CHANGELOG.md
LICENSE
MANIFEST.in
README.md
pyproject.toml
neuralops/__init__.py
neuralops/__main__.py
neuralops/api.py
neuralops/architectures.py
neuralops/checkpoint.py
neuralops/config.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/analysis/__init__.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_plots.py
neuralops/analysis/plotting.py
neuralops/analysis/report_generator.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/attention/__init__.py
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/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/terminal_ui.py
neuralops/cli/test_cmd.py
neuralops/cli/train_cmd.py
neuralops/compression/__init__.py
neuralops/compression_engine/__init__.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/__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/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/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/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/__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/_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/act_scale_gemm/act_scale_autograd.py
neuralops/core/cuda_kernels/act_scale_gemm/act_scale_binding.cpp
neuralops/core/cuda_kernels/act_scale_gemm/act_scale_gemm.cu
neuralops/core/cuda_kernels/adaptive_span/__init__.py
neuralops/core/cuda_kernels/adaptive_span/adaptive_span.cu
neuralops/core/cuda_kernels/adaptive_span/adaptive_span_autograd.py
neuralops/core/cuda_kernels/adaptive_span/adaptive_span_binding.cpp
neuralops/core/cuda_kernels/aegis_gate_norm/__init__.py
neuralops/core/cuda_kernels/aegis_gate_norm/aegis_gate_norm.cu
neuralops/core/cuda_kernels/aegis_gate_norm/aegis_gate_norm_autograd.py
neuralops/core/cuda_kernels/aegis_gate_norm/aegis_gate_norm_binding.cpp
neuralops/core/cuda_kernels/alibi_attention/__init__.py
neuralops/core/cuda_kernels/alibi_attention/alibi_attention.cu
neuralops/core/cuda_kernels/alibi_attention/alibi_autograd.py
neuralops/core/cuda_kernels/alibi_attention/alibi_binding.cpp
neuralops/core/cuda_kernels/bigbird/__init__.py
neuralops/core/cuda_kernels/bigbird/bigbird.cu
neuralops/core/cuda_kernels/bigbird/bigbird_autograd.py
neuralops/core/cuda_kernels/bigbird/bigbird_binding.cpp
neuralops/core/cuda_kernels/bitonic_topk/__init__.py
neuralops/core/cuda_kernels/bitonic_topk/bitonic_topk.cu
neuralops/core/cuda_kernels/bitonic_topk/bitonic_topk_autograd.py
neuralops/core/cuda_kernels/bitonic_topk/bitonic_topk_binding.cpp
neuralops/core/cuda_kernels/block_diag_gemm/__init__.py
neuralops/core/cuda_kernels/block_diag_gemm/block_diag_autograd.py
neuralops/core/cuda_kernels/block_diag_gemm/block_diag_binding.cpp
neuralops/core/cuda_kernels/block_diag_gemm/block_diag_gemm.cu
neuralops/core/cuda_kernels/causal_conv1d/__init__.py
neuralops/core/cuda_kernels/causal_conv1d/causal_conv1d.cu
neuralops/core/cuda_kernels/causal_conv1d/conv1d_autograd.py
neuralops/core/cuda_kernels/causal_conv1d/conv1d_binding.cpp
neuralops/core/cuda_kernels/channel_shuffle/__init__.py
neuralops/core/cuda_kernels/channel_shuffle/channel_shuffle.cu
neuralops/core/cuda_kernels/channel_shuffle/shuffle_autograd.py
neuralops/core/cuda_kernels/channel_shuffle/shuffle_binding.cpp
neuralops/core/cuda_kernels/cluster_attention/__init__.py
neuralops/core/cuda_kernels/cluster_attention/cluster_attention.cu
neuralops/core/cuda_kernels/cluster_attention/cluster_attention_autograd.py
neuralops/core/cuda_kernels/cluster_attention/cluster_attention_binding.cpp
neuralops/core/cuda_kernels/cosformer/__init__.py
neuralops/core/cuda_kernels/cosformer/cosformer.cu
neuralops/core/cuda_kernels/cosformer/cosformer_attn.cu
neuralops/core/cuda_kernels/cosformer/cosformer_autograd.py
neuralops/core/cuda_kernels/cosformer/cosformer_binding.cpp
neuralops/core/cuda_kernels/cross_attention/__init__.py
neuralops/core/cuda_kernels/cross_attention/cross_attention.cu
neuralops/core/cuda_kernels/cross_attention/cross_attn_autograd.py
neuralops/core/cuda_kernels/cross_attention/cross_attn_binding.cpp
neuralops/core/cuda_kernels/decay_linear_attention/__init__.py
neuralops/core/cuda_kernels/decay_linear_attention/decay_linear_attention.cu
neuralops/core/cuda_kernels/decay_linear_attention/decay_linear_attention_autograd.py
neuralops/core/cuda_kernels/decay_linear_attention/decay_linear_attention_binding.cpp
neuralops/core/cuda_kernels/differential_attention/__init__.py
neuralops/core/cuda_kernels/differential_attention/differential_attention.cu
neuralops/core/cuda_kernels/differential_attention/differential_attention_autograd.py
neuralops/core/cuda_kernels/differential_attention/differential_attention_binding.cpp
neuralops/core/cuda_kernels/dynamic_conv1d/__init__.py
neuralops/core/cuda_kernels/dynamic_conv1d/dynamic_conv1d.cu
neuralops/core/cuda_kernels/dynamic_conv1d/dynamic_conv1d_autograd.py
neuralops/core/cuda_kernels/dynamic_conv1d/dynamic_conv1d_binding.cpp
neuralops/core/cuda_kernels/entmax_bisect/__init__.py
neuralops/core/cuda_kernels/entmax_bisect/entmax_bisect.cu
neuralops/core/cuda_kernels/entmax_bisect/entmax_bisect_autograd.py
neuralops/core/cuda_kernels/entmax_bisect/entmax_bisect_binding.cpp
neuralops/core/cuda_kernels/entropy_gate/__init__.py
neuralops/core/cuda_kernels/entropy_gate/entropy_gate.cu
neuralops/core/cuda_kernels/entropy_gate/entropy_gate_autograd.py
neuralops/core/cuda_kernels/entropy_gate/entropy_gate_binding.cpp
neuralops/core/cuda_kernels/entropy_pruning/__init__.py
neuralops/core/cuda_kernels/entropy_pruning/entropy_pruning.cu
neuralops/core/cuda_kernels/entropy_pruning/entropy_pruning_autograd.py
neuralops/core/cuda_kernels/entropy_pruning/entropy_pruning_binding.cpp
neuralops/core/cuda_kernels/fast_attention/__init__.py
neuralops/core/cuda_kernels/fast_attention/fast_attention.cu
neuralops/core/cuda_kernels/fast_attention/fast_attention_autograd.py
neuralops/core/cuda_kernels/fast_attention/fast_attention_binding.cpp
neuralops/core/cuda_kernels/fast_gelu/__init__.py
neuralops/core/cuda_kernels/fast_gelu/fast_gelu.cu
neuralops/core/cuda_kernels/fast_gelu/fast_gelu_autograd.py
neuralops/core/cuda_kernels/fast_gelu/fast_gelu_binding.cpp
neuralops/core/cuda_kernels/favor_plus/__init__.py
neuralops/core/cuda_kernels/favor_plus/favor_plus.cu
neuralops/core/cuda_kernels/favor_plus/favor_plus_autograd.py
neuralops/core/cuda_kernels/favor_plus/favor_plus_binding.cpp
neuralops/core/cuda_kernels/flash_decode_stage2/__init__.py
neuralops/core/cuda_kernels/flash_decode_stage2/flash_decode_stage2.cu
neuralops/core/cuda_kernels/flash_decode_stage2/flash_decode_stage2_autograd.py
neuralops/core/cuda_kernels/flash_decode_stage2/flash_decode_stage2_binding.cpp
neuralops/core/cuda_kernels/flash_decoding/__init__.py
neuralops/core/cuda_kernels/flash_decoding/flash_dec_autograd.py
neuralops/core/cuda_kernels/flash_decoding/flash_dec_binding.cpp
neuralops/core/cuda_kernels/flash_decoding/flash_decoding.cu
neuralops/core/cuda_kernels/flash_gqa/__init__.py
neuralops/core/cuda_kernels/flash_gqa/flash_gqa.cu
neuralops/core/cuda_kernels/flash_gqa/flash_gqa.cuh
neuralops/core/cuda_kernels/flash_gqa/flash_gqa_autograd.py
neuralops/core/cuda_kernels/flash_gqa/flash_gqa_binding.cpp
neuralops/core/cuda_kernels/fms_scan/__init__.py
neuralops/core/cuda_kernels/fms_scan/fms_autograd.py
neuralops/core/cuda_kernels/fms_scan/fms_binding.cpp
neuralops/core/cuda_kernels/fms_scan/fms_scan.cu
neuralops/core/cuda_kernels/fp4_gemm/__init__.py
neuralops/core/cuda_kernels/fp4_gemm/fp4_autograd.py
neuralops/core/cuda_kernels/fp4_gemm/fp4_binding.cpp
neuralops/core/cuda_kernels/fp4_gemm/fp4_gemm.cu
neuralops/core/cuda_kernels/fp8_gemm/__init__.py
neuralops/core/cuda_kernels/fp8_gemm/fp8_autograd.py
neuralops/core/cuda_kernels/fp8_gemm/fp8_binding.cpp
neuralops/core/cuda_kernels/fp8_gemm/fp8_gemm.cu
neuralops/core/cuda_kernels/fused_ce/__init__.py
neuralops/core/cuda_kernels/fused_ce/fused_ce.cu
neuralops/core/cuda_kernels/fused_ce/fused_ce_autograd.py
neuralops/core/cuda_kernels/fused_ce/fused_ce_binding.cpp
neuralops/core/cuda_kernels/fused_dropout_add/__init__.py
neuralops/core/cuda_kernels/fused_dropout_add/dropout_add_autograd.py
neuralops/core/cuda_kernels/fused_dropout_add/dropout_add_binding.cpp
neuralops/core/cuda_kernels/fused_dropout_add/fused_dropout_add.cu
neuralops/core/cuda_kernels/fused_kd/__init__.py
neuralops/core/cuda_kernels/fused_kd/fused_kd.cu
neuralops/core/cuda_kernels/fused_kd/kd_autograd.py
neuralops/core/cuda_kernels/fused_kd/kd_binding.cpp
neuralops/core/cuda_kernels/fused_norm_linear/__init__.py
neuralops/core/cuda_kernels/fused_norm_linear/fused_norm_linear.cu
neuralops/core/cuda_kernels/fused_norm_linear/norm_linear_autograd.py
neuralops/core/cuda_kernels/fused_norm_linear/norm_linear_binding.cpp
neuralops/core/cuda_kernels/fused_rope/__init__.py
neuralops/core/cuda_kernels/fused_rope/fused_rope.cu
neuralops/core/cuda_kernels/fused_rope/rope_autograd.py
neuralops/core/cuda_kernels/fused_rope/rope_binding.cpp
neuralops/core/cuda_kernels/fwht_transform/__init__.py
neuralops/core/cuda_kernels/fwht_transform/fwht_transform.cu
neuralops/core/cuda_kernels/fwht_transform/fwht_transform_autograd.py
neuralops/core/cuda_kernels/fwht_transform/fwht_transform_binding.cpp
neuralops/core/cuda_kernels/galerkin_attention/__init__.py
neuralops/core/cuda_kernels/galerkin_attention/galerkin_attention.cu
neuralops/core/cuda_kernels/galerkin_attention/galerkin_attention_autograd.py
neuralops/core/cuda_kernels/galerkin_attention/galerkin_attention_binding.cpp
neuralops/core/cuda_kernels/gdn_delta_rule/__init__.py
neuralops/core/cuda_kernels/gdn_delta_rule/gdn_delta_rule.cu
neuralops/core/cuda_kernels/gdn_delta_rule/gdn_delta_rule_autograd.py
neuralops/core/cuda_kernels/gdn_delta_rule/gdn_delta_rule_binding.cpp
neuralops/core/cuda_kernels/gdn_scan/__init__.py
neuralops/core/cuda_kernels/gdn_scan/chunked_delta_gate_scan.cu
neuralops/core/cuda_kernels/gdn_scan/gdn_autograd.py
neuralops/core/cuda_kernels/gdn_scan/gdn_binding.cpp
neuralops/core/cuda_kernels/gla_scan/__init__.py
neuralops/core/cuda_kernels/gla_scan/gla_autograd.py
neuralops/core/cuda_kernels/gla_scan/gla_binding.cpp
neuralops/core/cuda_kernels/gla_scan/gla_scan.cu
neuralops/core/cuda_kernels/gla_unnormalized_scan/__init__.py
neuralops/core/cuda_kernels/gla_unnormalized_scan/gla_unnormalized_scan.cu
neuralops/core/cuda_kernels/gla_unnormalized_scan/gla_unnormalized_scan_autograd.py
neuralops/core/cuda_kernels/gla_unnormalized_scan/gla_unnormalized_scan_binding.cpp
neuralops/core/cuda_kernels/goldfinch_ahn/__init__.py
neuralops/core/cuda_kernels/goldfinch_ahn/goldfinch_ahn.cu
neuralops/core/cuda_kernels/goldfinch_ahn/goldfinch_ahn_autograd.py
neuralops/core/cuda_kernels/goldfinch_ahn/goldfinch_ahn_binding.cpp
neuralops/core/cuda_kernels/griffin_ssd/__init__.py
neuralops/core/cuda_kernels/griffin_ssd/griffin_ssd.cu
neuralops/core/cuda_kernels/griffin_ssd/griffin_ssd_autograd.py
neuralops/core/cuda_kernels/griffin_ssd/griffin_ssd_binding.cpp
neuralops/core/cuda_kernels/hadamard_gemm/__init__.py
neuralops/core/cuda_kernels/hadamard_gemm/hadamard_autograd.py
neuralops/core/cuda_kernels/hadamard_gemm/hadamard_binding.cpp
neuralops/core/cuda_kernels/hadamard_gemm/hadamard_gemm.cu
neuralops/core/cuda_kernels/hgrn2_scan/__init__.py
neuralops/core/cuda_kernels/hgrn2_scan/hgrn2_autograd.py
neuralops/core/cuda_kernels/hgrn2_scan/hgrn2_binding.cpp
neuralops/core/cuda_kernels/hgrn2_scan/hgrn2_scan.cu
neuralops/core/cuda_kernels/hgrn2_spatial_scan/__init__.py
neuralops/core/cuda_kernels/hgrn2_spatial_scan/hgrn2_spatial_scan.cu
neuralops/core/cuda_kernels/hgrn2_spatial_scan/hgrn2_spatial_scan_autograd.py
neuralops/core/cuda_kernels/hgrn2_spatial_scan/hgrn2_spatial_scan_binding.cpp
neuralops/core/cuda_kernels/hla_attention/__init__.py
neuralops/core/cuda_kernels/hla_attention/hla_attention.cu
neuralops/core/cuda_kernels/hla_attention/hla_attention_autograd.py
neuralops/core/cuda_kernels/hla_attention/hla_attention_binding.cpp
neuralops/core/cuda_kernels/hstu_attention/__init__.py
neuralops/core/cuda_kernels/hstu_attention/hstu_attention.cu
neuralops/core/cuda_kernels/hstu_attention/hstu_attention_autograd.py
neuralops/core/cuda_kernels/hstu_attention/hstu_attention_binding.cpp
neuralops/core/cuda_kernels/hybrid_local_kernel/__init__.py
neuralops/core/cuda_kernels/hybrid_local_kernel/hybrid_local_kernel.cu
neuralops/core/cuda_kernels/hybrid_local_kernel/hybrid_local_kernel_autograd.py
neuralops/core/cuda_kernels/hybrid_local_kernel/hybrid_local_kernel_binding.cpp
neuralops/core/cuda_kernels/hydra_attention/__init__.py
neuralops/core/cuda_kernels/hydra_attention/hydra_attention.cu
neuralops/core/cuda_kernels/hydra_attention/hydra_attention_autograd.py
neuralops/core/cuda_kernels/hydra_attention/hydra_attention_binding.cpp
neuralops/core/cuda_kernels/hymba_transx/__init__.py
neuralops/core/cuda_kernels/hymba_transx/hymba_transx.cu
neuralops/core/cuda_kernels/hymba_transx/hymba_transx_autograd.py
neuralops/core/cuda_kernels/hymba_transx/hymba_transx_binding.cpp
neuralops/core/cuda_kernels/jamba/__init__.py
neuralops/core/cuda_kernels/jamba/jamba.cu
neuralops/core/cuda_kernels/jamba/jamba_autograd.py
neuralops/core/cuda_kernels/jamba/jamba_binding.cpp
neuralops/core/cuda_kernels/jamba_info/__init__.py
neuralops/core/cuda_kernels/jamba_info/jamba_info.cu
neuralops/core/cuda_kernels/jamba_info/jamba_info_autograd.py
neuralops/core/cuda_kernels/jamba_info/jamba_info_binding.cpp
neuralops/core/cuda_kernels/kronecker_gemm/__init__.py
neuralops/core/cuda_kernels/kronecker_gemm/kronecker_autograd.py
neuralops/core/cuda_kernels/kronecker_gemm/kronecker_binding.cpp
neuralops/core/cuda_kernels/kronecker_gemm/kronecker_gemm.cu
neuralops/core/cuda_kernels/latent_kv_attn/__init__.py
neuralops/core/cuda_kernels/latent_kv_attn/latent_kv_attn.cu
neuralops/core/cuda_kernels/latent_kv_attn/latent_kv_autograd.py
neuralops/core/cuda_kernels/latent_kv_attn/latent_kv_binding.cpp
neuralops/core/cuda_kernels/layernorm/__init__.py
neuralops/core/cuda_kernels/layernorm/layernorm.cu
neuralops/core/cuda_kernels/layernorm/layernorm_autograd.py
neuralops/core/cuda_kernels/layernorm/layernorm_binding.cpp
neuralops/core/cuda_kernels/linear_attention/__init__.py
neuralops/core/cuda_kernels/linear_attention/linear_attn.cu
neuralops/core/cuda_kernels/linear_attention/linear_attn_autograd.py
neuralops/core/cuda_kernels/linear_attention/linear_attn_binding.cpp
neuralops/core/cuda_kernels/linear_rnn_attention/__init__.py
neuralops/core/cuda_kernels/linear_rnn_attention/linear_rnn_attention.cu
neuralops/core/cuda_kernels/linear_rnn_attention/linear_rnn_attention_autograd.py
neuralops/core/cuda_kernels/linear_rnn_attention/linear_rnn_attention_binding.cpp
neuralops/core/cuda_kernels/linformer_attention/__init__.py
neuralops/core/cuda_kernels/linformer_attention/linformer_attention.cu
neuralops/core/cuda_kernels/linformer_attention/linformer_attention_autograd.py
neuralops/core/cuda_kernels/linformer_attention/linformer_attention_binding.cpp
neuralops/core/cuda_kernels/liquid_attention/__init__.py
neuralops/core/cuda_kernels/liquid_attention/liquid_attention.cu
neuralops/core/cuda_kernels/liquid_attention/liquid_attention_autograd.py
neuralops/core/cuda_kernels/liquid_attention/liquid_attention_binding.cpp
neuralops/core/cuda_kernels/local_attention/__init__.py
neuralops/core/cuda_kernels/local_attention/local_attention.cu
neuralops/core/cuda_kernels/local_attention/local_attention_autograd.py
neuralops/core/cuda_kernels/local_attention/local_attention_binding.cpp
neuralops/core/cuda_kernels/logcumsumexp/__init__.py
neuralops/core/cuda_kernels/logcumsumexp/logcumsumexp.cu
neuralops/core/cuda_kernels/logcumsumexp/logcumsumexp_autograd.py
neuralops/core/cuda_kernels/logcumsumexp/logcumsumexp_binding.cpp
neuralops/core/cuda_kernels/longformer/__init__.py
neuralops/core/cuda_kernels/longformer/longformer.cu
neuralops/core/cuda_kernels/longformer/longformer_autograd.py
neuralops/core/cuda_kernels/longformer/longformer_binding.cpp
neuralops/core/cuda_kernels/low_rank_svd/__init__.py
neuralops/core/cuda_kernels/low_rank_svd/fused_lowrank_gated_gemm.cu
neuralops/core/cuda_kernels/low_rank_svd/lowrank_autograd.py
neuralops/core/cuda_kernels/low_rank_svd/lowrank_binding.cpp
neuralops/core/cuda_kernels/lut_gemm/__init__.py
neuralops/core/cuda_kernels/lut_gemm/lut_autograd.py
neuralops/core/cuda_kernels/lut_gemm/lut_binding.cpp
neuralops/core/cuda_kernels/lut_gemm/lut_gemm.cu
neuralops/core/cuda_kernels/mamba2_block/__init__.py
neuralops/core/cuda_kernels/mamba2_block/mamba2_block.cu
neuralops/core/cuda_kernels/mamba2_block/mamba2_block_autograd.py
neuralops/core/cuda_kernels/mamba2_block/mamba2_block_binding.cpp
neuralops/core/cuda_kernels/mamba_block/__init__.py
neuralops/core/cuda_kernels/mamba_block/mamba_block.cu
neuralops/core/cuda_kernels/mamba_block/mamba_block_autograd.py
neuralops/core/cuda_kernels/mamba_block/mamba_block_binding.cpp
neuralops/core/cuda_kernels/mamba_svd_flash/__init__.py
neuralops/core/cuda_kernels/mamba_svd_flash/mamba_svd_flash.cu
neuralops/core/cuda_kernels/mamba_svd_flash/mamba_svd_flash_autograd.py
neuralops/core/cuda_kernels/mamba_svd_flash/mamba_svd_flash_binding.cpp
neuralops/core/cuda_kernels/moe_routing/__init__.py
neuralops/core/cuda_kernels/moe_routing/expert_dispatch.cu
neuralops/core/cuda_kernels/moe_routing/moe_autograd.py
neuralops/core/cuda_kernels/moe_routing/moe_binding.cpp
neuralops/core/cuda_kernels/moe_routing/moe_router.cu
neuralops/core/cuda_kernels/moe_routing/moe_routing.cuh
neuralops/core/cuda_kernels/multi_scale_retention/__init__.py
neuralops/core/cuda_kernels/multi_scale_retention/multi_scale_retention.cu
neuralops/core/cuda_kernels/multi_scale_retention/multi_scale_retention_autograd.py
neuralops/core/cuda_kernels/multi_scale_retention/retention_autograd.py
neuralops/core/cuda_kernels/multi_scale_retention/retention_binding.cpp
neuralops/core/cuda_kernels/nasc_attention/__init__.py
neuralops/core/cuda_kernels/nasc_attention/nasc_attention.cu
neuralops/core/cuda_kernels/nasc_attention/nasc_attention_autograd.py
neuralops/core/cuda_kernels/nasc_attention/nasc_attention_binding.cpp
neuralops/core/cuda_kernels/nexus/__init__.py
neuralops/core/cuda_kernels/nexus/nexus.cu
neuralops/core/cuda_kernels/nexus/nexus_autograd.py
neuralops/core/cuda_kernels/nexus/nexus_binding.cpp
neuralops/core/cuda_kernels/nystrom_attention/__init__.py
neuralops/core/cuda_kernels/nystrom_attention/nystrom_attention.cu
neuralops/core/cuda_kernels/nystrom_attention/nystrom_attention_autograd.py
neuralops/core/cuda_kernels/nystrom_attention/nystrom_attention_binding.cpp
neuralops/core/cuda_kernels/orion/__init__.py
neuralops/core/cuda_kernels/orion/orion.cu
neuralops/core/cuda_kernels/orion/orion_autograd.py
neuralops/core/cuda_kernels/orion/orion_binding.cpp
neuralops/core/cuda_kernels/paged_attention/__init__.py
neuralops/core/cuda_kernels/paged_attention/paged_attention.cu
neuralops/core/cuda_kernels/paged_attention/paged_attention.cuh
neuralops/core/cuda_kernels/paged_attention/paged_attention_autograd.py
neuralops/core/cuda_kernels/paged_attention/paged_attention_binding.cpp
neuralops/core/cuda_kernels/paged_kv_cache/__init__.py
neuralops/core/cuda_kernels/paged_kv_cache/kv_cache_autograd.py
neuralops/core/cuda_kernels/paged_kv_cache/kv_cache_binding.cpp
neuralops/core/cuda_kernels/paged_kv_cache/kv_cache_copy.cu
neuralops/core/cuda_kernels/paged_kv_cache/paged_kv_cache.cuh
neuralops/core/cuda_kernels/paged_kv_evict/__init__.py
neuralops/core/cuda_kernels/paged_kv_evict/paged_kv_evict.cu
neuralops/core/cuda_kernels/paged_kv_evict/paged_kv_evict_autograd.py
neuralops/core/cuda_kernels/paged_kv_evict/paged_kv_evict_binding.cpp
neuralops/core/cuda_kernels/paged_recurrent_step/__init__.py
neuralops/core/cuda_kernels/paged_recurrent_step/paged_recurrent_step.cu
neuralops/core/cuda_kernels/paged_recurrent_step/paged_recurrent_step_autograd.py
neuralops/core/cuda_kernels/paged_recurrent_step/paged_recurrent_step_binding.cpp
neuralops/core/cuda_kernels/phantom/__init__.py
neuralops/core/cuda_kernels/phantom/phantom.cu
neuralops/core/cuda_kernels/phantom/phantom_autograd.py
neuralops/core/cuda_kernels/phantom/phantom_binding.cpp
neuralops/core/cuda_kernels/quantized_gemm/__init__.py
neuralops/core/cuda_kernels/quantized_gemm/fp8_gemm.cu
neuralops/core/cuda_kernels/quantized_gemm/quant_autograd.py
neuralops/core/cuda_kernels/quantized_gemm/quant_binding.cpp
neuralops/core/cuda_kernels/quantized_gemm/quant_gemm.cuh
neuralops/core/cuda_kernels/quantized_gemm/w4a16_gemm.cu
neuralops/core/cuda_kernels/recurrent_gla_step/__init__.py
neuralops/core/cuda_kernels/recurrent_gla_step/gla_step_autograd.py
neuralops/core/cuda_kernels/recurrent_gla_step/gla_step_binding.cpp
neuralops/core/cuda_kernels/recurrent_gla_step/recurrent_gla_step.cu
neuralops/core/cuda_kernels/recurrent_hgrn2_step/__init__.py
neuralops/core/cuda_kernels/recurrent_hgrn2_step/hgrn2_step_autograd.py
neuralops/core/cuda_kernels/recurrent_hgrn2_step/hgrn2_step_binding.cpp
neuralops/core/cuda_kernels/recurrent_hgrn2_step/recurrent_hgrn2_step.cu
neuralops/core/cuda_kernels/reformer/__init__.py
neuralops/core/cuda_kernels/reformer/reformer.cu
neuralops/core/cuda_kernels/reformer/reformer_autograd.py
neuralops/core/cuda_kernels/reformer/reformer_binding.cpp
neuralops/core/cuda_kernels/rfa_attention/__init__.py
neuralops/core/cuda_kernels/rfa_attention/rfa_attention.cu
neuralops/core/cuda_kernels/rfa_attention/rfa_attention_autograd.py
neuralops/core/cuda_kernels/rfa_attention/rfa_attention_binding.cpp
neuralops/core/cuda_kernels/rms_variance_match/__init__.py
neuralops/core/cuda_kernels/rms_variance_match/rms_variance_match.cu
neuralops/core/cuda_kernels/rms_variance_match/rms_variance_match_autograd.py
neuralops/core/cuda_kernels/rms_variance_match/rms_variance_match_binding.cpp
neuralops/core/cuda_kernels/rmsnorm/__init__.py
neuralops/core/cuda_kernels/rmsnorm/rmsnorm.cu
neuralops/core/cuda_kernels/rmsnorm/rmsnorm_autograd.py
neuralops/core/cuda_kernels/rmsnorm/rmsnorm_binding.cpp
neuralops/core/cuda_kernels/rotational_svd/__init__.py
neuralops/core/cuda_kernels/rotational_svd/rotational_svd.cu
neuralops/core/cuda_kernels/rotational_svd/rotational_svd_autograd.py
neuralops/core/cuda_kernels/rotational_svd/rotational_svd_binding.cpp
neuralops/core/cuda_kernels/routing_attention/__init__.py
neuralops/core/cuda_kernels/routing_attention/routing_attention.cu
neuralops/core/cuda_kernels/routing_attention/routing_attention_autograd.py
neuralops/core/cuda_kernels/routing_attention/routing_attention_binding.cpp
neuralops/core/cuda_kernels/rpca_sparse_svd/__init__.py
neuralops/core/cuda_kernels/rpca_sparse_svd/rpca_sparse_svd.cu
neuralops/core/cuda_kernels/rpca_sparse_svd/rpca_sparse_svd_autograd.py
neuralops/core/cuda_kernels/rpca_sparse_svd/rpca_sparse_svd_binding.cpp
neuralops/core/cuda_kernels/rwkv6/__init__.py
neuralops/core/cuda_kernels/rwkv6/rwkv6.cu
neuralops/core/cuda_kernels/rwkv6/rwkv6_autograd.py
neuralops/core/cuda_kernels/rwkv6/rwkv6_binding.cpp
neuralops/core/cuda_kernels/samba_m3/__init__.py
neuralops/core/cuda_kernels/samba_m3/samba_m3.cu
neuralops/core/cuda_kernels/samba_m3/samba_m3_autograd.py
neuralops/core/cuda_kernels/samba_m3/samba_m3_binding.cpp
neuralops/core/cuda_kernels/samba_moe/__init__.py
neuralops/core/cuda_kernels/samba_moe/samba_moe.cu
neuralops/core/cuda_kernels/samba_moe/samba_moe_autograd.py
neuralops/core/cuda_kernels/samba_moe/samba_moe_binding.cpp
neuralops/core/cuda_kernels/selective_scan/__init__.py
neuralops/core/cuda_kernels/selective_scan/selective_scan.cu
neuralops/core/cuda_kernels/selective_scan/selective_scan.cuh
neuralops/core/cuda_kernels/selective_scan/selective_scan_autograd.py
neuralops/core/cuda_kernels/selective_scan/selective_scan_binding.cpp
neuralops/core/cuda_kernels/selective_ssm/__init__.py
neuralops/core/cuda_kernels/selective_ssm/selective_ssm.cu
neuralops/core/cuda_kernels/selective_ssm/selective_ssm_autograd.py
neuralops/core/cuda_kernels/selective_ssm/selective_ssm_binding.cpp
neuralops/core/cuda_kernels/simple_ssm/__init__.py
neuralops/core/cuda_kernels/simple_ssm/simple_ssm.cu
neuralops/core/cuda_kernels/simple_ssm/simple_ssm_autograd.py
neuralops/core/cuda_kernels/simple_ssm/simple_ssm_binding.cpp
neuralops/core/cuda_kernels/sliding_window/__init__.py
neuralops/core/cuda_kernels/sliding_window/sliding_autograd.py
neuralops/core/cuda_kernels/sliding_window/sliding_binding.cpp
neuralops/core/cuda_kernels/sliding_window/sliding_window.cu
neuralops/core/cuda_kernels/sliding_window/sliding_window.cuh
neuralops/core/cuda_kernels/soa_attn/__init__.py
neuralops/core/cuda_kernels/soa_attn/soa_attn.cu
neuralops/core/cuda_kernels/soa_attn/soa_attn_autograd.py
neuralops/core/cuda_kernels/soa_attn/soa_attn_binding.cpp
neuralops/core/cuda_kernels/softplus/__init__.py
neuralops/core/cuda_kernels/softplus/softplus.cu
neuralops/core/cuda_kernels/softplus/softplus_autograd.py
neuralops/core/cuda_kernels/softplus/softplus_binding.cpp
neuralops/core/cuda_kernels/sparse_attention/__init__.py
neuralops/core/cuda_kernels/sparse_attention/block_sparse_attn.cu
neuralops/core/cuda_kernels/sparse_attention/sparse_attention.cu
neuralops/core/cuda_kernels/sparse_attention/sparse_attention.cuh
neuralops/core/cuda_kernels/sparse_attention/sparse_attention_autograd.py
neuralops/core/cuda_kernels/sparse_attention/sparse_attention_binding.cpp
neuralops/core/cuda_kernels/sparse_attention/sparse_autograd.py
neuralops/core/cuda_kernels/sparse_attention/sparse_binding.cpp
neuralops/core/cuda_kernels/spectra_v2/__init__.py
neuralops/core/cuda_kernels/spectra_v2/spectra_v2.cu
neuralops/core/cuda_kernels/spectra_v2/spectra_v2_autograd.py
neuralops/core/cuda_kernels/spectra_v2/spectra_v2_binding.cpp
neuralops/core/cuda_kernels/spectraformer_attention/__init__.py
neuralops/core/cuda_kernels/spectraformer_attention/spectraformer_attention.cu
neuralops/core/cuda_kernels/spectraformer_attention/spectraformer_attention_autograd.py
neuralops/core/cuda_kernels/spectraformer_attention/spectraformer_attention_binding.cpp
neuralops/core/cuda_kernels/spectral_mamba/__init__.py
neuralops/core/cuda_kernels/spectral_mamba/spectral_mamba.cu
neuralops/core/cuda_kernels/spectral_mamba/spectral_mamba_autograd.py
neuralops/core/cuda_kernels/spectral_mamba/spectral_mamba_binding.cpp
neuralops/core/cuda_kernels/spectral_shrinkage/__init__.py
neuralops/core/cuda_kernels/spectral_shrinkage/spectral_shrinkage.cu
neuralops/core/cuda_kernels/spectral_shrinkage/spectral_shrinkage_autograd.py
neuralops/core/cuda_kernels/spectral_shrinkage/spectral_shrinkage_binding.cpp
neuralops/core/cuda_kernels/speculative_verify/__init__.py
neuralops/core/cuda_kernels/speculative_verify/spec_autograd.py
neuralops/core/cuda_kernels/speculative_verify/spec_binding.cpp
neuralops/core/cuda_kernels/speculative_verify/speculative_verify.cu
neuralops/core/cuda_kernels/split_head_norm/__init__.py
neuralops/core/cuda_kernels/split_head_norm/split_head_norm.cu
neuralops/core/cuda_kernels/split_head_norm/split_head_norm_autograd.py
neuralops/core/cuda_kernels/split_head_norm/split_head_norm_binding.cpp
neuralops/core/cuda_kernels/state_update/__init__.py
neuralops/core/cuda_kernels/state_update/state_autograd.py
neuralops/core/cuda_kernels/state_update/state_binding.cpp
neuralops/core/cuda_kernels/state_update/state_update.cu
neuralops/core/cuda_kernels/svd_prefix_scan/__init__.py
neuralops/core/cuda_kernels/svd_prefix_scan/svd_prefix_scan.cu
neuralops/core/cuda_kernels/svd_prefix_scan/svd_prefix_scan_autograd.py
neuralops/core/cuda_kernels/svd_prefix_scan/svd_prefix_scan_binding.cpp
neuralops/core/cuda_kernels/swiglu/__init__.py
neuralops/core/cuda_kernels/swiglu/swiglu.cu
neuralops/core/cuda_kernels/swiglu/swiglu_autograd.py
neuralops/core/cuda_kernels/swiglu/swiglu_binding.cpp
neuralops/core/cuda_kernels/ternary_gemm/__init__.py
neuralops/core/cuda_kernels/ternary_gemm/ternary_autograd.py
neuralops/core/cuda_kernels/ternary_gemm/ternary_binding.cpp
neuralops/core/cuda_kernels/ternary_gemm/ternary_gemm.cu
neuralops/core/cuda_kernels/tpa_attention/__init__.py
neuralops/core/cuda_kernels/tpa_attention/tpa_attention.cu
neuralops/core/cuda_kernels/tpa_attention/tpa_attention_autograd.py
neuralops/core/cuda_kernels/tpa_attention/tpa_attention_binding.cpp
neuralops/core/cuda_kernels/tt_contraction/__init__.py
neuralops/core/cuda_kernels/tt_contraction/tt_autograd.py
neuralops/core/cuda_kernels/tt_contraction/tt_binding.cpp
neuralops/core/cuda_kernels/tt_contraction/tt_contraction.cu
neuralops/core/cuda_kernels/unified_rope_offset/__init__.py
neuralops/core/cuda_kernels/unified_rope_offset/unified_rope_offset.cu
neuralops/core/cuda_kernels/unified_rope_offset/unified_rope_offset_autograd.py
neuralops/core/cuda_kernels/unified_rope_offset/unified_rope_offset_binding.cpp
neuralops/core/cuda_kernels/upi_stuffed_mamba/__init__.py
neuralops/core/cuda_kernels/upi_stuffed_mamba/upi_stuffed_mamba.cu
neuralops/core/cuda_kernels/upi_stuffed_mamba/upi_stuffed_mamba_autograd.py
neuralops/core/cuda_kernels/upi_stuffed_mamba/upi_stuffed_mamba_binding.cpp
neuralops/core/cuda_kernels/varlen_attention/__init__.py
neuralops/core/cuda_kernels/varlen_attention/varlen_attention.cu
neuralops/core/cuda_kernels/varlen_attention/varlen_autograd.py
neuralops/core/cuda_kernels/varlen_attention/varlen_binding.cpp
neuralops/core/cuda_kernels/vspec/__init__.py
neuralops/core/cuda_kernels/vspec/vspec.cu
neuralops/core/cuda_kernels/vspec/vspec_autograd.py
neuralops/core/cuda_kernels/vspec/vspec_binding.cpp
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/triton_kernels/__init__.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/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/__init__.py
neuralops/data/base.py
neuralops/distributed/__init__.py
neuralops/distributed/context_parallel.py
neuralops/distributed/tensor_parallel.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/serving.py
neuralops/export/surgery_manifest.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/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/kernels/__init__.py
neuralops/kernels/extended_kernels.py
neuralops/kernels/cuda/__init__.py
neuralops/kernels/triton/__init__.py
neuralops/kernels/triton/block_sparse_streaming_attn.py
neuralops/kernels/triton/chunked_delta_gate_scan.py
neuralops/kernels/triton/cosformer_linear_attention.py
neuralops/kernels/triton/fused_act_scale_quant_gemm.py
neuralops/kernels/triton/fused_hadamard_w4a16_gemm.py
neuralops/kernels/triton/fused_kronecker_matmul.py
neuralops/kernels/triton/fused_latent_kv_cache_attention.py
neuralops/kernels/triton/fused_lowrank_gemm.py
neuralops/kernels/triton/hgrn2_fused_bwd_scan.py
neuralops/kernels/triton/hybrid_local_kernel_triton.py
neuralops/kernels/triton/lut_codebook_dequant_gemm.py
neuralops/kernels/triton/rpca_sparse_gemm.py
neuralops/kernels/triton/spectral_entropy_svd_gate.py
neuralops/kernels/triton/strided_tt.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/monitor/__init__.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/surgery/__init__.py
neuralops/surgery/endoskeletal_shell.py
neuralops/surgery/hf_cache_bridge.py
neuralops/surgery/param_recovery.py
neuralops/surgery/scanner.py
neuralops/surgery/shadow_twin.py
neuralops/surgery/surgery_manifest.py
neuralops/surgery/surgical_io.py
neuralops/surgery/topology_router.py
neuralops/surgery/universal_calibrator.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/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/losses.py
neuralops/trainer/metrics.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/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/training/checkpointing.py
neuralops/training/layer_distill.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/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/data_validator.py
neuralops/validation/memory_validator.py
neuralops/validation/model_validator.py
neuralops/validation/numerical_validator.py
neuralops/validation/report_generator.py
neuralops/validation/speed_validator.py
neuralops/validation/training_validator.py