<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-eagle">
    <titleInfo>
        <title>EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yuhui</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fangyun</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chao</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongyang</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Inference with modern Large Language Models (LLMs) is expensive and time-consuming, and speculative sampling has proven to be an effective solution. Most speculative sampling methods such as EAGLE use a static draft tree, implicitly assuming that the acceptance rate of draft tokens depends only on their position. Interestingly, we found that the acceptance rate of draft tokens is also context-dependent. In this paper, building upon EAGLE, we propose EAGLE-2, which introduces a new technique of context-aware dynamic draft tree into drafting modeling. This improvement leverages the fact that the draft model of EAGLE is well-calibrated: the confidence scores from the draft model approximate acceptance rates with small errors. We conducted extensive evaluations on three series of LLMs and six tasks, with EAGLE-2 achieving speedup ratios of up to **5x**, which is 1.3x that of EAGLE. EAGLE-2 also ensures that the distribution of the generated text remains unchanged, making it a **lossless** acceleration algorithm.</abstract>
    <identifier type="citekey">li-etal-2024-eagle</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.422</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>7421</start>
            <end>7432</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees
%A Li, Yuhui
%A Wei, Fangyun
%A Zhang, Chao
%A Zhang, Hongyang
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F li-etal-2024-eagle
%X Inference with modern Large Language Models (LLMs) is expensive and time-consuming, and speculative sampling has proven to be an effective solution. Most speculative sampling methods such as EAGLE use a static draft tree, implicitly assuming that the acceptance rate of draft tokens depends only on their position. Interestingly, we found that the acceptance rate of draft tokens is also context-dependent. In this paper, building upon EAGLE, we propose EAGLE-2, which introduces a new technique of context-aware dynamic draft tree into drafting modeling. This improvement leverages the fact that the draft model of EAGLE is well-calibrated: the confidence scores from the draft model approximate acceptance rates with small errors. We conducted extensive evaluations on three series of LLMs and six tasks, with EAGLE-2 achieving speedup ratios of up to **5x**, which is 1.3x that of EAGLE. EAGLE-2 also ensures that the distribution of the generated text remains unchanged, making it a **lossless** acceleration algorithm.
%U https://aclanthology.org/2024.emnlp-main.422
%P 7421-7432

Markdown (Informal)

[EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://aclanthology.org/2024.emnlp-main.422) (Li et al., EMNLP 2024)

• EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees (Li et al., EMNLP 2024)

ACL

• Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. 2024. EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7421–7432, Miami, Florida, USA. Association for Computational Linguistics.