts_metrics.py
foreblocks/darts/darts_plot.py
foreblocks/darts/darts_run.py
foreblocks/pre/__init__.py
foreblocks/pre/ewt.py
foreblocks/pre/filters.py
foreblocks/pre/impute.py
foreblocks/pre/outlier.py
foreblocks/tf/embeddings.py
foreblocks/tf/fed.py
foreblocks/tf/transformer.py
foreblocks/tf/transformer_att.py
foreblocks/tf/transformer_aux.py
foreblocks/tf/transformer_moe.py
foreblocks/third_party/flash_softpick_attn.py
foreblocks/third_party/vsgd.py
foreblocks/tuner/foretuner.py
foreblocks/tuner/foretuner_aux.py
foreblocks/tuner/foretuner_plot.py
foretools/fenginner.py
foretools/vmd.py
mamba/setup.py
mamba/benchmarks/benchmark_generation_mamba_simple.py
mamba/evals/lm_harness_eval.py
mamba/mamba_ssm/__init__.py
mamba/mamba_ssm/distributed/__init__.py
mamba/mamba_ssm/distributed/distributed_utils.py
mamba/mamba_ssm/distributed/tensor_parallel.py
mamba/mamba_ssm/models/__init__.py
mamba/mamba_ssm/models/config_mamba.py
mamba/mamba_ssm/models/mixer_seq_simple.py
mamba/mamba_ssm/modules/__init__.py
mamba/mamba_ssm/modules/block.py
mamba/mamba_ssm/modules/mamba2.py
mamba/mamba_ssm/modules/mamba2_simple.py
mamba/mamba_ssm/modules/mamba_simple.py
mamba/mamba_ssm/modules/mha.py
mamba/mamba_ssm/modules/mlp.py
mamba/mamba_ssm/modules/ssd_minimal.py
mamba/mamba_ssm/ops/__init__.py
mamba/mamba_ssm/ops/selective_scan_interface.py
mamba/mamba_ssm/ops/triton/__init__.py
mamba/mamba_ssm/ops/triton/k_activations.py
mamba/mamba_ssm/ops/triton/layer_norm.py
mamba/mamba_ssm/ops/triton/layernorm_gated.py
mamba/mamba_ssm/ops/triton/selective_state_update.py
mamba/mamba_ssm/ops/triton/softplus.py
mamba/mamba_ssm/ops/triton/ssd_bmm.py
mamba/mamba_ssm/ops/triton/ssd_chunk_scan.py
mamba/mamba_ssm/ops/triton/ssd_chunk_state.py
mamba/mamba_ssm/ops/triton/ssd_combined.py
mamba/mamba_ssm/ops/triton/ssd_state_passing.py
mamba/mamba_ssm/utils/__init__.py
mamba/mamba_ssm/utils/generation.py
mamba/mamba_ssm/utils/hf.py
mamba/mamba_ssm/utils/torch.py
mamba/tests/test_generation.py
mamba/tests/ops/test_selective_scan.py
mamba/tests/ops/triton/test_layernorm_gated.py
mamba/tests/ops/triton/test_selective_state_update.py
mamba/tests/ops/triton/test_ssd.py
work/elm.py
work/emd.py
work/nanosatellite_env.py
work/turbo_m.py
work/vmd.py
work/vmd_aux.py