CHANGELOG.md
CITATION.cff
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
MANIFEST.in
README.md
ROADMAP.md
SECURITY.md
pyproject.toml
pytest.ini
requirements.lock.txt
requirements.txt
neuralops/README.md
neuralops/__init__.py
neuralops/__main__.py
neuralops/_lazy.py
neuralops/_lazy_family.py
neuralops/_optional.py
neuralops/api.py
neuralops/architectures.py
neuralops/checkpoint.py
neuralops/fastapi_app.py
neuralops/hub.py
neuralops/lora.py
neuralops/main.py
neuralops/py.typed
neuralops/qwen_compat.py
neuralops/recipes.py
neuralops/registry.py
neuralops/replace_attention.py
neuralops/server.py
neuralops/serving.py
neuralops/transformers.py
neuralops.egg-info/PKG-INFO
neuralops.egg-info/SOURCES.txt
neuralops.egg-info/dependency_links.txt
neuralops.egg-info/entry_points.txt
neuralops.egg-info/requires.txt
neuralops.egg-info/top_level.txt
neuralops/adaptation/__init__.py
neuralops/adaptation/distillation/__init__.py
neuralops/adaptation/peft/__init__.py
neuralops/adapters/__init__.py
neuralops/adapters/base.py
neuralops/adapters/distilbert.py
neuralops/adapters/errors.py
neuralops/adapters/generic.py
neuralops/adapters/gpt2.py
neuralops/adapters/llama.py
neuralops/adapters/registry.py
neuralops/analysis/__init__.py
neuralops/analysis/flops_utils.py
neuralops/analysis/generate_all_modules_analysis.py
neuralops/analysis/generate_sweep_publication_artifacts.py
neuralops/analysis/inspector.py
neuralops/analysis/layerwise_analyzer.py
neuralops/analysis/metrics.py
neuralops/analysis/model_comparison.py
neuralops/analysis/paper_export.py
neuralops/analysis/paper_plots.py
neuralops/analysis/pareto_sweeper.py
neuralops/analysis/plotting.py
neuralops/analysis/report_generator.py
neuralops/analysis/results_ledger.py
neuralops/analysis/roofline.py
neuralops/analysis/utils.py
neuralops/analysis/comparison/__init__.py
neuralops/analysis/comparison/statistical_testing.py
neuralops/analysis/module_analysis/__init__.py
neuralops/analysis/module_analysis/aggregators.py
neuralops/analysis/module_analysis/constants.py
neuralops/analysis/module_analysis/main.py
neuralops/analysis/module_analysis/parsers.py
neuralops/analysis/module_analysis/reporters.py
neuralops/attentions/README.md
neuralops/attentions/__init__.py
neuralops/attentions/base.py
neuralops/attentions/adaptive/__init__.py
neuralops/attentions/adaptive/adaptive_span_attention.py
neuralops/attentions/adaptive/block_transformer_hiba.py
neuralops/attentions/adaptive/eat.py
neuralops/attentions/adaptive/infini_attention.py
neuralops/attentions/adaptive/lola_attention.py
neuralops/attentions/adaptive/progressive_token_pruning.py
neuralops/attentions/adaptive/sink_attention.py
neuralops/attentions/adaptive/span_expanded_attention.py
neuralops/attentions/adaptive/squeezing_heads_distill.py
neuralops/attentions/adaptive/token_compressed_attention.py
neuralops/attentions/dense/__init__.py
neuralops/attentions/dense/full_attention.py
neuralops/attentions/dense/zeros_attention.py
neuralops/attentions/experimental/__init__.py
neuralops/attentions/experimental/template_attention.py
neuralops/attentions/fast_kernels/__init__.py
neuralops/attentions/fast_kernels/adasplash_attention.py
neuralops/attentions/fast_kernels/flash_attention3.py
neuralops/attentions/fast_kernels/flash_attention3_fp8.py
neuralops/attentions/fast_kernels/soa_attn.py
neuralops/attentions/fast_kernels/xattention.py
neuralops/attentions/gated/__init__.py
neuralops/attentions/gated/decay_linear_attention.py
neuralops/attentions/gated/flagship_fla.py
neuralops/attentions/gated/gated_delta_net.py
neuralops/attentions/gated/gated_deltanet_block.py
neuralops/attentions/gated/hgrn2_gated_deltanet.py
neuralops/attentions/gated/hgrn2_gated_layer.py
neuralops/attentions/gated/hgrn2_gated_outer.py
neuralops/attentions/gated/hla_attention.py
neuralops/attentions/gated/kda_attention.py
neuralops/attentions/hybrid/__init__.py
neuralops/attentions/hybrid/fusion_attn.py
neuralops/attentions/hybrid/gated_hybrid_kernel_attention.py
neuralops/attentions/hybrid/granite_hybrid.py
neuralops/attentions/hybrid/halo_regla.py
neuralops/attentions/hybrid/hybrid_attention.py
neuralops/attentions/hybrid/hybrid_local_kernel_attention.py
neuralops/attentions/hybrid/landmark_local_attention.py
neuralops/attentions/hybrid/mixattention_moska.py
neuralops/attentions/hybrid/optimized_hybrid_attention.py
neuralops/attentions/hybrid/positive_kernel_linear_attention.py
neuralops/attentions/hybrid/refined_landmark_attention.py
neuralops/attentions/hybrid/regla_attention.py
neuralops/attentions/hybrid/spectron_fp8_attention.py
neuralops/attentions/hybrid/split_head_hybrid_attention.py
neuralops/attentions/hybrid/tri_branch_hybrid_attention.py
neuralops/attentions/linear/__init__.py
neuralops/attentions/linear/chela_slay.py
neuralops/attentions/linear/cosformer.py
neuralops/attentions/linear/galerkin_attention.py
neuralops/attentions/linear/gla_attention.py
neuralops/attentions/linear/linformer_attention.py
neuralops/attentions/linear/nasc_attention.py
neuralops/attentions/linear/nystrom_attention.py
neuralops/attentions/linear/performer_attention.py
neuralops/attentions/linear/primal_attention.py
neuralops/attentions/linear/rala_attention.py
neuralops/attentions/linear/rpc_attention.py
neuralops/attentions/linear/spectra_v2.py
neuralops/attentions/linear/spectraformer_attention.py
neuralops/attentions/linear/spectron.py
neuralops/attentions/linear/tlinformer_attention.py
neuralops/attentions/linear/tpa_attention.py
neuralops/attentions/linear/triton_cosformer.py
neuralops/attentions/modern/__init__.py
neuralops/attentions/modern/alibi.py
neuralops/attentions/modern/cross_attention.py
neuralops/attentions/modern/dynamic_conv_attention.py
neuralops/attentions/modern/gqa_attention.py
neuralops/attentions/modern/mla_attention.py
neuralops/attentions/modern/mqa.py
neuralops/attentions/modern/nha_attention.py
neuralops/attentions/modern/qcqa_attention.py
neuralops/attentions/modern/unified_rope.py
neuralops/attentions/modern/vig_attention.py
neuralops/attentions/modern/wgqa_attention.py
neuralops/attentions/sparse/__init__.py
neuralops/attentions/sparse/adaptive_sparse_attention.py
neuralops/attentions/sparse/bam_umoe.py
neuralops/attentions/sparse/cluster_attention.py
neuralops/attentions/sparse/expert_choice_moe.py
neuralops/attentions/sparse/hamming_attention.py
neuralops/attentions/sparse/lsh_attention.py
neuralops/attentions/sparse/moba_attention.py
neuralops/attentions/sparse/moe_deltakv_paged.py
neuralops/attentions/sparse/nsa_attention.py
neuralops/attentions/sparse/padre_attention.py
neuralops/attentions/sparse/reap_moe.py
neuralops/attentions/sparse/reap_moe_router.py
neuralops/attentions/sparse/routing_attention.py
neuralops/attentions/ssm/__init__.py
neuralops/attentions/ssm/goldfinch_ahn.py
neuralops/attentions/ssm/griffin_ssd.py
neuralops/attentions/ssm/hymba_transx.py
neuralops/attentions/ssm/jamba.py
neuralops/attentions/ssm/jamba_info.py
neuralops/attentions/ssm/mamba_block.py
neuralops/attentions/ssm/mamba_svd_flash.py
neuralops/attentions/ssm/nexus.py
neuralops/attentions/ssm/orion.py
neuralops/attentions/ssm/phantom.py
neuralops/attentions/ssm/samba_m3.py
neuralops/attentions/ssm/samba_moe.py
neuralops/attentions/ssm/selective_ssm.py
neuralops/attentions/ssm/simple_ssm.py
neuralops/attentions/ssm/spectral_mamba.py
neuralops/attentions/ssm/upi_stuffed_mamba.py
neuralops/attentions/ssm/vspec.py
neuralops/attentions/svd/__init__.py
neuralops/attentions/svd/adaptive_svd_attention.py
neuralops/attentions/svd/asvd_attention.py
neuralops/attentions/svd/compressed_attention.py
neuralops/attentions/svd/compressed_mha_attention.py
neuralops/attentions/svd/factorised_matrix_state.py
neuralops/attentions/svd/fused_svd_kernel.py
neuralops/attentions/svd/lora_attention.py
neuralops/attentions/svd/minimal_nova.py
neuralops/attentions/svd/minimal_svd.py
neuralops/attentions/svd/naive_svd.py
neuralops/attentions/svd/projection_factorized_attn.py
neuralops/attentions/svd/residual_svd_attention.py
neuralops/attentions/svd/salt_attention.py
neuralops/attentions/svd/svd_attention.py
neuralops/attentions/svd/svd_compressed.py
neuralops/attentions/svd/svd_linear_attention.py
neuralops/attentions/svd/svd_linear_decay.py
neuralops/attentions/svd/svd_llm_v2_attention.py
neuralops/attentions/svd/svd_mamba.py
neuralops/attentions/svd/svd_projection_attention.py
neuralops/attentions/svd/triton_svd_linear_attention.py
neuralops/backward_compat/__init__.py
neuralops/backward_compat/attentions.py
neuralops/backward_compat/compression_engine.py
neuralops/backward_compat/cuda_kernels.py
neuralops/backward_compat/triton_kernels.py
neuralops/benchmarks/README.md
neuralops/benchmarks/discovery_overrides.json
neuralops/benchmarks/static_catalog.json
neuralops/cli/README.md
neuralops/cli/__init__.py
neuralops/cli/bench_cmd.py
neuralops/cli/compress_cmd.py
neuralops/cli/doctor.py
neuralops/cli/eval_cmd.py
neuralops/cli/info.py
neuralops/cli/list_cmd.py
neuralops/cli/serve_cmd.py
neuralops/cli/surgery_cli.py
neuralops/cli/surgery_cmd.py
neuralops/cli/terminal_ui.py
neuralops/cli/test_cmd.py
neuralops/cli/train_cmd.py
neuralops/compression/__init__.py
neuralops/compression/aa_svd_compressor.py
neuralops/compression/astro_quantizer.py
neuralops/compression/base.py
neuralops/compression/experimental/__init__.py
neuralops/compression/experimental/flat_llm.py
neuralops/compression/experimental/hashed_net_compressor.py
neuralops/compression/experimental/liftr.py
neuralops/compression/experimental/lillama_compressor.py
neuralops/compression/experimental/roast_hashed_linear.py
neuralops/compression/kv_cache/__init__.py
neuralops/compression/kv_cache/aatc_xkv_compressor.py
neuralops/compression/kv_cache/cachenotes_compressor.py
neuralops/compression/kv_cache/delta_kv.py
neuralops/compression/kv_cache/hybridkv_compressor.py
neuralops/compression/kv_cache/kvtc_compressor.py
neuralops/compression/kv_cache/zerokv_neo_compressor.py
neuralops/compression/low_rank/__init__.py
neuralops/compression/low_rank/a3_compressor.py
neuralops/compression/low_rank/come_compressor.py
neuralops/compression/low_rank/compot_compressor.py
neuralops/compression/low_rank/cr_compressor.py
neuralops/compression/low_rank/cur_compressor.py
neuralops/compression/low_rank/cur_moe_compressor.py
neuralops/compression/low_rank/dora_qlora.py
neuralops/compression/low_rank/drone_compressor.py
neuralops/compression/low_rank/enlighten_compressor.py
neuralops/compression/low_rank/frandi_compressor.py
neuralops/compression/low_rank/grecodec_compressor.py
neuralops/compression/low_rank/lsc_compressor.py
neuralops/compression/low_rank/mgie_svd_compressor.py
neuralops/compression/low_rank/mlorq_compressor.py
neuralops/compression/low_rank/modegpt_compressor.py
neuralops/compression/low_rank/nmf_compressor.py
neuralops/compression/low_rank/oats_compressor.py
neuralops/compression/low_rank/rpca_compressor.py
neuralops/compression/low_rank/salr.py
neuralops/compression/low_rank/sdrm_compressor.py
neuralops/compression/low_rank/slim_compressor.py
neuralops/compression/low_rank/soka_compressor.py
neuralops/compression/low_rank/svd_llm_compressor.py
neuralops/compression/low_rank/tomoe_compressor.py
neuralops/compression/low_rank/uniql_compressor.py
neuralops/compression/pruning/__init__.py
neuralops/compression/pruning/admm_compressor.py
neuralops/compression/pruning/admm_pruner.py
neuralops/compression/pruning/armor_pruner.py
neuralops/compression/pruning/ast_pruner.py
neuralops/compression/pruning/bonsai_pruner.py
neuralops/compression/pruning/flap.py
neuralops/compression/pruning/mamba_shedder.py
neuralops/compression/pruning/proxsparse.py
neuralops/compression/pruning/sparsegpt.py
neuralops/compression/pruning/wanda.py
neuralops/compression/quantization/__init__.py
neuralops/compression/quantization/astro_quantizer.py
neuralops/compression/quantization/awq.py
neuralops/compression/quantization/awq_real.py
neuralops/compression/quantization/coopq_quantizer.py
neuralops/compression/quantization/faq_quantizer.py
neuralops/compression/quantization/fp8_compressor.py
neuralops/compression/quantization/gptq.py
neuralops/compression/quantization/gptq_real.py
neuralops/compression/quantization/huffman_coder.py
neuralops/compression/quantization/kmeans_quantize.py
neuralops/compression/quantization/quarot.py
neuralops/compression/quantization/rotational_slicegpt_int4.py
neuralops/compression/quantization/slicegpt.py
neuralops/compression/quantization/slicegpt_pca.py
neuralops/compression/quantization/smoothquant.py
neuralops/compression/quantization/smoothquant_real.py
neuralops/compression/svd/__init__.py
neuralops/compression/svd/aa_svd_compressor.py
neuralops/compression/svd/adaptive_ranks.py
neuralops/compression/svd/adasvd_compressor.py
neuralops/compression/svd/asvd_compressor.py
neuralops/compression/svd/auto_svd.py
neuralops/compression/svd/direct_svd.py
neuralops/compression/svd/dobi_svd.py
neuralops/compression/svd/dynamic_rank.py
neuralops/compression/svd/entropy_budget_allocation.py
neuralops/compression/svd/erc_svd.py
neuralops/compression/svd/fwsvd_compressor.py
neuralops/compression/svd/gfws_d_compressor.py
neuralops/compression/svd/hadamard_incoherent_svd.py
neuralops/compression/svd/hnc_svd_continuation.py
neuralops/compression/svd/hybrid_svd_layer.py
neuralops/compression/svd/optimal_subspace_projection.py
neuralops/compression/svd/residual_svd_compressor.py
neuralops/compression/svd/saes_svd_v2.py
neuralops/compression/svd/subspace_projection.py
neuralops/compression/svd/svd_linear.py
neuralops/compression/svd/swift_svd.py
neuralops/compression/svd/swift_svd_act.py
neuralops/compression/tensor_decomp/__init__.py
neuralops/compression/tensor_decomp/kronecker_compressor.py
neuralops/compression/tensor_decomp/kronecker_tt_lora.py
neuralops/compression/tensor_decomp/tt_compressor.py
neuralops/compression_engine/README.md
neuralops/compression_engine/__init__.py
neuralops/compression_engine/base.py
neuralops/compression_engine/experimental/__init__.py
neuralops/compression_engine/experimental/flat_llm.py
neuralops/compression_engine/experimental/hashed_net_compressor.py
neuralops/compression_engine/experimental/liftr.py
neuralops/compression_engine/experimental/lillama_compressor.py
neuralops/compression_engine/experimental/roast_hashed_linear.py
neuralops/compression_engine/kv_cache/__init__.py
neuralops/compression_engine/kv_cache/aatc_xkv_compressor.py
neuralops/compression_engine/kv_cache/cachenotes_compressor.py
neuralops/compression_engine/kv_cache/delta_kv.py
neuralops/compression_engine/kv_cache/hybridkv_compressor.py
neuralops/compression_engine/kv_cache/kvtc_compressor.py
neuralops/compression_engine/kv_cache/zerokv_neo_compressor.py
neuralops/compression_engine/low_rank/__init__.py
neuralops/compression_engine/low_rank/a3_compressor.py
neuralops/compression_engine/low_rank/come_compressor.py
neuralops/compression_engine/low_rank/compot_compressor.py
neuralops/compression_engine/low_rank/cr_compressor.py
neuralops/compression_engine/low_rank/cur_compressor.py
neuralops/compression_engine/low_rank/cur_moe_compressor.py
neuralops/compression_engine/low_rank/dora_qlora.py
neuralops/compression_engine/low_rank/drone_compressor.py
neuralops/compression_engine/low_rank/enlighten_compressor.py
neuralops/compression_engine/low_rank/frandi_compressor.py
neuralops/compression_engine/low_rank/grecodec_compressor.py
neuralops/compression_engine/low_rank/lsc_compressor.py
neuralops/compression_engine/low_rank/mgie_svd_compressor.py
neuralops/compression_engine/low_rank/mlorq_compressor.py
neuralops/compression_engine/low_rank/modegpt_compressor.py
neuralops/compression_engine/low_rank/nmf_compressor.py
neuralops/compression_engine/low_rank/oats_compressor.py
neuralops/compression_engine/low_rank/rpca_compressor.py
neuralops/compression_engine/low_rank/salr.py
neuralops/compression_engine/low_rank/sdrm_compressor.py
neuralops/compression_engine/low_rank/slim_compressor.py
neuralops/compression_engine/low_rank/soka_compressor.py
neuralops/compression_engine/low_rank/svd_llm_compressor.py
neuralops/compression_engine/low_rank/tomoe_compressor.py
neuralops/compression_engine/low_rank/uniql_compressor.py
neuralops/compression_engine/pruning/__init__.py
neuralops/compression_engine/pruning/admm_compressor.py
neuralops/compression_engine/pruning/admm_pruner.py
neuralops/compression_engine/pruning/armor_pruner.py
neuralops/compression_engine/pruning/ast_pruner.py
neuralops/compression_engine/pruning/bonsai_pruner.py
neuralops/compression_engine/pruning/flap.py
neuralops/compression_engine/pruning/mamba_shedder.py
neuralops/compression_engine/pruning/proxsparse.py
neuralops/compression_engine/pruning/sparsegpt.py
neuralops/compression_engine/pruning/wanda.py
neuralops/compression_engine/quantization/__init__.py
neuralops/compression_engine/quantization/astro_quantizer.py
neuralops/compression_engine/quantization/awq.py
neuralops/compression_engine/quantization/awq_real.py
neuralops/compression_engine/quantization/coopq_quantizer.py
neuralops/compression_engine/quantization/faq_quantizer.py
neuralops/compression_engine/quantization/fp8_compressor.py
neuralops/compression_engine/quantization/gptq.py
neuralops/compression_engine/quantization/gptq_real.py
neuralops/compression_engine/quantization/huffman_coder.py
neuralops/compression_engine/quantization/kmeans_quantize.py
neuralops/compression_engine/quantization/quarot.py
neuralops/compression_engine/quantization/rotational_slicegpt_int4.py
neuralops/compression_engine/quantization/slicegpt.py
neuralops/compression_engine/quantization/slicegpt_pca.py
neuralops/compression_engine/quantization/smoothquant.py
neuralops/compression_engine/quantization/smoothquant_real.py
neuralops/compression_engine/svd/__init__.py
neuralops/compression_engine/svd/aa_svd_compressor.py
neuralops/compression_engine/svd/adaptive_ranks.py
neuralops/compression_engine/svd/adasvd_compressor.py
neuralops/compression_engine/svd/asvd_compressor.py
neuralops/compression_engine/svd/auto_svd.py
neuralops/compression_engine/svd/direct_svd.py
neuralops/compression_engine/svd/dobi_svd.py
neuralops/compression_engine/svd/dynamic_rank.py
neuralops/compression_engine/svd/entropy_budget_allocation.py
neuralops/compression_engine/svd/erc_svd.py
neuralops/compression_engine/svd/fwsvd_compressor.py
neuralops/compression_engine/svd/gfws_d_compressor.py
neuralops/compression_engine/svd/hadamard_incoherent_svd.py
neuralops/compression_engine/svd/hnc_svd_continuation.py
neuralops/compression_engine/svd/hybrid_svd_layer.py
neuralops/compression_engine/svd/optimal_subspace_projection.py
neuralops/compression_engine/svd/residual_svd_compressor.py
neuralops/compression_engine/svd/saes_svd_v2.py
neuralops/compression_engine/svd/subspace_projection.py
neuralops/compression_engine/svd/svd_linear.py
neuralops/compression_engine/svd/swift_svd.py
neuralops/compression_engine/svd/swift_svd_act.py
neuralops/compression_engine/tensor_decomp/__init__.py
neuralops/compression_engine/tensor_decomp/kronecker_compressor.py
neuralops/compression_engine/tensor_decomp/kronecker_tt_lora.py
neuralops/compression_engine/tensor_decomp/tt_compressor.py
neuralops/config/README.md
neuralops/config/__init__.py
neuralops/config/compression_config.py
neuralops/config/config.py
neuralops/config/data_config.py
neuralops/config/experiment_config.py
neuralops/config/hardware_config.py
neuralops/config/loader.py
neuralops/config/method_config.py
neuralops/config/model_config.py
neuralops/config/sweep_config.py
neuralops/config/training_config.py
neuralops/core/__init__.py
neuralops/core/_attention_extractors.py
neuralops/core/_attention_helpers.py
neuralops/core/_attention_injectors.py
neuralops/core/_attention_surgery.py
neuralops/core/_attention_wrapper.py
neuralops/core/_lazy.py
neuralops/core/_post_init.py
neuralops/core/adapters.py
neuralops/core/amp_utils.py
neuralops/core/architecture.py
neuralops/core/attention_mask.py
neuralops/core/attention_surgery.py
neuralops/core/attention_utils.py
neuralops/core/base.py
neuralops/core/cache_utils.py
neuralops/core/common.py
neuralops/core/composable.py
neuralops/core/compression_engine.py
neuralops/core/compression_pipeline.py
neuralops/core/config.py
neuralops/core/cuda_graph.py
neuralops/core/deprecated_aliases.json
neuralops/core/device.py
neuralops/core/diagnostics.py
neuralops/core/errors.py
neuralops/core/exceptions.py
neuralops/core/extensibility.py
neuralops/core/fused_norm_attention.py
neuralops/core/gqa_utils.py
neuralops/core/hardware.py
neuralops/core/hardware_profile.py
neuralops/core/inspector.py
neuralops/core/lazy_import.py
neuralops/core/legacy_aliases.py
neuralops/core/mask_utils.py
neuralops/core/memory.py
neuralops/core/metrics.py
neuralops/core/model_family.py
neuralops/core/model_utils.py
neuralops/core/model_wrapper.py
neuralops/core/multi_mode_benchmark.py
neuralops/core/op_registry.py
neuralops/core/paper_export.py
neuralops/core/pruning_utils.py
neuralops/core/quantized_attention.py
neuralops/core/registry.py
neuralops/core/replace_attention.py
neuralops/core/results_ledger.py
neuralops/core/roofline.py
neuralops/core/rope.py
neuralops/core/run_long_context_sweep.py
neuralops/core/selective_scan.py
neuralops/core/snapshot_restore.py
neuralops/core/state_cache.py
neuralops/core/svd_utils.py
neuralops/core/t5_compat.py
neuralops/core/triton_linear_attn.py
neuralops/core/triton_sparse_attn.py
neuralops/core/utils.py
neuralops/core/autograd/__init__.py
neuralops/core/autograd/flash_attention.py
neuralops/core/autograd/fused_backward.py
neuralops/core/backend/__init__.py
neuralops/core/backend/dispatch.py
neuralops/core/cuda_kernels/README.md
neuralops/core/cuda_kernels/__init__.py
neuralops/core/cuda_kernels/_attention_autograd_builder.py
neuralops/core/cuda_kernels/_bindings.py
neuralops/core/cuda_kernels/_common.cuh
neuralops/core/cuda_kernels/_fallback.py
neuralops/core/cuda_kernels/_map.py
neuralops/core/cuda_kernels/_types.py
neuralops/core/cuda_kernels/_utils.py
neuralops/core/cuda_kernels/fallback.py
neuralops/core/cuda_kernels/act_scale_gemm/__init__.py
neuralops/core/cuda_kernels/adaptive_span/__init__.py
neuralops/core/cuda_kernels/aegis_gate_norm/__init__.py
neuralops/core/cuda_kernels/alibi_attention/__init__.py
neuralops/core/cuda_kernels/bigbird/__init__.py
neuralops/core/cuda_kernels/bitonic_topk/__init__.py
neuralops/core/cuda_kernels/block_diag_gemm/__init__.py
neuralops/core/cuda_kernels/causal_conv1d/__init__.py
neuralops/core/cuda_kernels/channel_shuffle/__init__.py
neuralops/core/cuda_kernels/cluster_attention/__init__.py
neuralops/core/cuda_kernels/cosformer/__init__.py
neuralops/core/cuda_kernels/cross_attention/__init__.py
neuralops/core/cuda_kernels/decay_linear_attention/__init__.py
neuralops/core/cuda_kernels/differential_attention/__init__.py
neuralops/core/cuda_kernels/dynamic_conv1d/__init__.py
neuralops/core/cuda_kernels/entmax_bisect/__init__.py
neuralops/core/cuda_kernels/entropy_gate/__init__.py
neuralops/core/cuda_kernels/entropy_pruning/__init__.py
neuralops/core/cuda_kernels/fast_attention/__init__.py
neuralops/core/cuda_kernels/fast_gelu/__init__.py
neuralops/core/cuda_kernels/favor_plus/__init__.py
neuralops/core/cuda_kernels/flash_decode_stage2/__init__.py
neuralops/core/cuda_kernels/flash_decoding/__init__.py
neuralops/core/cuda_kernels/flash_gqa/__init__.py
neuralops/core/cuda_kernels/fms_scan/__init__.py
neuralops/core/cuda_kernels/fp4_gemm/__init__.py
neuralops/core/cuda_kernels/fp8_gemm/__init__.py
neuralops/core/cuda_kernels/fused_ce/__init__.py
neuralops/core/cuda_kernels/fused_dropout_add/__init__.py
neuralops/core/cuda_kernels/fused_kd/__init__.py
neuralops/core/cuda_kernels/fused_norm_linear/__init__.py
neuralops/core/cuda_kernels/fused_rope/__init__.py
neuralops/core/cuda_kernels/fwht_transform/__init__.py
neuralops/core/cuda_kernels/galerkin_attention/__init__.py
neuralops/core/cuda_kernels/gdn_delta_rule/__init__.py
neuralops/core/cuda_kernels/gdn_scan/__init__.py
neuralops/core/cuda_kernels/gla_scan/__init__.py
neuralops/core/cuda_kernels/gla_unnormalized_scan/__init__.py
neuralops/core/cuda_kernels/goldfinch_ahn/__init__.py
neuralops/core/cuda_kernels/griffin_ssd/__init__.py
neuralops/core/cuda_kernels/hadamard_gemm/__init__.py
neuralops/core/cuda_kernels/hgrn2_scan/__init__.py
neuralops/core/cuda_kernels/hgrn2_spatial_scan/__init__.py
neuralops/core/cuda_kernels/hla_attention/__init__.py
neuralops/core/cuda_kernels/hstu_attention/__init__.py
neuralops/core/cuda_kernels/hybrid_local_kernel/__init__.py
neuralops/core/cuda_kernels/hydra_attention/__init__.py
neuralops/core/cuda_kernels/hymba_transx/__init__.py
neuralops/core/cuda_kernels/jamba/__init__.py
neuralops/core/cuda_kernels/jamba_info/__init__.py
neuralops/core/cuda_kernels/kronecker_gemm/__init__.py
neuralops/core/cuda_kernels/latent_kv_attn/__init__.py
neuralops/core/cuda_kernels/layernorm/__init__.py
neuralops/core/cuda_kernels/linear_attention/__init__.py
neuralops/core/cuda_kernels/linear_rnn_attention/__init__.py
neuralops/core/cuda_kernels/linformer_attention/__init__.py
neuralops/core/cuda_kernels/liquid_attention/__init__.py
neuralops/core/cuda_kernels/local_attention/__init__.py
neuralops/core/cuda_kernels/logcumsumexp/__init__.py
neuralops/core/cuda_kernels/longformer/__init__.py
neuralops/core/cuda_kernels/low_rank_svd/__init__.py
neuralops/core/cuda_kernels/lut_gemm/__init__.py
neuralops/core/cuda_kernels/mamba2_block/__init__.py
neuralops/core/cuda_kernels/mamba_block/__init__.py
neuralops/core/cuda_kernels/mamba_svd_flash/__init__.py
neuralops/core/cuda_kernels/moe_routing/__init__.py
neuralops/core/cuda_kernels/multi_scale_retention/__init__.py
neuralops/core/cuda_kernels/nasc_attention/__init__.py
neuralops/core/cuda_kernels/nexus/__init__.py
neuralops/core/cuda_kernels/nystrom_attention/__init__.py
neuralops/core/cuda_kernels/orion/__init__.py
neuralops/core/cuda_kernels/paged_attention/__init__.py
neuralops/core/cuda_kernels/paged_kv_cache/__init__.py
neuralops/core/cuda_kernels/paged_kv_evict/__init__.py
neuralops/core/cuda_kernels/paged_recurrent_step/__init__.py
neuralops/core/cuda_kernels/phantom/__init__.py
neuralops/core/cuda_kernels/quantized_gemm/__init__.py
neuralops/core/cuda_kernels/recurrent_gla_step/__init__.py
neuralops/core/cuda_kernels/recurrent_hgrn2_step/__init__.py
neuralops/core/cuda_kernels/reformer/__init__.py
neuralops/core/cuda_kernels/rfa_attention/__init__.py
neuralops/core/cuda_kernels/rms_variance_match/__init__.py
neuralops/core/cuda_kernels/rmsnorm/__init__.py
neuralops/core/cuda_kernels/rotational_svd/__init__.py
neuralops/core/cuda_kernels/routing_attention/__init__.py
neuralops/core/cuda_kernels/rpca_sparse_svd/__init__.py
neuralops/core/cuda_kernels/rwkv6/__init__.py
neuralops/core/cuda_kernels/samba_m3/__init__.py
neuralops/core/cuda_kernels/samba_moe/__init__.py
neuralops/core/cuda_kernels/selective_scan/__init__.py
neuralops/core/cuda_kernels/selective_ssm/__init__.py
neuralops/core/cuda_kernels/simple_ssm/__init__.py
neuralops/core/cuda_kernels/sliding_window/__init__.py
neuralops/core/cuda_kernels/soa_attn/__init__.py
neuralops/core/cuda_kernels/softplus/__init__.py
neuralops/core/cuda_kernels/sparse_attention/__init__.py
neuralops/core/cuda_kernels/spectra_v2/__init__.py
neuralops/core/cuda_kernels/spectraformer_attention/__init__.py
neuralops/core/cuda_kernels/spectral_mamba/__init__.py
neuralops/core/cuda_kernels/spectral_shrinkage/__init__.py
neuralops/core/cuda_kernels/speculative_verify/__init__.py
neuralops/core/cuda_kernels/split_head_norm/__init__.py
neuralops/core/cuda_kernels/state_update/__init__.py
neuralops/core/cuda_kernels/svd_prefix_scan/__init__.py
neuralops/core/cuda_kernels/swiglu/__init__.py
neuralops/core/cuda_kernels/ternary_gemm/__init__.py
neuralops/core/cuda_kernels/tpa_attention/__init__.py
neuralops/core/cuda_kernels/tt_contraction/__init__.py
neuralops/core/cuda_kernels/unified_rope_offset/__init__.py
neuralops/core/cuda_kernels/upi_stuffed_mamba/__init__.py
neuralops/core/cuda_kernels/varlen_attention/__init__.py
neuralops/core/cuda_kernels/vspec/__init__.py
neuralops/core/fused/__init__.py
neuralops/core/fused/fused_ce.py
neuralops/core/fused/fused_kd.py
neuralops/core/fused/fused_norm_linear.py
neuralops/core/low_rank/__init__.py
neuralops/core/low_rank/factorized.py
neuralops/core/low_rank/svd_linear.py
neuralops/core/peft/__init__.py
neuralops/core/peft/lora.py
neuralops/core/triton_kernels/__init__.py
neuralops/core/triton_kernels/_base.py
neuralops/core/triton_kernels/_common.py
neuralops/core/triton_kernels/_types.py
neuralops/core/triton_kernels/autotuned_configs.json
neuralops/core/triton_kernels/autotuner.py
neuralops/core/triton_kernels/block_sparse.py
neuralops/core/triton_kernels/cosformer_triton_kernel.py
neuralops/core/triton_kernels/cur_linear.py
neuralops/core/triton_kernels/differential_attention.py
neuralops/core/triton_kernels/dynamic_sparse_attention.py
neuralops/core/triton_kernels/elementwise.py
neuralops/core/triton_kernels/flash_decoding.py
neuralops/core/triton_kernels/fms_scan.py
neuralops/core/triton_kernels/fused_ce.py
neuralops/core/triton_kernels/fused_kd.py
neuralops/core/triton_kernels/fused_norm_linear.py
neuralops/core/triton_kernels/fused_rope.py
neuralops/core/triton_kernels/gdn_scan.py
neuralops/core/triton_kernels/gla_scan.py
neuralops/core/triton_kernels/gqa.py
neuralops/core/triton_kernels/hardware_profile.py
neuralops/core/triton_kernels/hgrn2_scan.py
neuralops/core/triton_kernels/hydra_attention.py
neuralops/core/triton_kernels/linear_attn.py
neuralops/core/triton_kernels/low_rank.py
neuralops/core/triton_kernels/op_registry.py
neuralops/core/triton_kernels/paged_attention.py
neuralops/core/triton_kernels/retnet_retention.py
neuralops/core/triton_kernels/selective_scan.py
neuralops/core/triton_kernels/sliding_window.py
neuralops/core/triton_kernels/softplus.py
neuralops/core/triton_kernels/sparse_attn.py
neuralops/core/triton_kernels/state_update.py
neuralops/core/triton_kernels/varlen_attention.py
neuralops/core/triton_kernels/standalone/__init__.py
neuralops/core/triton_kernels/standalone/block_sparse_streaming_attn.py
neuralops/core/triton_kernels/standalone/chunked_delta_gate_scan.py
neuralops/core/triton_kernels/standalone/cosformer_linear_attention.py
neuralops/core/triton_kernels/standalone/fused_act_scale_quant_gemm.py
neuralops/core/triton_kernels/standalone/fused_hadamard_w4a16_gemm.py
neuralops/core/triton_kernels/standalone/fused_kronecker_matmul.py
neuralops/core/triton_kernels/standalone/fused_latent_kv_cache_attention.py
neuralops/core/triton_kernels/standalone/fused_lowrank_gemm.py
neuralops/core/triton_kernels/standalone/hgrn2_fused_bwd_scan.py
neuralops/core/triton_kernels/standalone/hybrid_local_kernel_triton.py
neuralops/core/triton_kernels/standalone/lut_codebook_dequant_gemm.py
neuralops/core/triton_kernels/standalone/rpca_sparse_gemm.py
neuralops/core/triton_kernels/standalone/spectral_entropy_svd_gate.py
neuralops/core/triton_kernels/standalone/strided_tt.py
neuralops/core/utils/__init__.py
neuralops/core/utils/config.py
neuralops/core/utils/general.py
neuralops/core/utils/gqa.py
neuralops/core/utils/lora.py
neuralops/core/utils/masks.py
neuralops/core/utils/rope.py
neuralops/data/README.md
neuralops/data/__init__.py
neuralops/data/base.py
neuralops/data/glue.py
neuralops/data/glue_loader.py
neuralops/data/multi_choice.py
neuralops/data/multidataset.py
neuralops/data/packing.py
neuralops/data/streaming.py
neuralops/data/synthetic_generator.py
neuralops/data/benchmark_datasets/__init__.py
neuralops/data/benchmark_datasets/loaders.py
neuralops/data/benchmark_datasets/manifest.py
neuralops/data/benchmark_datasets/synthetic.py
neuralops/distributed/__init__.py
neuralops/distributed/context_parallel.py
neuralops/distributed/fsdp2.py
neuralops/distributed/megatron_hooks.py
neuralops/distributed/tensor_parallel.py
neuralops/evaluation/__init__.py
neuralops/evaluation/ab_testing.py
neuralops/evaluation/eval_all_models_datasets.py
neuralops/evaluation/eval_data.py
neuralops/evaluation/eval_patcher.py
neuralops/evaluation/eval_perplexity.py
neuralops/evaluation/eval_pipeline.py
neuralops/evaluation/eval_reporter.py
neuralops/evaluation/eval_types.py
neuralops/evaluation/eval_utils.py
neuralops/evaluation/fairness.py
neuralops/evaluation/full_mnli_validation.py
neuralops/evaluation/harness.py
neuralops/evaluation/label_quality.py
neuralops/evaluation/lm_eval_adapter.py
neuralops/evaluation/metrics.py
neuralops/evaluation/niah.py
neuralops/evaluation/niah_passkey.py
neuralops/evaluation/ppl.py
neuralops/evaluation/retraining.py
neuralops/evaluation/run_baseline_comparison.py
neuralops/evaluation/run_lm_eval_harness.py
neuralops/evaluation/standalone/README.md
neuralops/evaluation/standalone/__init__.py
neuralops/evaluation/standalone/__main__.py
neuralops/evaluation/standalone/cli.py
neuralops/evaluation/standalone/eval_arithmetic_continuation_256steps.py
neuralops/evaluation/standalone/eval_concurrent_offloading_jitter.py
neuralops/evaluation/standalone/eval_continuous_500token_stress.py
neuralops/evaluation/standalone/eval_cot_jitter_128steps.py
neuralops/evaluation/standalone/eval_reasoning_and_cot_scaling.py
neuralops/evaluation/standalone/eval_reasoning_long_context.py
neuralops/evaluation/standalone/eval_speculative_decoding.py
neuralops/evaluation/standalone/eval_speculative_sweep_k1_k8.py
neuralops/evaluation/standalone/eval_ultra_long_context_scaling.py
neuralops/evaluation/standalone/master_comprehensive_evaluation.py
neuralops/executor/__init__.py
neuralops/executor/executor.py
neuralops/executor/plan.py
neuralops/executor/planner.py
neuralops/executor/result.py
neuralops/executor/snapshot.py
neuralops/experiment_logging/__init__.py
neuralops/experiment_logging/callbacks.py
neuralops/experiment_logging/config.py
neuralops/experiment_logging/integration.py
neuralops/experiment_logging/logger.py
neuralops/experiment_logging/tracker.py
neuralops/export/__init__.py
neuralops/export/exporter.py
neuralops/export/hf_compat.py
neuralops/export/runtime_compat.py
neuralops/export/serving.py
neuralops/export/surgery_manifest.py
neuralops/export/unified.py
neuralops/inference/__init__.py
neuralops/inference/engine.py
neuralops/inference/paged_cache.py
neuralops/inference/speculative_decoding.py
neuralops/integrations/__init__.py
neuralops/integrations/compressed_tensors.py
neuralops/integrations/distributed_compile.py
neuralops/integrations/hf_automodel.py
neuralops/integrations/radix_prefix_cache.py
neuralops/integrations/serving.py
neuralops/integrations/sglang.py
neuralops/integrations/tensorrt_llm.py
neuralops/integrations/tgi.py
neuralops/integrations/vllm.py
neuralops/integrations/vllm_plugin.py
neuralops/integrations/fla/__init__.py
neuralops/integrations/fla/adapter.py
neuralops/integrations/fla/cache_translator.py
neuralops/integrations/fla/registry_bridge.py
neuralops/integrations/fla/weights_converter.py
neuralops/integrations/sglang/__init__.py
neuralops/integrations/sglang/radix_recurrent.py
neuralops/integrations/vllm/__init__.py
neuralops/integrations/vllm/backend.py
neuralops/integrations/vllm/state_table.py
neuralops/kernels/__init__.py
neuralops/kernels/extended_kernels.py
neuralops/kernels/cuda/__init__.py
neuralops/kernels/triton/__init__.py
neuralops/layers/__init__.py
neuralops/layers/base.py
neuralops/layers/expert_choice_moe.py
neuralops/layers/fused_svd_kernel.py
neuralops/layers/gated_delta_net.py
neuralops/layers/hgrn2_gated_layer.py
neuralops/layers/minimal_svd.py
neuralops/layers/simple_ssm.py
neuralops/layers/svd_linear_attention.py
neuralops/layers/adaptive/__init__.py
neuralops/layers/adaptive/adaptive_span_attention.py
neuralops/layers/adaptive/block_transformer_hiba.py
neuralops/layers/adaptive/eat.py
neuralops/layers/adaptive/infini_attention.py
neuralops/layers/adaptive/lola_attention.py
neuralops/layers/adaptive/progressive_token_pruning.py
neuralops/layers/adaptive/sink_attention.py
neuralops/layers/adaptive/span_expanded_attention.py
neuralops/layers/adaptive/squeezing_heads_distill.py
neuralops/layers/adaptive/token_compressed_attention.py
neuralops/layers/dense/__init__.py
neuralops/layers/dense/full_attention.py
neuralops/layers/dense/zeros_attention.py
neuralops/layers/experimental/__init__.py
neuralops/layers/experimental/template_attention.py
neuralops/layers/fast_kernels/__init__.py
neuralops/layers/fast_kernels/adasplash_attention.py
neuralops/layers/fast_kernels/flash_attention3.py
neuralops/layers/fast_kernels/flash_attention3_fp8.py
neuralops/layers/fast_kernels/soa_attn.py
neuralops/layers/fast_kernels/xattention.py
neuralops/layers/gated/__init__.py
neuralops/layers/gated/decay_linear_attention.py
neuralops/layers/gated/flagship_fla.py
neuralops/layers/gated/gated_delta_net.py
neuralops/layers/gated/gated_deltanet_block.py
neuralops/layers/gated/hgrn2_gated_deltanet.py
neuralops/layers/gated/hgrn2_gated_layer.py
neuralops/layers/gated/hgrn2_gated_outer.py
neuralops/layers/gated/hla_attention.py
neuralops/layers/gated/kda_attention.py
neuralops/layers/hybrid/__init__.py
neuralops/layers/hybrid/fusion_attn.py
neuralops/layers/hybrid/gated_hybrid_kernel_attention.py
neuralops/layers/hybrid/granite_hybrid.py
neuralops/layers/hybrid/halo_regla.py
neuralops/layers/hybrid/hybrid_attention.py
neuralops/layers/hybrid/hybrid_local_kernel_attention.py
neuralops/layers/hybrid/landmark_local_attention.py
neuralops/layers/hybrid/mixattention_moska.py
neuralops/layers/hybrid/optimized_hybrid_attention.py
neuralops/layers/hybrid/positive_kernel_linear_attention.py
neuralops/layers/hybrid/refined_landmark_attention.py
neuralops/layers/hybrid/regla_attention.py
neuralops/layers/hybrid/spectron_fp8_attention.py
neuralops/layers/hybrid/split_head_hybrid_attention.py
neuralops/layers/hybrid/tri_branch_hybrid_attention.py
neuralops/layers/linear/__init__.py
neuralops/layers/linear/chela_slay.py
neuralops/layers/linear/cosformer.py
neuralops/layers/linear/galerkin_attention.py
neuralops/layers/linear/gla_attention.py
neuralops/layers/linear/linformer_attention.py
neuralops/layers/linear/nasc_attention.py
neuralops/layers/linear/nystrom_attention.py
neuralops/layers/linear/performer_attention.py
neuralops/layers/linear/primal_attention.py
neuralops/layers/linear/rala_attention.py
neuralops/layers/linear/rpc_attention.py
neuralops/layers/linear/spectra_v2.py
neuralops/layers/linear/spectraformer_attention.py
neuralops/layers/linear/spectron.py
neuralops/layers/linear/tlinformer_attention.py
neuralops/layers/linear/tpa_attention.py
neuralops/layers/linear/triton_cosformer.py
neuralops/layers/modern/__init__.py
neuralops/layers/modern/alibi.py
neuralops/layers/modern/cross_attention.py
neuralops/layers/modern/dynamic_conv_attention.py
neuralops/layers/modern/gqa_attention.py
neuralops/layers/modern/mla_attention.py
neuralops/layers/modern/mqa.py
neuralops/layers/modern/nha_attention.py
neuralops/layers/modern/qcqa_attention.py
neuralops/layers/modern/unified_rope.py
neuralops/layers/modern/vig_attention.py
neuralops/layers/modern/wgqa_attention.py
neuralops/layers/sparse/__init__.py
neuralops/layers/sparse/adaptive_sparse_attention.py
neuralops/layers/sparse/bam_umoe.py
neuralops/layers/sparse/cluster_attention.py
neuralops/layers/sparse/expert_choice_moe.py
neuralops/layers/sparse/hamming_attention.py
neuralops/layers/sparse/lsh_attention.py
neuralops/layers/sparse/moba_attention.py
neuralops/layers/sparse/moe_deltakv_paged.py
neuralops/layers/sparse/nsa_attention.py
neuralops/layers/sparse/padre_attention.py
neuralops/layers/sparse/reap_moe.py
neuralops/layers/sparse/reap_moe_router.py
neuralops/layers/sparse/routing_attention.py
neuralops/layers/ssm/__init__.py
neuralops/layers/ssm/goldfinch_ahn.py
neuralops/layers/ssm/griffin_ssd.py
neuralops/layers/ssm/hymba_transx.py
neuralops/layers/ssm/jamba.py
neuralops/layers/ssm/jamba_info.py
neuralops/layers/ssm/mamba_block.py
neuralops/layers/ssm/mamba_svd_flash.py
neuralops/layers/ssm/nexus.py
neuralops/layers/ssm/orion.py
neuralops/layers/ssm/phantom.py
neuralops/layers/ssm/samba_m3.py
neuralops/layers/ssm/samba_moe.py
neuralops/layers/ssm/selective_ssm.py
neuralops/layers/ssm/simple_ssm.py
neuralops/layers/ssm/spectral_mamba.py
neuralops/layers/ssm/upi_stuffed_mamba.py
neuralops/layers/ssm/vspec.py
neuralops/layers/svd/__init__.py
neuralops/layers/svd/adaptive_svd_attention.py
neuralops/layers/svd/asvd_attention.py
neuralops/layers/svd/compressed_attention.py
neuralops/layers/svd/compressed_mha_attention.py
neuralops/layers/svd/factorised_matrix_state.py
neuralops/layers/svd/fused_svd_kernel.py
neuralops/layers/svd/lora_attention.py
neuralops/layers/svd/minimal_nova.py
neuralops/layers/svd/minimal_svd.py
neuralops/layers/svd/naive_svd.py
neuralops/layers/svd/projection_factorized_attn.py
neuralops/layers/svd/residual_svd_attention.py
neuralops/layers/svd/salt_attention.py
neuralops/layers/svd/svd_attention.py
neuralops/layers/svd/svd_compressed.py
neuralops/layers/svd/svd_linear_attention.py
neuralops/layers/svd/svd_linear_decay.py
neuralops/layers/svd/svd_llm_v2_attention.py
neuralops/layers/svd/svd_mamba.py
neuralops/layers/svd/svd_projection_attention.py
neuralops/layers/svd/triton_svd_linear_attention.py
neuralops/models/__init__.py
neuralops/models/cache.py
neuralops/models/configuration.py
neuralops/models/cuda_graph.py
neuralops/models/gla_hf_model.py
neuralops/models/hub.py
neuralops/models/hybrid_spec.py
neuralops/models/layer_norm_fix.py
neuralops/models/modeling.py
neuralops/models/modeling_block.py
neuralops/models/modeling_mlp.py
neuralops/models/modeling_norm.py
neuralops/models/modeling_rope.py
neuralops/models/paged_state.py
neuralops/models/surgical_io.py
neuralops/operations/__init__.py
neuralops/operations/base.py
neuralops/operations/errors.py
neuralops/operations/registry.py
neuralops/operations/adaptation/__init__.py
neuralops/operations/adaptation/distill.py
neuralops/operations/adaptation/heal.py
neuralops/operations/adaptation/lora.py
neuralops/operations/architecture/__init__.py
neuralops/operations/architecture/drop_layer.py
neuralops/operations/architecture/modify.py
neuralops/operations/architecture/reduce_mlp.py
neuralops/operations/attention/__init__.py
neuralops/operations/attention/configure.py
neuralops/operations/attention/replace.py
neuralops/operations/export/__init__.py
neuralops/operations/export/checkpoint.py
neuralops/operations/export/model.py
neuralops/operations/verify/__init__.py
neuralops/operations/verify/parity.py
neuralops/operations/weights/__init__.py
neuralops/operations/weights/compress.py
neuralops/operations/weights/decompose.py
neuralops/operations/weights/prune.py
neuralops/operations/weights/quantize.py
neuralops/operations/weights/svd_aasvd.py
neuralops/operations/weights/svd/__init__.py
neuralops/operations/weights/svd/aasvd.py
neuralops/ops/__init__.py
neuralops/ops/cuda/README.md
neuralops/ops/cuda/__init__.py
neuralops/ops/cuda/_attention_autograd_builder.py
neuralops/ops/cuda/_bindings.py
neuralops/ops/cuda/_common.cuh
neuralops/ops/cuda/_fallback.py
neuralops/ops/cuda/_map.py
neuralops/ops/cuda/_types.py
neuralops/ops/cuda/_utils.py
neuralops/ops/cuda/fallback.py
neuralops/ops/cuda/act_scale_gemm/__init__.py
neuralops/ops/cuda/act_scale_gemm/act_scale_autograd.py
neuralops/ops/cuda/act_scale_gemm/act_scale_binding.cpp
neuralops/ops/cuda/act_scale_gemm/act_scale_gemm.cu
neuralops/ops/cuda/adaptive_span/__init__.py
neuralops/ops/cuda/adaptive_span/adaptive_span.cu
neuralops/ops/cuda/adaptive_span/adaptive_span_autograd.py
neuralops/ops/cuda/adaptive_span/adaptive_span_binding.cpp
neuralops/ops/cuda/aegis_gate_norm/__init__.py
neuralops/ops/cuda/aegis_gate_norm/aegis_gate_norm.cu
neuralops/ops/cuda/aegis_gate_norm/aegis_gate_norm_autograd.py
neuralops/ops/cuda/aegis_gate_norm/aegis_gate_norm_binding.cpp
neuralops/ops/cuda/alibi_attention/__init__.py
neuralops/ops/cuda/alibi_attention/alibi_attention.cu
neuralops/ops/cuda/alibi_attention/alibi_autograd.py
neuralops/ops/cuda/alibi_attention/alibi_binding.cpp
neuralops/ops/cuda/asvd/__init__.py
neuralops/ops/cuda/asvd/asvd.cu
neuralops/ops/cuda/asvd/autograd.py
neuralops/ops/cuda/asvd/binding.cpp
neuralops/ops/cuda/based_taylor_attention/__init__.py
neuralops/ops/cuda/based_taylor_attention/autograd.py
neuralops/ops/cuda/based_taylor_attention/based_taylor_attention.cu
neuralops/ops/cuda/based_taylor_attention/binding.cpp
neuralops/ops/cuda/bigbird/__init__.py
neuralops/ops/cuda/bigbird/bigbird.cu
neuralops/ops/cuda/bigbird/bigbird_autograd.py
neuralops/ops/cuda/bigbird/bigbird_binding.cpp
neuralops/ops/cuda/bitonic_topk/__init__.py
neuralops/ops/cuda/bitonic_topk/bitonic_topk.cu
neuralops/ops/cuda/bitonic_topk/bitonic_topk_autograd.py
neuralops/ops/cuda/bitonic_topk/bitonic_topk_binding.cpp
neuralops/ops/cuda/block_diag_gemm/__init__.py
neuralops/ops/cuda/block_diag_gemm/block_diag_autograd.py
neuralops/ops/cuda/block_diag_gemm/block_diag_binding.cpp
neuralops/ops/cuda/block_diag_gemm/block_diag_gemm.cu
neuralops/ops/cuda/causal_conv1d/__init__.py
neuralops/ops/cuda/causal_conv1d/causal_conv1d.cu
neuralops/ops/cuda/causal_conv1d/conv1d_autograd.py
neuralops/ops/cuda/causal_conv1d/conv1d_binding.cpp
neuralops/ops/cuda/channel_shuffle/__init__.py
neuralops/ops/cuda/channel_shuffle/channel_shuffle.cu
neuralops/ops/cuda/channel_shuffle/shuffle_autograd.py
neuralops/ops/cuda/channel_shuffle/shuffle_binding.cpp
neuralops/ops/cuda/cluster_attention/__init__.py
neuralops/ops/cuda/cluster_attention/cluster_attention.cu
neuralops/ops/cuda/cluster_attention/cluster_attention_autograd.py
neuralops/ops/cuda/cluster_attention/cluster_attention_binding.cpp
neuralops/ops/cuda/cosformer/__init__.py
neuralops/ops/cuda/cosformer/cosformer.cu
neuralops/ops/cuda/cosformer/cosformer_attn.cu
neuralops/ops/cuda/cosformer/cosformer_autograd.py
neuralops/ops/cuda/cosformer/cosformer_binding.cpp
neuralops/ops/cuda/cross_attention/__init__.py
neuralops/ops/cuda/cross_attention/cross_attention.cu
neuralops/ops/cuda/cross_attention/cross_attn_autograd.py
neuralops/ops/cuda/cross_attention/cross_attn_binding.cpp
neuralops/ops/cuda/decay_linear_attention/__init__.py
neuralops/ops/cuda/decay_linear_attention/decay_linear_attention.cu
neuralops/ops/cuda/decay_linear_attention/decay_linear_attention_autograd.py
neuralops/ops/cuda/decay_linear_attention/decay_linear_attention_binding.cpp
neuralops/ops/cuda/differential_attention/__init__.py
neuralops/ops/cuda/differential_attention/differential_attention.cu
neuralops/ops/cuda/differential_attention/differential_attention_autograd.py
neuralops/ops/cuda/differential_attention/differential_attention_binding.cpp
neuralops/ops/cuda/direct_svd/__init__.py
neuralops/ops/cuda/direct_svd/autograd.py
neuralops/ops/cuda/direct_svd/binding.cpp
neuralops/ops/cuda/direct_svd/direct_svd.cu
neuralops/ops/cuda/dynamic_conv1d/__init__.py
neuralops/ops/cuda/dynamic_conv1d/dynamic_conv1d.cu
neuralops/ops/cuda/dynamic_conv1d/dynamic_conv1d_autograd.py
neuralops/ops/cuda/dynamic_conv1d/dynamic_conv1d_binding.cpp
neuralops/ops/cuda/entmax_bisect/__init__.py
neuralops/ops/cuda/entmax_bisect/entmax_bisect.cu
neuralops/ops/cuda/entmax_bisect/entmax_bisect_autograd.py
neuralops/ops/cuda/entmax_bisect/entmax_bisect_binding.cpp
neuralops/ops/cuda/entropy_gate/__init__.py
neuralops/ops/cuda/entropy_gate/entropy_gate.cu
neuralops/ops/cuda/entropy_gate/entropy_gate_autograd.py
neuralops/ops/cuda/entropy_gate/entropy_gate_binding.cpp
neuralops/ops/cuda/entropy_pruning/__init__.py
neuralops/ops/cuda/entropy_pruning/entropy_pruning.cu
neuralops/ops/cuda/entropy_pruning/entropy_pruning_autograd.py
neuralops/ops/cuda/entropy_pruning/entropy_pruning_binding.cpp
neuralops/ops/cuda/fast_attention/__init__.py
neuralops/ops/cuda/fast_attention/fast_attention.cu
neuralops/ops/cuda/fast_attention/fast_attention_autograd.py
neuralops/ops/cuda/fast_attention/fast_attention_binding.cpp
neuralops/ops/cuda/fast_gelu/__init__.py
neuralops/ops/cuda/fast_gelu/fast_gelu.cu
neuralops/ops/cuda/fast_gelu/fast_gelu_autograd.py
neuralops/ops/cuda/fast_gelu/fast_gelu_binding.cpp
neuralops/ops/cuda/favor_plus/__init__.py
neuralops/ops/cuda/favor_plus/favor_plus.cu
neuralops/ops/cuda/favor_plus/favor_plus_autograd.py
neuralops/ops/cuda/favor_plus/favor_plus_binding.cpp
neuralops/ops/cuda/flash_decode_stage2/__init__.py
neuralops/ops/cuda/flash_decode_stage2/flash_decode_stage2.cu
neuralops/ops/cuda/flash_decode_stage2/flash_decode_stage2_autograd.py
neuralops/ops/cuda/flash_decode_stage2/flash_decode_stage2_binding.cpp
neuralops/ops/cuda/flash_decoding/__init__.py
neuralops/ops/cuda/flash_decoding/flash_dec_autograd.py
neuralops/ops/cuda/flash_decoding/flash_dec_binding.cpp
neuralops/ops/cuda/flash_decoding/flash_decoding.cu
neuralops/ops/cuda/flash_gqa/__init__.py
neuralops/ops/cuda/flash_gqa/flash_gqa.cu
neuralops/ops/cuda/flash_gqa/flash_gqa.cuh
neuralops/ops/cuda/flash_gqa/flash_gqa_autograd.py
neuralops/ops/cuda/flash_gqa/flash_gqa_binding.cpp
neuralops/ops/cuda/fms_scan/__init__.py
neuralops/ops/cuda/fms_scan/fms_autograd.py
neuralops/ops/cuda/fms_scan/fms_binding.cpp
neuralops/ops/cuda/fms_scan/fms_scan.cu
neuralops/ops/cuda/fp4_gemm/__init__.py
neuralops/ops/cuda/fp4_gemm/fp4_autograd.py
neuralops/ops/cuda/fp4_gemm/fp4_binding.cpp
neuralops/ops/cuda/fp4_gemm/fp4_gemm.cu
neuralops/ops/cuda/fp8_gemm/__init__.py
neuralops/ops/cuda/fp8_gemm/fp8_autograd.py
neuralops/ops/cuda/fp8_gemm/fp8_binding.cpp
neuralops/ops/cuda/fp8_gemm/fp8_gemm.cu
neuralops/ops/cuda/fused_ce/__init__.py
neuralops/ops/cuda/fused_ce/fused_ce.cu
neuralops/ops/cuda/fused_ce/fused_ce_autograd.py
neuralops/ops/cuda/fused_ce/fused_ce_binding.cpp
neuralops/ops/cuda/fused_dropout_add/__init__.py
neuralops/ops/cuda/fused_dropout_add/dropout_add_autograd.py
neuralops/ops/cuda/fused_dropout_add/dropout_add_binding.cpp
neuralops/ops/cuda/fused_dropout_add/fused_dropout_add.cu
neuralops/ops/cuda/fused_kd/__init__.py
neuralops/ops/cuda/fused_kd/fused_kd.cu
neuralops/ops/cuda/fused_kd/kd_autograd.py
neuralops/ops/cuda/fused_kd/kd_binding.cpp
neuralops/ops/cuda/fused_norm_linear/__init__.py
neuralops/ops/cuda/fused_norm_linear/fused_norm_linear.cu
neuralops/ops/cuda/fused_norm_linear/norm_linear_autograd.py
neuralops/ops/cuda/fused_norm_linear/norm_linear_binding.cpp
neuralops/ops/cuda/fused_rope/__init__.py
neuralops/ops/cuda/fused_rope/fused_rope.cu
neuralops/ops/cuda/fused_rope/rope_autograd.py
neuralops/ops/cuda/fused_rope/rope_binding.cpp
neuralops/ops/cuda/fwht_transform/__init__.py
neuralops/ops/cuda/fwht_transform/fwht_transform.cu
neuralops/ops/cuda/fwht_transform/fwht_transform_autograd.py
neuralops/ops/cuda/fwht_transform/fwht_transform_binding.cpp
neuralops/ops/cuda/galerkin_attention/__init__.py
neuralops/ops/cuda/galerkin_attention/galerkin_attention.cu
neuralops/ops/cuda/galerkin_attention/galerkin_attention_autograd.py
neuralops/ops/cuda/galerkin_attention/galerkin_attention_binding.cpp
neuralops/ops/cuda/gated_deltanet/__init__.py
neuralops/ops/cuda/gated_deltanet/autograd.py
neuralops/ops/cuda/gated_deltanet/binding.cpp
neuralops/ops/cuda/gated_deltanet/gated_deltanet.cu
neuralops/ops/cuda/gdn_delta_rule/__init__.py
neuralops/ops/cuda/gdn_delta_rule/gdn_delta_rule.cu
neuralops/ops/cuda/gdn_delta_rule/gdn_delta_rule_autograd.py
neuralops/ops/cuda/gdn_delta_rule/gdn_delta_rule_binding.cpp
neuralops/ops/cuda/gdn_scan/__init__.py
neuralops/ops/cuda/gdn_scan/chunked_delta_gate_scan.cu
neuralops/ops/cuda/gdn_scan/gdn_autograd.py
neuralops/ops/cuda/gdn_scan/gdn_binding.cpp
neuralops/ops/cuda/gla_chunk_attn/__init__.py
neuralops/ops/cuda/gla_chunk_attn/autograd.py
neuralops/ops/cuda/gla_chunk_attn/binding.cpp
neuralops/ops/cuda/gla_chunk_attn/gla_chunk_attn.cu
neuralops/ops/cuda/gla_scan/__init__.py
neuralops/ops/cuda/gla_scan/gla_autograd.py
neuralops/ops/cuda/gla_scan/gla_binding.cpp
neuralops/ops/cuda/gla_scan/gla_scan.cu
neuralops/ops/cuda/gla_unnormalized_scan/__init__.py
neuralops/ops/cuda/gla_unnormalized_scan/gla_unnormalized_scan.cu
neuralops/ops/cuda/gla_unnormalized_scan/gla_unnormalized_scan_autograd.py
neuralops/ops/cuda/gla_unnormalized_scan/gla_unnormalized_scan_binding.cpp
neuralops/ops/cuda/goldfinch_ahn/__init__.py
neuralops/ops/cuda/goldfinch_ahn/goldfinch_ahn.cu
neuralops/ops/cuda/goldfinch_ahn/goldfinch_ahn_autograd.py
neuralops/ops/cuda/goldfinch_ahn/goldfinch_ahn_binding.cpp
neuralops/ops/cuda/griffin_ssd/__init__.py
neuralops/ops/cuda/griffin_ssd/griffin_ssd.cu
neuralops/ops/cuda/griffin_ssd/griffin_ssd_autograd.py
neuralops/ops/cuda/griffin_ssd/griffin_ssd_binding.cpp
neuralops/ops/cuda/hadamard_gemm/__init__.py
neuralops/ops/cuda/hadamard_gemm/hadamard_autograd.py
neuralops/ops/cuda/hadamard_gemm/hadamard_binding.cpp
neuralops/ops/cuda/hadamard_gemm/hadamard_gemm.cu
neuralops/ops/cuda/hgrn2_scan/__init__.py
neuralops/ops/cuda/hgrn2_scan/hgrn2_autograd.py
neuralops/ops/cuda/hgrn2_scan/hgrn2_binding.cpp
neuralops/ops/cuda/hgrn2_scan/hgrn2_scan.cu
neuralops/ops/cuda/hgrn2_spatial_scan/__init__.py
neuralops/ops/cuda/hgrn2_spatial_scan/hgrn2_spatial_scan.cu
neuralops/ops/cuda/hgrn2_spatial_scan/hgrn2_spatial_scan_autograd.py
neuralops/ops/cuda/hgrn2_spatial_scan/hgrn2_spatial_scan_binding.cpp
neuralops/ops/cuda/hla_attention/__init__.py
neuralops/ops/cuda/hla_attention/hla_attention.cu
neuralops/ops/cuda/hla_attention/hla_attention_autograd.py
neuralops/ops/cuda/hla_attention/hla_attention_binding.cpp
neuralops/ops/cuda/hstu_attention/__init__.py
neuralops/ops/cuda/hstu_attention/hstu_attention.cu
neuralops/ops/cuda/hstu_attention/hstu_attention_autograd.py
neuralops/ops/cuda/hstu_attention/hstu_attention_binding.cpp
neuralops/ops/cuda/hybrid_local_kernel/__init__.py
neuralops/ops/cuda/hybrid_local_kernel/hybrid_local_kernel.cu
neuralops/ops/cuda/hybrid_local_kernel/hybrid_local_kernel_autograd.py
neuralops/ops/cuda/hybrid_local_kernel/hybrid_local_kernel_binding.cpp
neuralops/ops/cuda/hydra_attention/__init__.py
neuralops/ops/cuda/hydra_attention/hydra_attention.cu
neuralops/ops/cuda/hydra_attention/hydra_attention_autograd.py
neuralops/ops/cuda/hydra_attention/hydra_attention_binding.cpp
neuralops/ops/cuda/hymba_transx/__init__.py
neuralops/ops/cuda/hymba_transx/hymba_transx.cu
neuralops/ops/cuda/hymba_transx/hymba_transx_autograd.py
neuralops/ops/cuda/hymba_transx/hymba_transx_binding.cpp
neuralops/ops/cuda/jamba/__init__.py
neuralops/ops/cuda/jamba/jamba.cu
neuralops/ops/cuda/jamba/jamba_autograd.py
neuralops/ops/cuda/jamba/jamba_binding.cpp
neuralops/ops/cuda/jamba_info/__init__.py
neuralops/ops/cuda/jamba_info/jamba_info.cu
neuralops/ops/cuda/jamba_info/jamba_info_autograd.py
neuralops/ops/cuda/jamba_info/jamba_info_binding.cpp
neuralops/ops/cuda/kronecker_gemm/__init__.py
neuralops/ops/cuda/kronecker_gemm/kronecker_autograd.py
neuralops/ops/cuda/kronecker_gemm/kronecker_binding.cpp
neuralops/ops/cuda/kronecker_gemm/kronecker_gemm.cu
neuralops/ops/cuda/latent_kv_attn/__init__.py
neuralops/ops/cuda/latent_kv_attn/latent_kv_attn.cu
neuralops/ops/cuda/latent_kv_attn/latent_kv_autograd.py
neuralops/ops/cuda/latent_kv_attn/latent_kv_binding.cpp
neuralops/ops/cuda/layernorm/__init__.py
neuralops/ops/cuda/layernorm/layernorm.cu
neuralops/ops/cuda/layernorm/layernorm_autograd.py
neuralops/ops/cuda/layernorm/layernorm_binding.cpp
neuralops/ops/cuda/lightning_attention/__init__.py
neuralops/ops/cuda/lightning_attention/autograd.py
neuralops/ops/cuda/lightning_attention/binding.cpp
neuralops/ops/cuda/lightning_attention/lightning_attention.cu
neuralops/ops/cuda/linear_attention/__init__.py
neuralops/ops/cuda/linear_attention/linear_attn.cu
neuralops/ops/cuda/linear_attention/linear_attn_autograd.py
neuralops/ops/cuda/linear_attention/linear_attn_binding.cpp
neuralops/ops/cuda/linear_rnn_attention/__init__.py
neuralops/ops/cuda/linear_rnn_attention/linear_rnn_attention.cu
neuralops/ops/cuda/linear_rnn_attention/linear_rnn_attention_autograd.py
neuralops/ops/cuda/linear_rnn_attention/linear_rnn_attention_binding.cpp
neuralops/ops/cuda/linformer_attention/__init__.py
neuralops/ops/cuda/linformer_attention/linformer_attention.cu
neuralops/ops/cuda/linformer_attention/linformer_attention_autograd.py
neuralops/ops/cuda/linformer_attention/linformer_attention_binding.cpp
neuralops/ops/cuda/liquid_attention/__init__.py
neuralops/ops/cuda/liquid_attention/liquid_attention.cu
neuralops/ops/cuda/liquid_attention/liquid_attention_autograd.py
neuralops/ops/cuda/liquid_attention/liquid_attention_binding.cpp
neuralops/ops/cuda/local_attention/__init__.py
neuralops/ops/cuda/local_attention/local_attention.cu
neuralops/ops/cuda/local_attention/local_attention_autograd.py
neuralops/ops/cuda/local_attention/local_attention_binding.cpp
neuralops/ops/cuda/logcumsumexp/__init__.py
neuralops/ops/cuda/logcumsumexp/logcumsumexp.cu
neuralops/ops/cuda/logcumsumexp/logcumsumexp_autograd.py
neuralops/ops/cuda/logcumsumexp/logcumsumexp_binding.cpp
neuralops/ops/cuda/longformer/__init__.py
neuralops/ops/cuda/longformer/longformer.cu
neuralops/ops/cuda/longformer/longformer_autograd.py
neuralops/ops/cuda/longformer/longformer_binding.cpp
neuralops/ops/cuda/low_rank_svd/__init__.py
neuralops/ops/cuda/low_rank_svd/fused_lowrank_gated_gemm.cu
neuralops/ops/cuda/low_rank_svd/lowrank_autograd.py
neuralops/ops/cuda/low_rank_svd/lowrank_binding.cpp
neuralops/ops/cuda/lut_gemm/__init__.py
neuralops/ops/cuda/lut_gemm/lut_autograd.py
neuralops/ops/cuda/lut_gemm/lut_binding.cpp
neuralops/ops/cuda/lut_gemm/lut_gemm.cu
neuralops/ops/cuda/mamba2_block/__init__.py
neuralops/ops/cuda/mamba2_block/mamba2_block.cu
neuralops/ops/cuda/mamba2_block/mamba2_block_autograd.py
neuralops/ops/cuda/mamba2_block/mamba2_block_binding.cpp
neuralops/ops/cuda/mamba_block/__init__.py
neuralops/ops/cuda/mamba_block/mamba_block.cu
neuralops/ops/cuda/mamba_block/mamba_block_autograd.py
neuralops/ops/cuda/mamba_block/mamba_block_binding.cpp
neuralops/ops/cuda/mamba_svd_flash/__init__.py
neuralops/ops/cuda/mamba_svd_flash/mamba_svd_flash.cu
neuralops/ops/cuda/mamba_svd_flash/mamba_svd_flash_autograd.py
neuralops/ops/cuda/mamba_svd_flash/mamba_svd_flash_binding.cpp
neuralops/ops/cuda/moe_routing/__init__.py
neuralops/ops/cuda/moe_routing/expert_dispatch.cu
neuralops/ops/cuda/moe_routing/moe_autograd.py
neuralops/ops/cuda/moe_routing/moe_binding.cpp
neuralops/ops/cuda/moe_routing/moe_router.cu
neuralops/ops/cuda/moe_routing/moe_routing.cuh
neuralops/ops/cuda/multi_scale_retention/__init__.py
neuralops/ops/cuda/multi_scale_retention/multi_scale_retention.cu
neuralops/ops/cuda/multi_scale_retention/multi_scale_retention_autograd.py
neuralops/ops/cuda/multi_scale_retention/retention_autograd.py
neuralops/ops/cuda/multi_scale_retention/retention_binding.cpp
neuralops/ops/cuda/nasc_attention/__init__.py
neuralops/ops/cuda/nasc_attention/nasc_attention.cu
neuralops/ops/cuda/nasc_attention/nasc_attention_autograd.py
neuralops/ops/cuda/nasc_attention/nasc_attention_binding.cpp
neuralops/ops/cuda/nexus/__init__.py
neuralops/ops/cuda/nexus/nexus.cu
neuralops/ops/cuda/nexus/nexus_autograd.py
neuralops/ops/cuda/nexus/nexus_binding.cpp
neuralops/ops/cuda/nystrom_attention/__init__.py
neuralops/ops/cuda/nystrom_attention/nystrom_attention.cu
neuralops/ops/cuda/nystrom_attention/nystrom_attention_autograd.py
neuralops/ops/cuda/nystrom_attention/nystrom_attention_binding.cpp
neuralops/ops/cuda/orion/__init__.py
neuralops/ops/cuda/orion/orion.cu
neuralops/ops/cuda/orion/orion_autograd.py
neuralops/ops/cuda/orion/orion_binding.cpp
neuralops/ops/cuda/paged_attention/__init__.py
neuralops/ops/cuda/paged_attention/paged_attention.cu
neuralops/ops/cuda/paged_attention/paged_attention.cuh
neuralops/ops/cuda/paged_attention/paged_attention_autograd.py
neuralops/ops/cuda/paged_attention/paged_attention_binding.cpp
neuralops/ops/cuda/paged_kv_cache/__init__.py
neuralops/ops/cuda/paged_kv_cache/kv_cache_autograd.py
neuralops/ops/cuda/paged_kv_cache/kv_cache_binding.cpp
neuralops/ops/cuda/paged_kv_cache/kv_cache_copy.cu
neuralops/ops/cuda/paged_kv_cache/paged_kv_cache.cuh
neuralops/ops/cuda/paged_kv_evict/__init__.py
neuralops/ops/cuda/paged_kv_evict/paged_kv_evict.cu
neuralops/ops/cuda/paged_kv_evict/paged_kv_evict_autograd.py
neuralops/ops/cuda/paged_kv_evict/paged_kv_evict_binding.cpp
neuralops/ops/cuda/paged_recurrent_step/__init__.py
neuralops/ops/cuda/paged_recurrent_step/paged_recurrent_step.cu
neuralops/ops/cuda/paged_recurrent_step/paged_recurrent_step_autograd.py
neuralops/ops/cuda/paged_recurrent_step/paged_recurrent_step_binding.cpp
neuralops/ops/cuda/phantom/__init__.py
neuralops/ops/cuda/phantom/phantom.cu
neuralops/ops/cuda/phantom/phantom_autograd.py
neuralops/ops/cuda/phantom/phantom_binding.cpp
neuralops/ops/cuda/quantized_gemm/__init__.py
neuralops/ops/cuda/quantized_gemm/fp8_gemm.cu
neuralops/ops/cuda/quantized_gemm/quant_autograd.py
neuralops/ops/cuda/quantized_gemm/quant_binding.cpp
neuralops/ops/cuda/quantized_gemm/quant_gemm.cuh
neuralops/ops/cuda/quantized_gemm/w4a16_gemm.cu
neuralops/ops/cuda/recurrent_gla_step/__init__.py
neuralops/ops/cuda/recurrent_gla_step/gla_step_autograd.py
neuralops/ops/cuda/recurrent_gla_step/gla_step_binding.cpp
neuralops/ops/cuda/recurrent_gla_step/recurrent_gla_step.cu
neuralops/ops/cuda/recurrent_hgrn2_step/__init__.py
neuralops/ops/cuda/recurrent_hgrn2_step/hgrn2_step_autograd.py
neuralops/ops/cuda/recurrent_hgrn2_step/hgrn2_step_binding.cpp
neuralops/ops/cuda/recurrent_hgrn2_step/recurrent_hgrn2_step.cu
neuralops/ops/cuda/reformer/__init__.py
neuralops/ops/cuda/reformer/reformer.cu
neuralops/ops/cuda/reformer/reformer_autograd.py
neuralops/ops/cuda/reformer/reformer_binding.cpp
neuralops/ops/cuda/retnet_chunk_retention/__init__.py
neuralops/ops/cuda/retnet_chunk_retention/autograd.py
neuralops/ops/cuda/retnet_chunk_retention/binding.cpp
neuralops/ops/cuda/retnet_chunk_retention/retnet_chunk_retention.cu
neuralops/ops/cuda/rfa_attention/__init__.py
neuralops/ops/cuda/rfa_attention/rfa_attention.cu
neuralops/ops/cuda/rfa_attention/rfa_attention_autograd.py
neuralops/ops/cuda/rfa_attention/rfa_attention_binding.cpp
neuralops/ops/cuda/rms_variance_match/__init__.py
neuralops/ops/cuda/rms_variance_match/rms_variance_match.cu
neuralops/ops/cuda/rms_variance_match/rms_variance_match_autograd.py
neuralops/ops/cuda/rms_variance_match/rms_variance_match_binding.cpp
neuralops/ops/cuda/rmsnorm/__init__.py
neuralops/ops/cuda/rmsnorm/rmsnorm.cu
neuralops/ops/cuda/rmsnorm/rmsnorm_autograd.py
neuralops/ops/cuda/rmsnorm/rmsnorm_binding.cpp
neuralops/ops/cuda/rotational_svd/__init__.py
neuralops/ops/cuda/rotational_svd/rotational_svd.cu
neuralops/ops/cuda/rotational_svd/rotational_svd_autograd.py
neuralops/ops/cuda/rotational_svd/rotational_svd_binding.cpp
neuralops/ops/cuda/routing_attention/__init__.py
neuralops/ops/cuda/routing_attention/routing_attention.cu
neuralops/ops/cuda/routing_attention/routing_attention_autograd.py
neuralops/ops/cuda/routing_attention/routing_attention_binding.cpp
neuralops/ops/cuda/rpca_sparse_svd/__init__.py
neuralops/ops/cuda/rpca_sparse_svd/rpca_sparse_svd.cu
neuralops/ops/cuda/rpca_sparse_svd/rpca_sparse_svd_autograd.py
neuralops/ops/cuda/rpca_sparse_svd/rpca_sparse_svd_binding.cpp
neuralops/ops/cuda/rwkv6/__init__.py
neuralops/ops/cuda/rwkv6/rwkv6.cu
neuralops/ops/cuda/rwkv6/rwkv6_autograd.py
neuralops/ops/cuda/rwkv6/rwkv6_binding.cpp
neuralops/ops/cuda/rwkv6_state_scan/__init__.py
neuralops/ops/cuda/rwkv6_state_scan/autograd.py
neuralops/ops/cuda/rwkv6_state_scan/binding.cpp
neuralops/ops/cuda/rwkv6_state_scan/rwkv6_state_scan.cu
neuralops/ops/cuda/samba_m3/__init__.py
neuralops/ops/cuda/samba_m3/samba_m3.cu
neuralops/ops/cuda/samba_m3/samba_m3_autograd.py
neuralops/ops/cuda/samba_m3/samba_m3_binding.cpp
neuralops/ops/cuda/samba_moe/__init__.py
neuralops/ops/cuda/samba_moe/samba_moe.cu
neuralops/ops/cuda/samba_moe/samba_moe_autograd.py
neuralops/ops/cuda/samba_moe/samba_moe_binding.cpp
neuralops/ops/cuda/selective_scan/__init__.py
neuralops/ops/cuda/selective_scan/selective_scan.cu
neuralops/ops/cuda/selective_scan/selective_scan.cuh
neuralops/ops/cuda/selective_scan/selective_scan_autograd.py
neuralops/ops/cuda/selective_scan/selective_scan_binding.cpp
neuralops/ops/cuda/selective_ssm/__init__.py
neuralops/ops/cuda/selective_ssm/selective_ssm.cu
neuralops/ops/cuda/selective_ssm/selective_ssm_autograd.py
neuralops/ops/cuda/selective_ssm/selective_ssm_binding.cpp
neuralops/ops/cuda/simple_ssm/__init__.py
neuralops/ops/cuda/simple_ssm/simple_ssm.cu
neuralops/ops/cuda/simple_ssm/simple_ssm_autograd.py
neuralops/ops/cuda/simple_ssm/simple_ssm_binding.cpp
neuralops/ops/cuda/sliding_window/__init__.py
neuralops/ops/cuda/sliding_window/sliding_autograd.py
neuralops/ops/cuda/sliding_window/sliding_binding.cpp
neuralops/ops/cuda/sliding_window/sliding_window.cu
neuralops/ops/cuda/sliding_window/sliding_window.cuh
neuralops/ops/cuda/soa_attn/__init__.py
neuralops/ops/cuda/soa_attn/soa_attn.cu
neuralops/ops/cuda/soa_attn/soa_attn_autograd.py
neuralops/ops/cuda/soa_attn/soa_attn_binding.cpp
neuralops/ops/cuda/softplus/__init__.py
neuralops/ops/cuda/softplus/softplus.cu
neuralops/ops/cuda/softplus/softplus_autograd.py
neuralops/ops/cuda/softplus/softplus_binding.cpp
neuralops/ops/cuda/sparse_attention/__init__.py
neuralops/ops/cuda/sparse_attention/block_sparse_attn.cu
neuralops/ops/cuda/sparse_attention/sparse_attention.cu
neuralops/ops/cuda/sparse_attention/sparse_attention.cuh
neuralops/ops/cuda/sparse_attention/sparse_attention_autograd.py
neuralops/ops/cuda/sparse_attention/sparse_attention_binding.cpp
neuralops/ops/cuda/sparse_attention/sparse_autograd.py
neuralops/ops/cuda/sparse_attention/sparse_binding.cpp
neuralops/ops/cuda/spectra_v2/__init__.py
neuralops/ops/cuda/spectra_v2/spectra_v2.cu
neuralops/ops/cuda/spectra_v2/spectra_v2_autograd.py
neuralops/ops/cuda/spectra_v2/spectra_v2_binding.cpp
neuralops/ops/cuda/spectraformer_attention/__init__.py
neuralops/ops/cuda/spectraformer_attention/spectraformer_attention.cu
neuralops/ops/cuda/spectraformer_attention/spectraformer_attention_autograd.py
neuralops/ops/cuda/spectraformer_attention/spectraformer_attention_binding.cpp
neuralops/ops/cuda/spectral_mamba/__init__.py
neuralops/ops/cuda/spectral_mamba/spectral_mamba.cu
neuralops/ops/cuda/spectral_mamba/spectral_mamba_autograd.py
neuralops/ops/cuda/spectral_mamba/spectral_mamba_binding.cpp
neuralops/ops/cuda/spectral_shrinkage/__init__.py
neuralops/ops/cuda/spectral_shrinkage/spectral_shrinkage.cu
neuralops/ops/cuda/spectral_shrinkage/spectral_shrinkage_autograd.py
neuralops/ops/cuda/spectral_shrinkage/spectral_shrinkage_binding.cpp
neuralops/ops/cuda/speculative_verify/__init__.py
neuralops/ops/cuda/speculative_verify/spec_autograd.py
neuralops/ops/cuda/speculative_verify/spec_binding.cpp
neuralops/ops/cuda/speculative_verify/speculative_verify.cu
neuralops/ops/cuda/split_head_norm/__init__.py
neuralops/ops/cuda/split_head_norm/split_head_norm.cu
neuralops/ops/cuda/split_head_norm/split_head_norm_autograd.py
neuralops/ops/cuda/split_head_norm/split_head_norm_binding.cpp
neuralops/ops/cuda/state_update/__init__.py
neuralops/ops/cuda/state_update/state_autograd.py
neuralops/ops/cuda/state_update/state_binding.cpp
neuralops/ops/cuda/state_update/state_update.cu
neuralops/ops/cuda/svd_prefix_scan/__init__.py
neuralops/ops/cuda/svd_prefix_scan/svd_prefix_scan.cu
neuralops/ops/cuda/svd_prefix_scan/svd_prefix_scan_autograd.py
neuralops/ops/cuda/svd_prefix_scan/svd_prefix_scan_binding.cpp
neuralops/ops/cuda/swiglu/__init__.py
neuralops/ops/cuda/swiglu/swiglu.cu
neuralops/ops/cuda/swiglu/swiglu_autograd.py
neuralops/ops/cuda/swiglu/swiglu_binding.cpp
neuralops/ops/cuda/ternary_gemm/__init__.py
neuralops/ops/cuda/ternary_gemm/ternary_autograd.py
neuralops/ops/cuda/ternary_gemm/ternary_binding.cpp
neuralops/ops/cuda/ternary_gemm/ternary_gemm.cu
neuralops/ops/cuda/tpa_attention/__init__.py
neuralops/ops/cuda/tpa_attention/tpa_attention.cu
neuralops/ops/cuda/tpa_attention/tpa_attention_autograd.py
neuralops/ops/cuda/tpa_attention/tpa_attention_binding.cpp
neuralops/ops/cuda/tt_contraction/__init__.py
neuralops/ops/cuda/tt_contraction/tt_autograd.py
neuralops/ops/cuda/tt_contraction/tt_binding.cpp
neuralops/ops/cuda/tt_contraction/tt_contraction.cu
neuralops/ops/cuda/unified_rope_offset/__init__.py
neuralops/ops/cuda/unified_rope_offset/unified_rope_offset.cu
neuralops/ops/cuda/unified_rope_offset/unified_rope_offset_autograd.py
neuralops/ops/cuda/unified_rope_offset/unified_rope_offset_binding.cpp
neuralops/ops/cuda/upi_stuffed_mamba/__init__.py
neuralops/ops/cuda/upi_stuffed_mamba/upi_stuffed_mamba.cu
neuralops/ops/cuda/upi_stuffed_mamba/upi_stuffed_mamba_autograd.py
neuralops/ops/cuda/upi_stuffed_mamba/upi_stuffed_mamba_binding.cpp
neuralops/ops/cuda/varlen_attention/__init__.py
neuralops/ops/cuda/varlen_attention/varlen_attention.cu
neuralops/ops/cuda/varlen_attention/varlen_autograd.py
neuralops/ops/cuda/varlen_attention/varlen_binding.cpp
neuralops/ops/cuda/vspec/__init__.py
neuralops/ops/cuda/vspec/vspec.cu
neuralops/ops/cuda/vspec/vspec_autograd.py
neuralops/ops/cuda/vspec/vspec_binding.cpp
neuralops/ops/pytorch/__init__.py
neuralops/ops/triton/README.md
neuralops/ops/triton/__init__.py
neuralops/ops/triton/_base.py
neuralops/ops/triton/_common.py
neuralops/ops/triton/_types.py
neuralops/ops/triton/adaptive_sparse_triton.py
neuralops/ops/triton/autotuned_configs.json
neuralops/ops/triton/autotuner.py
neuralops/ops/triton/based_scan.py
neuralops/ops/triton/block_sparse.py
neuralops/ops/triton/chela_slay_triton.py
neuralops/ops/triton/cosformer_triton_kernel.py
neuralops/ops/triton/cross_attention_triton.py
neuralops/ops/triton/cur_linear.py
neuralops/ops/triton/differential_attention.py
neuralops/ops/triton/dynamic_conv_triton.py
neuralops/ops/triton/dynamic_sparse_attention.py
neuralops/ops/triton/elementwise.py
neuralops/ops/triton/flash_decoding.py
neuralops/ops/triton/fms_scan.py
neuralops/ops/triton/fused_ce.py
neuralops/ops/triton/fused_kd.py
neuralops/ops/triton/fused_norm_linear.py
neuralops/ops/triton/fused_rope.py
neuralops/ops/triton/gdn_scan.py
neuralops/ops/triton/gla_scan.py
neuralops/ops/triton/gqa.py
neuralops/ops/triton/hardware_profile.py
neuralops/ops/triton/hgrn2_scan.py
neuralops/ops/triton/hydra_attention.py
neuralops/ops/triton/lightning_scan.py
neuralops/ops/triton/linear_attn.py
neuralops/ops/triton/low_rank.py
neuralops/ops/triton/lsh_attention_triton.py
neuralops/ops/triton/op_registry.py
neuralops/ops/triton/paged_attention.py
neuralops/ops/triton/prune_admm.py
neuralops/ops/triton/prune_sparsegpt.py
neuralops/ops/triton/prune_wanda.py
neuralops/ops/triton/quantize_awq.py
neuralops/ops/triton/quantize_fp8.py
neuralops/ops/triton/quantize_kmeans.py
neuralops/ops/triton/rala_attention_triton.py
neuralops/ops/triton/retnet_retention.py
neuralops/ops/triton/routing_attention_triton.py
neuralops/ops/triton/rwkv6_scan.py
neuralops/ops/triton/selective_scan.py
neuralops/ops/triton/sliding_window.py
neuralops/ops/triton/softplus.py
neuralops/ops/triton/sparse_attn.py
neuralops/ops/triton/state_update.py
neuralops/ops/triton/token_compressed_triton.py
neuralops/ops/triton/varlen_attention.py
neuralops/ops/triton/standalone/__init__.py
neuralops/ops/triton/standalone/block_sparse_streaming_attn.py
neuralops/ops/triton/standalone/chunked_delta_gate_scan.py
neuralops/ops/triton/standalone/cosformer_linear_attention.py
neuralops/ops/triton/standalone/fused_act_scale_quant_gemm.py
neuralops/ops/triton/standalone/fused_hadamard_w4a16_gemm.py
neuralops/ops/triton/standalone/fused_kronecker_matmul.py
neuralops/ops/triton/standalone/fused_latent_kv_cache_attention.py
neuralops/ops/triton/standalone/fused_lowrank_gemm.py
neuralops/ops/triton/standalone/hgrn2_fused_bwd_scan.py
neuralops/ops/triton/standalone/hybrid_local_kernel_triton.py
neuralops/ops/triton/standalone/lut_codebook_dequant_gemm.py
neuralops/ops/triton/standalone/rpca_sparse_gemm.py
neuralops/ops/triton/standalone/spectral_entropy_svd_gate.py
neuralops/ops/triton/standalone/strided_tt.py
neuralops/optimization/__init__.py
neuralops/optimization/kernels/__init__.py
neuralops/pipeline_transform/__init__.py
neuralops/pipeline_transform/auto_config.py
neuralops/pipeline_transform/dependencies.py
neuralops/pipeline_transform/errors.py
neuralops/pipeline_transform/executor.py
neuralops/pipeline_transform/hardware_planner.py
neuralops/pipeline_transform/plan.py
neuralops/pipeline_transform/planner.py
neuralops/pipeline_transform/result.py
neuralops/pipeline_transform/rollback.py
neuralops/pipeline_transform/snapshot.py
neuralops/recipe/__init__.py
neuralops/recipe/canonical.py
neuralops/recipe/errors.py
neuralops/recipe/loader.py
neuralops/recipe/schema.py
neuralops/recipe/serializer.py
neuralops/recipe/versioning.py
neuralops/reporting/__init__.py
neuralops/reporting/environment.py
neuralops/reporting/evidence.py
neuralops/reporting/report.py
neuralops/results_saver/__init__.py
neuralops/results_saver/config.py
neuralops/results_saver/saver.py
neuralops/results_saver/backends/__init__.py
neuralops/results_saver/backends/huggingface.py
neuralops/results_saver/pipeline/__init__.py
neuralops/results_saver/pipeline/result_writer.py
neuralops/results_saver/storage/__init__.py
neuralops/results_saver/storage/sqlite_ops.py
neuralops/results_saver/writers/__init__.py
neuralops/results_saver/writers/csv_writer.py
neuralops/results_saver/writers/json_parquet_writer.py
neuralops/results_saver/writers/plot_writer.py
neuralops/runners/__init__.py
neuralops/runners/run_master_pipeline.py
neuralops/runners/run_monitor_server.py
neuralops/runners/run_sweep.py
neuralops/runners/sweep_registry.json
neuralops/runners/unified_orchestrator.py
neuralops/runners/module_sweeps/__init__.py
neuralops/runners/monitor/__init__.py
neuralops/runners/monitor/advanced_data.py
neuralops/runners/monitor/endpoints.py
neuralops/runners/monitor/fastapi_app.py
neuralops/runners/monitor/rendering.py
neuralops/runners/monitor/schemas.py
neuralops/runners/monitor/server.py
neuralops/runners/monitor/stats.py
neuralops/runners/monitor/telemetry.py
neuralops/serving/__init__.py
neuralops/serving/request_batcher.py
neuralops/surgery/__init__.py
neuralops/surgery/attention_replace.py
neuralops/surgery/calibration.py
neuralops/surgery/endoskeletal_shell.py
neuralops/surgery/healing.py
neuralops/surgery/hf_cache_bridge.py
neuralops/surgery/layer_replacement.py
neuralops/surgery/model_surgery.py
neuralops/surgery/param_recovery.py
neuralops/surgery/pipeline.py
neuralops/surgery/recipe.py
neuralops/surgery/registry.py
neuralops/surgery/scanner.py
neuralops/surgery/shadow_twin.py
neuralops/surgery/surgery.py
neuralops/surgery/surgery_manifest.py
neuralops/surgery/surgical_io.py
neuralops/surgery/topology_router.py
neuralops/surgery/universal_calibrator.py
neuralops/surgery/validation.py
neuralops/surgery/attention/replace.py
neuralops/surgery/layers/prune.py
neuralops/surgery/mlp/shrink.py
neuralops/surgery/recovery/distill.py
neuralops/surgery/weights/quantize.py
neuralops/tracking/__init__.py
neuralops/tracking/backends.py
neuralops/tracking/callbacks.py
neuralops/tracking/tracker.py
neuralops/trainer/__init__.py
neuralops/trainer/base_trainer.py
neuralops/trainer/callbacks.py
neuralops/trainer/checkpointing.py
neuralops/trainer/custom_loop_trainer.py
neuralops/trainer/foundation_pretrainer.py
neuralops/trainer/hf_callback.py
neuralops/trainer/hf_trainer.py
neuralops/trainer/hyperopt.py
neuralops/trainer/layer_distill.py
neuralops/trainer/losses.py
neuralops/trainer/metrics.py
neuralops/trainer/neuralops_trainer.py
neuralops/trainer/registry.py
neuralops/trainer/results_manager.py
neuralops/trainer/rl_trainer.py
neuralops/trainer/schedulers.py
neuralops/trainer/train_lra.py
neuralops/trainer/trainer.py
neuralops/trainer/trainer_factory.py
neuralops/trainer/trainer_svd.py
neuralops/trainer/unsloth_trainer.py
neuralops/trainer/utils.py
neuralops/trainer/distillation/multi_level_kd.py
neuralops/trainer/methods/__init__.py
neuralops/trainer/methods/fisher.py
neuralops/trainer/methods/gelora.py
neuralops/trainer/methods/llrd.py
neuralops/trainer/methods/lora.py
neuralops/trainer/methods/mixout.py
neuralops/trainer/methods/rdrop_r3f.py
neuralops/trainer/methods/registry.py
neuralops/trainer/optimizers/__init__.py
neuralops/trainer/optimizers/factory.py
neuralops/trainer/optimizers/lion.py
neuralops/trainer/optimizers/muon.py
neuralops/trainer/optimizers/riemannian.py
neuralops/trainer/optimizers/stiefel.py
neuralops/trainer/peft_recovery/svd_adapters.py
neuralops/trainer/regularizers/attention_stability.py
neuralops/trainer/rl_alignment/preference_and_onpolicy.py
neuralops/trainer/surgery_schedules/mohawk.py
neuralops/trainer/ttt/test_time_trainer.py
neuralops/training/__init__.py
neuralops/utils/__init__.py
neuralops/utils/amp_safety.py
neuralops/utils/architecture.py
neuralops/utils/attention_profiler.py
neuralops/utils/checkpoint.py
neuralops/utils/config.py
neuralops/utils/device.py
neuralops/utils/helpers.py
neuralops/utils/hf_git_exporter.py
neuralops/utils/hub_integration.py
neuralops/utils/layer_norm_fix.py
neuralops/utils/logger.py
neuralops/utils/logging_config.py
neuralops/utils/lora.py
neuralops/utils/metrics.py
neuralops/utils/model_family.py
neuralops/utils/paths.py
neuralops/utils/profiler.py
neuralops/utils/qwen_compat.py
neuralops/utils/replace_attention.py
neuralops/utils/results_saver.py
neuralops/utils/seed.py
neuralops/utils/varlen_padding.py
neuralops/utils/compat/__init__.py
neuralops/utils/compat/aliases.py
neuralops/utils/compat/architectures.py
neuralops/utils/compat/param_recovery.py
neuralops/validation/__init__.py
neuralops/validation/base.py
neuralops/validation/data_validator.py
neuralops/validation/memory_validator.py
neuralops/validation/model_validator.py
neuralops/validation/numerical_validator.py
neuralops/validation/profiles.py
neuralops/validation/report_generator.py
neuralops/validation/result.py
neuralops/validation/runner.py
neuralops/validation/speed_validator.py
neuralops/validation/training_validator.py
neuralops/validation/gates/__init__.py
neuralops/validation/gates/behavioral.py
neuralops/validation/gates/behavioral/__init__.py
neuralops/validation/gates/behavioral/attention_patterns.py
neuralops/validation/gates/behavioral/logit_kl.py
neuralops/validation/gates/behavioral/output_similarity.py
neuralops/validation/gates/behavioral/perplexity.py
neuralops/validation/gates/empirical/__init__.py
neuralops/validation/gates/empirical/accuracy.py
neuralops/validation/gates/empirical/latency.py
neuralops/validation/gates/empirical/niah.py
neuralops/validation/gates/empirical/throughput.py
neuralops/validation/gates/empirical/vram.py
neuralops/validation/gates/numerical/__init__.py
neuralops/validation/gates/numerical/forward_pass.py
neuralops/validation/gates/numerical/no_nan_inf.py
neuralops/validation/gates/structural/__init__.py
neuralops/validation/gates/structural/connectivity.py
neuralops/validation/gates/structural/dtypes.py
neuralops/validation/gates/structural/parameter_count.py
neuralops/validation/gates/structural/shapes.py
neuralops/validator/__init__.py
neuralops/validator/errors.py
neuralops/validator/static.py