{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/accelerating-large-language-model-decoding","title":"Accelerating Large Language Model Decoding with Speculative Sampling","arxiv_id":"2302.01318","date":"2023-02-02","proceeding":null,"authors":["Charlie Chen","Sebastian Borgeaud","Geoffrey Irving","Jean-Baptiste Lespiau","Laurent SIfre","John Jumper"],"abstract":"We present speculative sampling, an algorithm for accelerating transformer decoding by enabling the generation of multiple tokens from each transformer call. Our algorithm relies on the observation that the latency of parallel scoring of short continuations, generated by a faster but less powerful draft model, is comparable to that of sampling a single token from the larger target model. This is combined with a novel modified rejection sampling scheme which preserves the distribution of the target model within hardware numerics. We benchmark speculative sampling with Chinchilla, a 70 billion parameter language model, achieving a 2-2.5x decoding speedup in a distributed setup, without compromising the sample quality or making modifications to the model itself.","url_abs":"https://arxiv.org/abs/2302.01318v1","url_pdf":"https://arxiv.org/pdf/2302.01318v1.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":"accelerating-large-language-model-decoding","repo_url":"https://github.com/apoorvumang/prompt-lookup-decoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"accelerating-large-language-model-decoding","repo_url":"https://github.com/eth-sri/language-model-arithmetic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"accelerating-large-language-model-decoding","repo_url":"https://github.com/feifeibear/llmspeculativesampling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"accelerating-large-language-model-decoding","repo_url":"https://github.com/nlpodyssey/rwkv.f90","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"accelerating-large-language-model-decoding","repo_url":"https://github.com/wdrink/simplear","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"chinchilla","method_name":"Chinchilla"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.01318","atlas_url":"https://app.syntology.ai/?focus=2302.01318","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2302.01318"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2302.01318\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2302.01318"},"call":"get_concepts_for_paper(arxiv_id=\"2302.01318\")"}],"by_repo":[{"repo":"apoorvumang/prompt-lookup-decoding","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"eth-sri/language-model-arithmetic","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2311.14479"],"harvested_for_calls":[{"arxiv_id":"2311.14479","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.14479"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.14479\")"}]},{"repo":"feifeibear/llmspeculativesampling","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2211.17192"],"harvested_for_calls":[{"arxiv_id":"2211.17192","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2211.17192"},"call":"get_harvested_code_for_paper(arxiv_id=\"2211.17192\")"}]},{"repo":"nlpodyssey/rwkv.f90","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"wdrink/simplear","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2504.11455"],"harvested_for_calls":[{"arxiv_id":"2504.11455","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2504.11455"},"call":"get_harvested_code_for_paper(arxiv_id=\"2504.11455\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3ef0f1fd37282c4c55aafd90a25bf18d1e32a3e4f51bb173444e56d604781114","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}