Papers › Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

29 Apr 2024arXiv:2404.18911archive 2025-07-28

Fangcheng Liu, Yehui Tang, Zhenhua Liu, Yunsheng Ni, Kai Han, Yunhe Wang

Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models while maintaining a consistent sampling distribution. However, the conventional approach of training a separate draft model to achieve a satisfactory token acceptance rate can be costly. Drawing inspiration from early exiting, we propose a novel self-speculative decoding framework \emph{Kangaroo}, which uses a fixed shallow sub-network as a self-draft model, with the remaining layers serving as the larger target model. We train a lightweight and efficient adapter module on top of the sub-network to bridge the gap between the sub-network and the full model's representation ability. It is noteworthy that the inference latency of the self-draft model may no longer be negligible compared to the large model, necessitating strategies to increase the token acceptance rate while minimizing the drafting steps of the small model. To address this challenge, we introduce an additional early exiting mechanism for generating draft tokens. Specifically, we halt the small model's subsequent prediction during the drafting phase once the confidence level for the current token falls below a certain threshold. Extensive experiments on the Spec-Bench demonstrate the effectiveness of Kangaroo. Under single-sequence verification, Kangaroo achieves speedups up to 1.68× on Spec-Bench, outperforming Medusa-1 with 88.7\% fewer additional parameters (67M compared to 591M). The code for Kangaroo is available at https://github.com/Equationliu/Kangaroo.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2404.18911")

Code

Syntology Ran 4 of 6 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Equationliu/Kangaroo officialmentioned on GitHubpytorch 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

6 samples harvested; 4 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
2ran · fixture could not drive it
1ran
2unverified

Licence: 6 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Equationliu/Kangaroo. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

repeat_kv Equationliu/Kangaroo/kangaroo/adapter.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 30d7eec482ebf6b1 · report
apply_rotary_pos_emb Equationliu/Kangaroo/kangaroo/adapter.py official repository ran · fixture could not drive it no licence file found · pointer only · f725bc2d76076485 · report
baseline_forward Equationliu/Kangaroo/evaluation/inference_baseline.py official repository ran no licence file found · pointer only · df4cc783cc8f5272 · report
rotate_half Equationliu/Kangaroo/kangaroo/adapter.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · b99eea6376d1e212 · report
kangaroo_forward Equationliu/Kangaroo/evaluation/inference_kangaroo.py official repository unverified no licence file found · pointer only · 59f5346ce1d6bf08 · report
speed Equationliu/Kangaroo/evaluation/speed.py official repository unverified no licence file found · pointer only · aac7165992097239 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdapterEarly exiting

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