{"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/radar-fast-long-context-decoding-for-any","title":"Radar: Fast Long-Context Decoding for Any Transformer","arxiv_id":"2503.10571","date":"2025-03-13","proceeding":null,"authors":["Yongchang Hao","Mengyao Zhai","Hossein Hajimirsadeghi","Sepidehsadat Hosseini","Frederick Tung"],"abstract":"Transformer models have demonstrated exceptional performance across a wide range of applications. Though forming the foundation of Transformer models, the dot-product attention does not scale well to long-context data since its time requirement grows quadratically with context length. In this work, we propose Radar, a training-free approach that accelerates inference by dynamically searching for the most important context tokens. For any pre-trained Transformer, Radar can reduce the decoding time complexity without training or heuristically evicting tokens. Moreover, we provide theoretical justification for our approach, demonstrating that Radar can reliably identify the most important tokens with high probability. We conduct extensive comparisons with the previous methods on a wide range of tasks. The results demonstrate that Radar achieves the state-of-the-art performance across different architectures with reduced time complexity, offering a practical solution for efficient long-context processing of Transformers.","url_abs":"https://arxiv.org/abs/2503.10571v1","url_pdf":"https://arxiv.org/pdf/2503.10571v1.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":"radar-fast-long-context-decoding-for-any","repo_url":"https://github.com/BorealisAI/radar-decoding","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"LGPL-3.0"}}],"tasks":[],"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":"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":{"atlas_url":"https://app.syntology.ai/?focus=2503.10571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10571"}},"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/BorealisAI/radar-decoding","reach":{"status":"ok","spdx":"LGPL-3.0"}}],"summary":{"ran_honours":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"b349b79d9cc2934b","entry":"count_score","repo":"borealisai/radar-decoding","repo_kind":"official","path":"research/longbench/longbench.py","file_url":"https://github.com/borealisai/radar-decoding/blob/HEAD/research/longbench/longbench.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"LGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b349b79d9cc2934b"}},{"code_sha256_prefix":"e7e75981cb464788","entry":"normalize_answer","repo":"borealisai/radar-decoding","repo_kind":"official","path":"research/longbench/longbench.py","file_url":"https://github.com/borealisai/radar-decoding/blob/HEAD/research/longbench/longbench.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":"LGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e7e75981cb464788"}},{"code_sha256_prefix":"8c5c581f9264c810","entry":"normalize_zh_answer","repo":"borealisai/radar-decoding","repo_kind":"official","path":"research/longbench/longbench.py","file_url":"https://github.com/borealisai/radar-decoding/blob/HEAD/research/longbench/longbench.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":"LGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"8c5c581f9264c810"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}