[2607.08642] DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Computer Science > Computation and Language

arXiv:2607.08642 (cs)

[Submitted on 9 Jul 2026]

Title:DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding

Authors:Saw S. Lin (Zhiqi Zhang), Jyh-Shing Roger Jang<br>View a PDF of the paper titled DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding, by Saw S. Lin (Zhiqi Zhang) and Jyh-Shing Roger Jang

View PDF<br>HTML (experimental)

Abstract:Speculative decoding accelerates LLM inference by drafting several tokens and verifying them in parallel. Block-diffusion drafters such as DFlash produce

a draft block in one pass but model only per-position marginals; best-first tree methods such as DDTree expand candidate trees from those marginals. The

released Domino drafter adds a GRU-based causal correction that makes each draft token's distribution path-dependent, a structure DDTree's factorized

formulation cannot represent. We introduce DominoTree, a training-free best-first draft tree scored by Domino's conditional, non-factorized correction

along each root-to-node path, made practical by restricting the per-node correction to a candidate top-M. On Qwen3-4B across eight benchmarks, DominoTree

reaches up to 6.6x speedup over autoregressive decoding and the highest mean accept length of any evaluated method, up to 10.7 tokens per round, at every

temperature we test. DominoTree constructs its tree with a GPU-native, CUDA-graph builder that is bit-identical to a reference Python implementation, so

acceptance is unchanged, while keeping per-round tree construction cheap. With this builder as default, DominoTree wins throughput over the released

Domino decoder at every temperature, 9-10% overall on Qwen3-4B and up to +22% on Alpaca, and over DDTree/CaDDTree at every temperature we test. On Qwen3-

8B, DominoTree keeps the highest accepted length at every temperature and adds a decisive throughput win at T=0, +24% over DDTree; at higher temperature

that edge over DDTree/CaDDTree narrows to a tie and a small loss, while its Overall aggregate wins over DFlash and Domino persist.

Comments:<br>23 pages, 2 figures, 11 tables. Code: this https URL

Subjects:

Computation and Language (cs.CL)

Cite as:<br>arXiv:2607.08642 [cs.CL]

(or<br>arXiv:2607.08642v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.08642

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Saw San Lin [view email]<br>[v1]<br>Thu, 9 Jul 2026 16:16:35 UTC (115 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding, by Saw S. Lin (Zhiqi Zhang) and Jyh-Shing Roger Jang<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.CL

next >

new<br>recent<br>| 2026-07

Change to browse by:

cs

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What...