AI News HubLIVE
原文2 min read

Efficient On-Device Diffusion LLM Inference with Mobile NPU

This paper presents llada.cpp, the first NPU-aware inference framework for accelerating diffusion LLMs on smartphones. It introduces three techniques—Multi-Block Speculative Decoding, Dual-Path Progressive Revision, and Swap-Optimized Memory Runtime—to overcome challenges like shrinking workloads, KV cache reuse, and memory overhead. llada.cpp reduces LLaDA-8B generation latency by 17x-42x over CPU baseline with no quality loss.

SourcearXiv Machine LearningAuthor: Tuowei Wang, Yanfan Sun, Ju Ren

[2606.13740] Efficient On-Device Diffusion LLM Inference with Mobile NPU

[Submitted on 11 Jun 2026]

Title:Efficient On-Device Diffusion LLM Inference with Mobile NPU

View a PDF of the paper titled Efficient On-Device Diffusion LLM Inference with Mobile NPU, by Tuowei Wang and 2 other authors

View PDF HTML (experimental)

Abstract:Diffusion large language models (dLLMs) accelerate generation by denoising multiple tokens in parallel, making them attractive for latency-sensitive mobile inference. However, repeated denoising introduces substantial computation on smartphones. Mobile neural processing units (NPUs) offer high-throughput dense matrix computation, but efficiently exploiting them remains challenging: token commitment shrinks per-block effective workloads, token revision complicates KV cache reuse, and limited NPU-visible address space incurs costly remapping and data transfer overheads.

In this paper, we propose this http URL, the first NPU-aware inference framework for accelerating dLLMs on smartphones. this http URL aligns block-wise dLLM inference with the execution characteristics of mobile NPUs through three techniques. (1) Multi-Block Speculative Decoding fills the shrinking workload in late-stage current-block decoding with speculative future-block tokens. (2) Dual-Path Progressive Revision keeps committed tokens revisable until stable and refreshes unstable tokens through a CPU-side path without stalling dense NPU execution. (3) Swap-Optimized Memory Runtime compacts NPU-visible address layouts and overlaps data staging with NPU computation to reduce remapping and transfer overheads. We implement this http URL as an end-to-end framework and evaluate it across diverse hardware platforms and dLLM workloads. this http URL reduces LLaDA-8B generation latency by 17x-42x over the CPU baseline with prefix KV cache reuse, while preserving generation quality.

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2606.13740 [cs.LG]

(or arXiv:2606.13740v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.13740

arXiv-issued DOI via DataCite

Submission history

From: Tuowei Wang [view email] [v1] Thu, 11 Jun 2026 12:44:57 UTC (547 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Efficient On-Device Diffusion LLM Inference with Mobile NPU, by Tuowei Wang and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-06

Change to browse by:

cs

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?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

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?)