{"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/flash-attention-forward","entry":"flash_attention_forward","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":14,"n_papers_ran":0,"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":7,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":7},"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":"2605.07465","paper":"/paper/arxiv-2605-07465","title":"SEIF: Self-Evolving Reinforcement Learning for Instruction Following","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Rainier-rq1/SEIF","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/Rainier-rq1/SEIF/blob/HEAD/verl/models/transformers/flash_attention_utils.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":"d71e909038b965a1","mcp_get_code":{"code_sha256":"d71e909038b965a1"}},{"arxiv_id":"2604.13556","paper":"/paper/arxiv-2604-13556","title":"YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"wuyou2002/YOCO-plus","path":"models/utils.py","file_url":"https://github.com/wuyou2002/YOCO-plus/blob/HEAD/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"92eac4dd828162e7","mcp_get_code":{"code_sha256":"92eac4dd828162e7"}},{"arxiv_id":"2603.02635","paper":"/paper/arxiv-2603-02635","title":"SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal Safety","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"hiyouga/EasyR1","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/hiyouga/EasyR1/blob/HEAD/verl/models/transformers/flash_attention_utils.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":"7688ceba543fa185","mcp_get_code":{"code_sha256":"7688ceba543fa185"}},{"arxiv_id":"2602.12735","paper":"/paper/arxiv-2602-12735","title":"VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Alibaba-NLP/VRAG","path":"VRAG-RL/verl/models/transformers/qwen2_vl.py","file_url":"https://github.com/Alibaba-NLP/VRAG/blob/HEAD/VRAG-RL/verl/models/transformers/qwen2_vl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"736144d442549c26","mcp_get_code":{"code_sha256":"736144d442549c26"}},{"arxiv_id":"2601.05167","paper":"/paper/arxiv-2601-05167","title":"RelayLLM: Efficient Reasoning via Collaborative Decoding","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Chengsong-Huang/RelayLLM","path":"RL_stage/verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/Chengsong-Huang/RelayLLM/blob/HEAD/RL_stage/verl/models/transformers/flash_attention_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"81c1dcce890376c5","mcp_get_code":{"code_sha256":"81c1dcce890376c5"}},{"arxiv_id":"2507.07966","paper":"/paper/scaling-rl-to-long-videos","title":"Scaling RL to Long Videos","date":"2025-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/Long-RL","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/NVlabs/Long-RL/blob/HEAD/verl/models/transformers/flash_attention_utils.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":"2058875a75c3ff14","mcp_get_code":{"code_sha256":"2058875a75c3ff14"}},{"arxiv_id":"2507.05386","paper":"/paper/reinforcement-fine-tuning-naturally-mitigates","title":"Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training","date":"2025-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhhvvv/rft_vs_sft","path":"EasyR1/verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/zhhvvv/rft_vs_sft/blob/HEAD/EasyR1/verl/models/transformers/flash_attention_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d71e909038b965a1","mcp_get_code":{"code_sha256":"d71e909038b965a1"}},{"arxiv_id":"2506.01908","paper":"/paper/reinforcement-learning-tuning-for-videollms","title":"Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency","date":"2025-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"appletea233/temporal-r1","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/appletea233/temporal-r1/blob/HEAD/verl/models/transformers/flash_attention_utils.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":"75ed715f4ad2c9ee","mcp_get_code":{"code_sha256":"75ed715f4ad2c9ee"}},{"arxiv_id":"2505.16282","paper":"/paper/arpo-end-to-end-policy-optimization-for-gui","title":"ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/arpo","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/dvlab-research/arpo/blob/HEAD/verl/models/transformers/flash_attention_utils.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":"d71e909038b965a1","mcp_get_code":{"code_sha256":"d71e909038b965a1"}},{"arxiv_id":"2504.05520","paper":"/paper/efficient-reinforcement-finetuning-via","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","date":"2025-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uscnlp-lime/verl","path":"verl/models/transformers/qwen2_vl.py","file_url":"https://github.com/uscnlp-lime/verl/blob/HEAD/verl/models/transformers/qwen2_vl.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":"736144d442549c26","mcp_get_code":{"code_sha256":"736144d442549c26"}},{"arxiv_id":"2503.17352","paper":"/paper/openvlthinker-an-early-exploration-to-complex","title":"OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement","date":"2025-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihedeng9/openvlthinker","path":"EasyR1/verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/yihedeng9/openvlthinker/blob/HEAD/EasyR1/verl/models/transformers/flash_attention_utils.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":"7688ceba543fa185","mcp_get_code":{"code_sha256":"7688ceba543fa185"}},{"arxiv_id":"2502.19613","paper":"/paper/self-rewarding-correction-for-mathematical","title":"Self-rewarding correction for mathematical reasoning","date":"2025-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agentica-project/verl-pipeline","path":"verl/models/transformers/qwen2_vl.py","file_url":"https://github.com/agentica-project/verl-pipeline/blob/HEAD/verl/models/transformers/qwen2_vl.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":"736144d442549c26","mcp_get_code":{"code_sha256":"736144d442549c26"}},{"arxiv_id":"2410.14442","paper":"/paper/a-systematic-study-of-cross-layer-kv-sharing","title":"A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"whyNLP/LCKV","path":"models/utils.py","file_url":"https://github.com/whyNLP/LCKV/blob/HEAD/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"92eac4dd828162e7","mcp_get_code":{"code_sha256":"92eac4dd828162e7"}},{"arxiv_id":"openreview_Y1PXB8HBV7","paper":null,"title":"arXiv:openreview_Y1PXB8HBV7","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"youwyouw/mirl-main","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/youwyouw/mirl-main/blob/HEAD/verl/models/transformers/flash_attention_utils.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":"7688ceba543fa185","mcp_get_code":{"code_sha256":"7688ceba543fa185"}}]}