AI News HubLIVE
Original source2 min read

EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction

EntMTP is a training-free scheduler that dynamically switches tree-based attention topologies based on local generation entropy, enabling deep speculation in low-entropy regions and conservative speculation in high-entropy regions. It maximizes throughput without sacrificing quality, achieving 1.15x speedup over Hydra and peak 1.36x over Medusa on various benchmarks.

SourcearXiv Computational LinguisticsAuthor: Carrie Chen

[2606.27550] EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction

[Submitted on 25 Jun 2026]

Title:EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction

View a PDF of the paper titled EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction, by Carrie Chen

View PDF HTML (experimental)

Abstract:Multi-token prediction has been shown to increase data density during training, improve downstream text-generation quality, and serves as the defacto approach for self-speculative decoding. Existing foundation and open source models that use MTP heads commit to a static tree-based attention topology throughout the entire generation sequence, meaning the speculation depth, and thus the compute required during verification, stays constant regardless of the context. This is fundamentally misaligned with the entropy patterns of natural language where low-entropy regions often support reliable multi-step drafting, while high-entropy regions require more conservative speculation. To address this, we propose Entropy-guided Multi-Token Prediction (EntMTP), a training-free scheduler that toggles between tree-based attention topologies from a set of task-specific pareto-optimal trees conditioned on a running estimate of local generation entropy. By matching speculation depth to context predictability, EntMTP maximizes expected accepted-token throughput across the full distribution of generated text without sacrificing generation quality. When evaluated across Humaneval, ShareGPT, GSM8k, and Litbench benchmarks, EntMTP consistently achieves a 1.15x speedup against Hydra and peak speedup of 1.36x against Medusa baselines respectively.

Comments: 7 pages, 5 figures

Subjects:

Computation and Language (cs.CL); Machine Learning (cs.LG)

Cite as: arXiv:2606.27550 [cs.CL]

(or arXiv:2606.27550v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.27550

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Carrie Chen [view email] [v1] Thu, 25 Jun 2026 20:54:27 UTC (1,173 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction, by Carrie Chen

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-06

Change to browse by:

cs cs.LG

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

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? | Disable MathJax (What is MathJax?)