[2605.19893] SSV: Sparse Speculative Verification for Efficient LLM Inference

-->

Computer Science > Operating Systems

arXiv:2605.19893 (cs)

[Submitted on 19 May 2026 (v1), last revised 20 May 2026 (this version, v2)]

Title:SSV: Sparse Speculative Verification for Efficient LLM Inference

Authors:Zhibin Wang, Ziyu Zhong, Nuo Shen, Yuhang Zhou, Rong Gu, Sheng Zhong<br>View a PDF of the paper titled SSV: Sparse Speculative Verification for Efficient LLM Inference, by Zhibin Wang and 4 other authors

View PDF<br>HTML (experimental)

Abstract:Speculative decoding and dynamic sparse attention are two complementary approaches for accelerating long-context LLM inference: the former amortizes target-model execution across multiple verifier queries, while the latter reduces each query's KV-cache working set. Directly combining them, however, exposes a structural mismatch: speculative verification relies on cross-query commonality, whereas dynamic sparse attention assigns query-specific sparse layouts. This mismatch limits KV-block reuse, amplifies NSA's branch-wise overheads, and makes verification strategy selection input- and regime-dependent. We present SSV, a sparse speculative-verification framework that turns dynamic sparse attention into a verification-oriented workload. SSV combines overlap-aware grouped-query execution, refresh/reuse-based NSA kernel fusion, and profile-guided prompt-adaptive orchestration to improve cross-query reuse, reduce selected-index and branch-fusion overheads, and select effective draft-verification strategies under user-specified precision classes. Experiments on NVIDIA H100 GPUs show that SSV achieves up to 3.49x end-to-end throughput over autoregressive NSA decoding and up to 6.86x kernel speedups for sparse speculative verification.

Subjects:

Operating Systems (cs.OS)

Cite as:<br>arXiv:2605.19893 [cs.OS]

(or<br>arXiv:2605.19893v2 [cs.OS] for this version)

https://doi.org/10.48550/arXiv.2605.19893

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Yuhang Zhou [view email]<br>[v1]<br>Tue, 19 May 2026 14:24:27 UTC (2,447 KB)

[v2]<br>Wed, 20 May 2026 15:53:57 UTC (2,446 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled SSV: Sparse Speculative Verification for Efficient LLM Inference, by Zhibin Wang and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.OS

next >

new<br>recent<br>| 2026-05

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 is MathJax?)