{"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":"/code/apply-rotary-emb-torch","entry":"apply_rotary_emb_torch","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":8,"n_papers_ran":5,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":3,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":2},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2605.15422","paper":"/paper/arxiv-2605-15422","title":"DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"amazon-science/dualkv-flash-attn-for-rl","path":"flash-attention/flash_attn/layers/rotary.py","file_url":"https://github.com/amazon-science/dualkv-flash-attn-for-rl/blob/HEAD/flash-attention/flash_attn/layers/rotary.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"5ec949977c334f87","mcp_get_code":{"code_sha256":"5ec949977c334f87"}},{"arxiv_id":"2604.23798","paper":"/paper/arxiv-2604-23798","title":"ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Dao-AILab/flash-attention","path":"flash_attn/layers/rotary.py","file_url":"https://github.com/Dao-AILab/flash-attention/blob/HEAD/flash_attn/layers/rotary.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"5ec949977c334f87","mcp_get_code":{"code_sha256":"5ec949977c334f87"}},{"arxiv_id":"2604.07394","paper":"/paper/arxiv-2604-07394","title":"Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"qqtang-code/FluxAttention","path":"fluxattn/training/modeling_flash_qwen.py","file_url":"https://github.com/qqtang-code/FluxAttention/blob/HEAD/fluxattn/training/modeling_flash_qwen.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2ed34e7143f94ce9","mcp_get_code":{"code_sha256":"2ed34e7143f94ce9"}},{"arxiv_id":"2601.17367","paper":"/paper/arxiv-2601-17367","title":"Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"LCM-Lab/Elastic-Attention","path":"elasticattn/training/modeling_flash_qwen.py","file_url":"https://github.com/LCM-Lab/Elastic-Attention/blob/HEAD/elasticattn/training/modeling_flash_qwen.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2ed34e7143f94ce9","mcp_get_code":{"code_sha256":"2ed34e7143f94ce9"}},{"arxiv_id":"2511.10056","paper":"/paper/arxiv-2511-10056","title":"From Static Structures to Ensembles: Studying and Harnessing Protein Structure Tokenization","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"IDEA-XL/TokenMD","path":"esm/layers/rotary.py","file_url":"https://github.com/IDEA-XL/TokenMD/blob/HEAD/esm/layers/rotary.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bddcd125505ea666","mcp_get_code":{"code_sha256":"bddcd125505ea666"}},{"arxiv_id":"2412.06464","paper":"/paper/gated-delta-networks-improving-mamba2-with","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","date":"2024-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/GatedDeltaNet","path":"lit_gpt/rotary.py","file_url":"https://github.com/NVlabs/GatedDeltaNet/blob/HEAD/lit_gpt/rotary.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5ec949977c334f87","mcp_get_code":{"code_sha256":"5ec949977c334f87"}},{"arxiv_id":"2407.08608","paper":"/paper/flashattention-3-fast-and-accurate-attention","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","date":"2024-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dao-ailab/flash-attention","path":"flash_attn/layers/rotary.py","file_url":"https://github.com/dao-ailab/flash-attention/blob/HEAD/flash_attn/layers/rotary.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"5ec949977c334f87","mcp_get_code":{"code_sha256":"5ec949977c334f87"}},{"arxiv_id":"2309.06180","paper":"/paper/2309-06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","date":"2023-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ROCm/flash-attention","path":"flash_attn/layers/rotary.py","file_url":"https://github.com/ROCm/flash-attention/blob/HEAD/flash_attn/layers/rotary.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"5ec949977c334f87","mcp_get_code":{"code_sha256":"5ec949977c334f87"}}]}