[2605.26558] Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding

-->

Computer Science > Hardware Architecture

arXiv:2605.26558 (cs)

[Submitted on 26 May 2026]

Title:Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding

Authors:Soongyu Choi, Yuntae Kim, Muyoung Son, Joo-Young Kim<br>View a PDF of the paper titled Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding, by Soongyu Choi and 3 other authors

View PDF<br>HTML (experimental)

Abstract:Speculative decoding has emerged as a promising lossless approach for accelerating Large Language Models (LLMs). As reasoning LLMs increasingly suffer from decode-stage overhead and approximation-based methods degrade accuracy, lossless speculative decoding has become essential for efficient inference. However, existing methods still struggle to deliver strong low-batch performance without additional training, limiting practical deployment on consumer devices. To address this challenge, we propose Cassandra, an algorithm-hardware co-designed self-speculative decoding framework optimized for low-batch scenarios. Cassandra constructs a high-performance, training-free draft model through fine-grained data selection. Using optimized pruning and mantissa truncation, it identifies the most salient values in both model weights and the Key-Value (KV) cache, enabling rapid candidate token generation before full-precision parallel verification. Unlike prior self-speculative decoding methods based on layer skipping or structured KV compression, Cassandra achieves significantly higher efficiency. To further reduce the overhead of format conversion between Cassandra representations and standard floating-point formats, we also introduce a lightweight encoder-decoder hardware module designed for seamless integration with commercial GPUs and NPUs. Experimental results show that Cassandra achieves up to 2.41x speedup over the BF16 baseline without additional training. Furthermore, on Llama 3 8B running on an NVIDIA GeForce RTX 4090, Cassandra generates 1.81x more tokens under the same memory budget compared to Eagle-3, a state-of-the-art speculative decoding method.

Comments:<br>To appear at ISCA 2026

Subjects:

Hardware Architecture (cs.AR)

Cite as:<br>arXiv:2605.26558 [cs.AR]

(or<br>arXiv:2605.26558v1 [cs.AR] for this version)

https://doi.org/10.48550/arXiv.2605.26558

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Soongyu Choi [view email]<br>[v1]<br>Tue, 26 May 2026 05:12:44 UTC (5,865 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding, by Soongyu Choi and 3 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.AR

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?)