Papers › Accelerating Large Language Model Decoding with Speculative Sampling

Accelerating Large Language Model Decoding with Speculative Sampling

2 Feb 2023arXiv:2302.01318archive 2025-07-28

Charlie Chen, Sebastian Borgeaud, Geoffrey Irving, Jean-Baptiste Lespiau, Laurent SIfre, John Jumper

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.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

apoorvumang/prompt-lookup-decoding mentioned on GitHubpytorchSyntology: not harvested report
eth-sri/language-model-arithmetic mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Controlled Text Generation via Language Model Arithmetic (arXiv:2311.14479; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
feifeibear/llmspeculativesampling mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fast Inference from Transformers via Speculative Decoding (arXiv:2211.17192; that paper's own run record: 15 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
nlpodyssey/rwkv.f90 mentioned on GitHubMITSyntology: not harvested report
wdrink/simplear mentioned on GitHubjaxMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through... (arXiv:2504.11455; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingLarge Language Modelmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Chinchilla

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections