AI News HubLIVE
Original source2 min read

Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices

A new GPU inference method for LLMs with moderate sparsity (around 50%) is proposed, using a three-layer matrix storage format that enables sparse tensor cores and CUDA cores to jointly accelerate sparse matrix multiplication. It is the first to outperform dense matrix multiplication on modern HBM-equipped GPUs, achieving up to 1.64x kernel-level speedup over SpInfer and 1.41x end-to-end speedup over FlashLLM.

SourcearXiv Machine LearningAuthor: Tao Lu, Haoyu Wang, Zonghui Wang, Keshen Xiang, Jiaheng Zhang, Wenzhi Chen

-->

[Submitted on 13 Jun 2026]

Title:Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices

View a PDF of the paper titled Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices, by Tao Lu and 5 other authors

View PDF HTML (experimental)

Abstract:With the growing deployment of large language models (LLMs), LLM inference cost has become a key challenge. Pruning techniques that introduce sparsity into weight matrices can accelerate inference. However, maintaining model quality typically limits pruning to moderate unstructured sparsity (around 50\%). At these sparsity levels, none of the existing GPU kernels for sparse matrix multiplication (SpMM) can outperform their dense counterparts. This paper proposes an efficient GPU inference method for LLMs with moderate sparsity. We propose a three-layer matrix storage format comprising: (i) a Sparse-TC layer enabling sparse tensor cores to accelerate SpMM; (ii) a Slot-Filling layer using parallel differential distance for matrix compression while supporting low-cost on-chip decoding; (iii) a lightweight Residual Layer ensuring correct SpMM computation. Building on this format, we design a SpMM kernel that jointly utilizes sparse tensor cores and CUDA cores. This design enables an efficient execution pipeline and overlaps on-chip computation with memory access. Evaluations show that our work is the first to outperform dense matrix multiplication on modern GPUs equipped with high-bandwidth memory (HBM). It achieves up to 1.64x kernel-level speedup over SpInfer (EuroSys'25, Best paper) and up to 1.41x end-to-end speedups over FlashLLM (VLDB'24). Our source code: this https URL.

Comments: DAC 2026

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR)

Cite as: arXiv:2607.08786 [cs.LG]

(or arXiv:2607.08786v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.08786

arXiv-issued DOI via DataCite

Submission history

From: Tao Lu [view email] [v1] Sat, 13 Jun 2026 13:38:27 UTC (236 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices, by Tao Lu and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-07

Change to browse by:

cs cs.AI cs.AR

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?)