EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
CoRR(2024)
摘要
Auto-regressive decoding makes the inference of Large Language Models (LLMs)
time-consuming. We propose a simple framework, EAGLE (Extrapolation Algorithm
for Greater Language-model Efficiency), for lossless acceleration. Unlike
traditional speculative sampling methods, EAGLE operates the drafting process
auto-regressively at the more regular (second-top-layer) feature level and
addresses the sampling uncertainty issues in the next-feature prediction
problems by integrating tokens from one time step ahead. The acceleration
provided by EAGLE is lossless: it involves no fine-tuning of the target LLM,
and the generated text maintains the same distribution as that of vanilla
auto-regressive decoding. As of the submission of this paper, EAGLE is the
fastest known framework within the speculative sampling family. On MT-bench,
EAGLE is 3x faster than vanilla decoding, 2x faster than Lookahead, and 1.6x
faster than Medusa. Using gpt-fast, EAGLE attains on average 160 tokens/s with
LLaMA2-Chat 13B on a single RTX 3090 GPU, compared to 24 tokens/s of
Huggingface's implementations.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要