{"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/sam-decoding-speculative-decoding-via-suffix","title":"SAM Decoding: Speculative Decoding via Suffix Automaton","arxiv_id":"2411.10666","date":"2024-11-16","proceeding":null,"authors":["Yuxuan Hu","Ke Wang","Xiaokang Zhang","Fanjin Zhang","Cuiping Li","Hong Chen","Jing Zhang"],"abstract":"Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration. Retrieval-based SD methods, one kind of model-free method, have yielded promising speedup, but they often rely on incomplete retrieval resources, inefficient retrieval methods, and are constrained to certain domains. This paper presents a novel retrieval-based speculative decoding method that adapts suffix automaton (SAM) for efficient and accurate draft generation by utilizing common text corpus and dynamic text sequence. Unlike existing $n$-gram matching methods, SAM-Decoding finds the exact longest suffix match, achieving an average time complexity of O(1) per generation step of SAM update and suffix retrieval. It can also integrate with existing methods, adaptively selecting a draft generation strategy based on match length to generalize to broader domains. Extensive experiments on Spec-Bench show that our method is $18\\%+$ faster than other retrieval-based SD methods. Additionally, when combined with advanced EAGLE-2, it provides an additional speedup of $3.28\\%$ -- $11.13\\%$ across various-sized LLM backbones. Our code is available at our \\href{https://github.com/hyx1999/SAM-Decoding}{repository}.","url_abs":"https://arxiv.org/abs/2411.10666v3","url_pdf":"https://arxiv.org/pdf/2411.10666v3.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":"sam-decoding-speculative-decoding-via-suffix","repo_url":"https://github.com/hyx1999/sam-decoding","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"sam","method_name":"SAM"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.10666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10666"}},"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/hyx1999/sam-decoding","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"4384f1c14a42560d","entry":"load_eagle","repo":"hyx1999/sam-decoding","repo_kind":"official","path":"samd_sam_only/samd_config.py","file_url":"https://github.com/hyx1999/sam-decoding/blob/HEAD/samd_sam_only/samd_config.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":"4384f1c14a42560d"}},{"code_sha256_prefix":"7da3f3c3257345db","entry":"load_eagle2","repo":"hyx1999/sam-decoding","repo_kind":"official","path":"samd_sam_only/samd_config.py","file_url":"https://github.com/hyx1999/sam-decoding/blob/HEAD/samd_sam_only/samd_config.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":"7da3f3c3257345db"}},{"code_sha256_prefix":"f231b30bd85c1ce0","entry":"load_token_recycle","repo":"hyx1999/sam-decoding","repo_kind":"official","path":"samd_sam_only/samd_config.py","file_url":"https://github.com/hyx1999/sam-decoding/blob/HEAD/samd_sam_only/samd_config.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":"f231b30bd85c1ce0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}