{"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/longrecipe-recipe-for-efficient-long-context","title":"LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models","arxiv_id":"2409.00509","date":"2024-08-31","proceeding":null,"authors":["Zhiyuan Hu","Yuliang Liu","Jinman Zhao","Suyuchen Wang","Yan Wang","Wei Shen","Qing Gu","Anh Tuan Luu","See-Kiong Ng","Zhiwei Jiang","Bryan Hooi"],"abstract":"Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences. Meanwhile, extending the context window in LLMs through post-pretraining is highly resource-intensive. To address this, we introduce LongRecipe, an efficient training strategy for extending the context window of LLMs, including impactful token analysis, position index transformation, and training optimization strategies. It simulates long-sequence inputs while maintaining training efficiency and significantly improves the model's understanding of long-range dependencies. Experiments on three types of LLMs show that LongRecipe can utilize long sequences while requiring only 30% of the target context window size, and reduces computational training resource over 85% compared to full sequence training. Furthermore, LongRecipe also preserves the original LLM's capabilities in general tasks. Ultimately, we can extend the effective context window of open-source LLMs from 8k to 128k, achieving performance close to GPT-4 with just one day of dedicated training using a single GPU with 80G memory. Our code is released at https://github.com/zhiyuanhubj/LongRecipe.","url_abs":"https://arxiv.org/abs/2409.00509v2","url_pdf":"https://arxiv.org/pdf/2409.00509v2.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":"longrecipe-recipe-for-efficient-long-context","repo_url":"https://github.com/zhiyuanhubj/LongRecipe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"8k"},{"task_slug":null,"task_name":"GPU"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2409.00509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.00509"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhiyuanhubj/LongRecipe","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"ce7333f42d88b05d","entry":"maybe_get_set_global_memory_buffer","repo":"zhiyuanhubj/LongRecipe","repo_kind":"official","path":"utils/easy_context/dist_flash_attn/async_communication.py","file_url":"https://github.com/zhiyuanhubj/LongRecipe/blob/HEAD/utils/easy_context/dist_flash_attn/async_communication.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ce7333f42d88b05d"}},{"code_sha256_prefix":"ee03eab03d798c57","entry":"maybe_get_set_global_memory_buffer_bwd","repo":"zhiyuanhubj/LongRecipe","repo_kind":"official","path":"utils/easy_context/dist_flash_attn/async_communication.py","file_url":"https://github.com/zhiyuanhubj/LongRecipe/blob/HEAD/utils/easy_context/dist_flash_attn/async_communication.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ee03eab03d798c57"}},{"code_sha256_prefix":"5785cb16b92ebd18","entry":"process_data_single","repo":"zhiyuanhubj/LongRecipe","repo_kind":"official","path":"preprocess_token_PI/dataprocessor.py","file_url":"https://github.com/zhiyuanhubj/LongRecipe/blob/HEAD/preprocess_token_PI/dataprocessor.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5785cb16b92ebd18"}},{"code_sha256_prefix":"4be6bef6c83e9c27","entry":"is_last_time","repo":"zhiyuanhubj/LongRecipe","repo_kind":"official","path":"utils/easy_context/dist_flash_attn/async_communication.py","file_url":"https://github.com/zhiyuanhubj/LongRecipe/blob/HEAD/utils/easy_context/dist_flash_attn/async_communication.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4be6bef6c83e9c27"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}