Papers › EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

26 Jan 2024arXiv:2401.15077archive 2025-07-28

Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang

Autoregressive decoding makes the inference of Large Language Models (LLMs) time-consuming. In this paper, we reconsider speculative sampling and derive two key observations. Firstly, autoregression at the feature (second-to-top-layer) level is more straightforward than at the token level. Secondly, the inherent uncertainty in feature (second-to-top-layer) level autoregression constrains its performance. Based on these insights, we introduce EAGLE (Extrapolation Algorithm for Greater Language-model Efficiency), a simple yet highly efficient speculative sampling framework. By incorporating a token sequence advanced by one time step, EAGLE effectively resolves the uncertainty, enabling precise second-to-top-layer feature prediction with minimal overhead. We conducted comprehensive evaluations of EAGLE, including all models from the Vicuna and LLaMA2-Chat series, the MoE model Mixtral 8x7B Instruct, and tasks in dialogue, code generation, mathematical reasoning, and instruction following. For LLaMA2-Chat 70B, EAGLE achieved a latency speedup ratio of 2.7x-3.5x, doubled throughput, while maintaining the distribution of the generated text.

PaperPDFCode

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

Code

safeailab/eagle officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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.

Code Syntology ran Syntology

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

Tasks

Code GenerationInstruction FollowingLanguage ModelingLanguage ModellingMathematical Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Lookahead

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