{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/flashattention-fast-and-memory-efficient","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","arxiv_id":"2205.14135","date":"2022-05-27","proceeding":null,"authors":["Tri Dao","Daniel Y. Fu","Stefano Ermon","Atri Rudra","Christopher Ré"],"abstract":"Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by trading off model quality to reduce the compute complexity, but often do not achieve wall-clock speedup. We argue that a missing principle is making attention algorithms IO-aware -- accounting for reads and writes between levels of GPU memory. We propose FlashAttention, an IO-aware exact attention algorithm that uses tiling to reduce the number of memory reads/writes between GPU high bandwidth memory (HBM) and GPU on-chip SRAM. We analyze the IO complexity of FlashAttention, showing that it requires fewer HBM accesses than standard attention, and is optimal for a range of SRAM sizes. We also extend FlashAttention to block-sparse attention, yielding an approximate attention algorithm that is faster than any existing approximate attention method. FlashAttention trains Transformers faster than existing baselines: 15% end-to-end wall-clock speedup on BERT-large (seq. length 512) compared to the MLPerf 1.1 training speed record, 3$\\times$ speedup on GPT-2 (seq. length 1K), and 2.4$\\times$ speedup on long-range arena (seq. length 1K-4K). FlashAttention and block-sparse FlashAttention enable longer context in Transformers, yielding higher quality models (0.7 better perplexity on GPT-2 and 6.4 points of lift on long-document classification) and entirely new capabilities: the first Transformers to achieve better-than-chance performance on the Path-X challenge (seq. length 16K, 61.4% accuracy) and Path-256 (seq. length 64K, 63.1% accuracy).","url_abs":"https://arxiv.org/abs/2205.14135v2","url_pdf":"https://arxiv.org/pdf/2205.14135v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/dao-ailab/flash-attention","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/hazyresearch/flash-attention","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/ROCm/flash-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/alibaba/megatron-llama","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/answerdotai/modernbert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/csguoh/fastvar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/latkins/trifast","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/lucidrains/block-recurrent-transformer-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/lucidrains/flash-cosine-sim-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/microsoft/chunk-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/softmax1/flash-attention-softmax-n","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/facebookresearch/xformers/blob/main/xformers/ops/fmha/flash.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"flashattention-fast-and-memory-efficient","repo_url":"https://github.com/pytorch/pytorch/blob/main/torch/nn/functional.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"16k","task_name":"16k"},{"task_slug":"4k","task_name":"4k"},{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"grouped-query-attention","method_name":"Grouped-query attention"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"multi-query-attention","method_name":"Multi-Query Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"rope","method_name":"Rotary Embeddings"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.14135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14135"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/NVIDIA/apex","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/csguoh/fastvar","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/flash-cosine-sim-attention","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/softmax1/flash-attention-softmax-n","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/xformers/blob/main/xformers/ops/fmha/flash.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/latkins/trifast","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dao-ailab/flash-attention","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pytorch/pytorch/blob/main/torch/nn/functional.py","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/google-research/long-range-arena","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ROCm/flash-attention","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hazyresearch/flash-attention","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/block-recurrent-transformer-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/chunk-attention","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/answerdotai/modernbert","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba/megatron-llama","reach":null}],"summary":{"ran":2,"ran_violates":1,"ran_fixture":1,"ran_draft_wrong":5,"unverified":21},"by_repo_kind":{"listed":{"samples":21,"ran":9,"repositories":4},"found_in_text":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"836e169269626b2d","entry":"FlashCosineSimAttention","repo":"lucidrains/flash-cosine-sim-attention","repo_kind":"listed","path":"flash_cosine_sim_attention/flash_cosine_sim_attention.py","file_url":"https://github.com/lucidrains/flash-cosine-sim-attention/blob/HEAD/flash_cosine_sim_attention/flash_cosine_sim_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"836e169269626b2d"}},{"code_sha256_prefix":"3a48757821245a9c","entry":"FlashSelfAttention","repo":"alibaba/megatron-llama","repo_kind":"listed","path":"megatron/model/transformer.py","file_url":"https://github.com/alibaba/megatron-llama/blob/HEAD/megatron/model/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3a48757821245a9c"}},{"code_sha256_prefix":"5e1eae834b42ab87","entry":"and_reduce","repo":"lucidrains/block-recurrent-transformer-pytorch","repo_kind":"listed","path":"block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","file_url":"https://github.com/lucidrains/block-recurrent-transformer-pytorch/blob/HEAD/block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5e1eae834b42ab87"}},{"code_sha256_prefix":"445b382660c20892","entry":"flash_cosine_sim_attention","repo":"lucidrains/flash-cosine-sim-attention","repo_kind":"listed","path":"flash_cosine_sim_attention/flash_cosine_sim_attention.py","file_url":"https://github.com/lucidrains/flash-cosine-sim-attention/blob/HEAD/flash_cosine_sim_attention/flash_cosine_sim_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"445b382660c20892"}},{"code_sha256_prefix":"bf71ddb7b6318152","entry":"grouped_l2norm","repo":"lucidrains/flash-cosine-sim-attention","repo_kind":"listed","path":"flash_cosine_sim_attention/flash_cosine_sim_attention.py","file_url":"https://github.com/lucidrains/flash-cosine-sim-attention/blob/HEAD/flash_cosine_sim_attention/flash_cosine_sim_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf71ddb7b6318152"}},{"code_sha256_prefix":"ebc7297040578822","entry":"l2norm","repo":"lucidrains/flash-cosine-sim-attention","repo_kind":"listed","path":"flash_cosine_sim_attention/flash_cosine_sim_attention.py","file_url":"https://github.com/lucidrains/flash-cosine-sim-attention/blob/HEAD/flash_cosine_sim_attention/flash_cosine_sim_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ebc7297040578822"}},{"code_sha256_prefix":"ccb62a80e7c1e0af","entry":"l2norm_cpu","repo":"lucidrains/flash-cosine-sim-attention","repo_kind":"listed","path":"flash_cosine_sim_attention/flash_cosine_sim_attention.py","file_url":"https://github.com/lucidrains/flash-cosine-sim-attention/blob/HEAD/flash_cosine_sim_attention/flash_cosine_sim_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ccb62a80e7c1e0af"}},{"code_sha256_prefix":"2ae574072ec6f776","entry":"once","repo":"lucidrains/block-recurrent-transformer-pytorch","repo_kind":"listed","path":"block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","file_url":"https://github.com/lucidrains/block-recurrent-transformer-pytorch/blob/HEAD/block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ae574072ec6f776"}},{"code_sha256_prefix":"a0902e24bf5299e7","entry":"unpack_one","repo":"lucidrains/block-recurrent-transformer-pytorch","repo_kind":"listed","path":"block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","file_url":"https://github.com/lucidrains/block-recurrent-transformer-pytorch/blob/HEAD/block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0902e24bf5299e7"}},{"code_sha256_prefix":"a91304b317adcfe6","entry":"Attend","repo":"lucidrains/block-recurrent-transformer-pytorch","repo_kind":"listed","path":"block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","file_url":"https://github.com/lucidrains/block-recurrent-transformer-pytorch/blob/HEAD/block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a91304b317adcfe6"}},{"code_sha256_prefix":"7ec53192aa7f5504","entry":"attention_reference","repo":"latkins/trifast","repo_kind":"listed","path":"src/trifast/equiv.py","file_url":"https://github.com/latkins/trifast/blob/HEAD/src/trifast/equiv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7ec53192aa7f5504"}},{"code_sha256_prefix":"e370fc6ece6221ed","entry":"create_band_mask_from_inputs","repo":"google-research/long-range-arena","repo_kind":"found_in_text","path":"lra_benchmarks/models/bigbird/bigbird_attention.py","file_url":"https://github.com/google-research/long-range-arena/blob/HEAD/lra_benchmarks/models/bigbird/bigbird_attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e370fc6ece6221ed"}},{"code_sha256_prefix":"5aedb376f0772dfe","entry":"create_rand_mask_from_inputs","repo":"google-research/long-range-arena","repo_kind":"found_in_text","path":"lra_benchmarks/models/bigbird/bigbird_attention.py","file_url":"https://github.com/google-research/long-range-arena/blob/HEAD/lra_benchmarks/models/bigbird/bigbird_attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5aedb376f0772dfe"}},{"code_sha256_prefix":"e70a5be792d21381","entry":"disable_tf32","repo":"latkins/trifast","repo_kind":"listed","path":"src/trifast/utils.py","file_url":"https://github.com/latkins/trifast/blob/HEAD/src/trifast/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e70a5be792d21381"}},{"code_sha256_prefix":"8c357c18a7a5df9f","entry":"enable_tf32","repo":"latkins/trifast","repo_kind":"listed","path":"src/trifast/utils.py","file_url":"https://github.com/latkins/trifast/blob/HEAD/src/trifast/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c357c18a7a5df9f"}},{"code_sha256_prefix":"69095fe94801bb6a","entry":"flash_cosine_sim_attention_cpu","repo":"lucidrains/flash-cosine-sim-attention","repo_kind":"listed","path":"flash_cosine_sim_attention/flash_cosine_sim_attention.py","file_url":"https://github.com/lucidrains/flash-cosine-sim-attention/blob/HEAD/flash_cosine_sim_attention/flash_cosine_sim_attention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"69095fe94801bb6a"}},{"code_sha256_prefix":"f6a5967228c7a9d2","entry":"gen_tensors","repo":"latkins/trifast","repo_kind":"listed","path":"src/trifast/utils.py","file_url":"https://github.com/latkins/trifast/blob/HEAD/src/trifast/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6a5967228c7a9d2"}},{"code_sha256_prefix":"5e965cd1402c118a","entry":"get_block_rand_mask","repo":"google-research/long-range-arena","repo_kind":"found_in_text","path":"lra_benchmarks/models/bigbird/bigbird_attention.py","file_url":"https://github.com/google-research/long-range-arena/blob/HEAD/lra_benchmarks/models/bigbird/bigbird_attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e965cd1402c118a"}},{"code_sha256_prefix":"0d78a4ebde5b96c9","entry":"get_tsv_dataset","repo":"google-research/long-range-arena","repo_kind":"found_in_text","path":"lra_benchmarks/matching/build_vocab.py","file_url":"https://github.com/google-research/long-range-arena/blob/HEAD/lra_benchmarks/matching/build_vocab.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d78a4ebde5b96c9"}},{"code_sha256_prefix":"64a65eaa8e65ea8c","entry":"get_tsv_dataset","repo":"google-research/long-range-arena","repo_kind":"found_in_text","path":"lra_benchmarks/matching/input_pipeline.py","file_url":"https://github.com/google-research/long-range-arena/blob/HEAD/lra_benchmarks/matching/input_pipeline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"64a65eaa8e65ea8c"}},{"code_sha256_prefix":"518990c8ea44ffc6","entry":"l2norm_tensors","repo":"lucidrains/flash-cosine-sim-attention","repo_kind":"listed","path":"flash_cosine_sim_attention/flash_cosine_sim_attention.py","file_url":"https://github.com/lucidrains/flash-cosine-sim-attention/blob/HEAD/flash_cosine_sim_attention/flash_cosine_sim_attention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"518990c8ea44ffc6"}},{"code_sha256_prefix":"dfce9c8c32b2f721","entry":"neg_inf","repo":"latkins/trifast","repo_kind":"listed","path":"src/trifast/equiv.py","file_url":"https://github.com/latkins/trifast/blob/HEAD/src/trifast/equiv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dfce9c8c32b2f721"}},{"code_sha256_prefix":"86ca4a3f9ab20a35","entry":"pack_one","repo":"lucidrains/block-recurrent-transformer-pytorch","repo_kind":"listed","path":"block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","file_url":"https://github.com/lucidrains/block-recurrent-transformer-pytorch/blob/HEAD/block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"86ca4a3f9ab20a35"}},{"code_sha256_prefix":"405da6c9ec4f68dd","entry":"parse_int_list","repo":"latkins/trifast","repo_kind":"listed","path":"src/trifast/tune.py","file_url":"https://github.com/latkins/trifast/blob/HEAD/src/trifast/tune.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"405da6c9ec4f68dd"}},{"code_sha256_prefix":"59e4e06672a6c268","entry":"preprocess_dataset","repo":"google-research/long-range-arena","repo_kind":"found_in_text","path":"lra_benchmarks/listops/input_pipeline.py","file_url":"https://github.com/google-research/long-range-arena/blob/HEAD/lra_benchmarks/listops/input_pipeline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59e4e06672a6c268"}},{"code_sha256_prefix":"1affbc4020c2fc7b","entry":"rename_close_brackets","repo":"google-research/long-range-arena","repo_kind":"found_in_text","path":"lra_benchmarks/listops/input_pipeline.py","file_url":"https://github.com/google-research/long-range-arena/blob/HEAD/lra_benchmarks/listops/input_pipeline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1affbc4020c2fc7b"}},{"code_sha256_prefix":"60bb0fb77bbdfb3e","entry":"sinusoidal_init","repo":"google-research/long-range-arena","repo_kind":"found_in_text","path":"lra_benchmarks/models/layers/common_layers.py","file_url":"https://github.com/google-research/long-range-arena/blob/HEAD/lra_benchmarks/models/layers/common_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"60bb0fb77bbdfb3e"}},{"code_sha256_prefix":"1b603b0ef7263401","entry":"triangle_attention_simple","repo":"latkins/trifast","repo_kind":"listed","path":"src/trifast/equiv.py","file_url":"https://github.com/latkins/trifast/blob/HEAD/src/trifast/equiv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b603b0ef7263401"}},{"code_sha256_prefix":"7f47b6e7368cff8b","entry":"valid_dtypes","repo":"latkins/trifast","repo_kind":"listed","path":"src/trifast/tune.py","file_url":"https://github.com/latkins/trifast/blob/HEAD/src/trifast/tune.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f47b6e7368cff8b"}},{"code_sha256_prefix":"fbeafd410f521a6f","entry":"whitespace_tokenize","repo":"google-research/long-range-arena","repo_kind":"found_in_text","path":"lra_benchmarks/matching/build_vocab.py","file_url":"https://github.com/google-research/long-range-arena/blob/HEAD/lra_benchmarks/matching/build_vocab.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fbeafd410f521a6f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}