Mixture of Attentions For Speculative Decoding
Keywords: large language models, speculative decoding, EAGLE
TL;DR: Using dynamical system view of LLM generation for better speculative decoding architecture
Abstract: The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy.
Speculative decoding (SD) leverages smaller models to efficiently propose future tokens, which are then verified by the LLM in parallel.
Small models that utilise activations from the LLM currently achieve the fastest decoding speeds.
However, we identify several limitations of SD models including the lack of on-policyness during training and partial observability.
To address these shortcomings, we propose a more grounded architecture for small models by introducing a Mixture of Attentions for SD.
Our novel architecture can be applied in two scenarios: a conventional single device deployment and a novel client-server deployment where the small model is hosted on a consumer device and the LLM on a server.
In a single-device scenario, we demonstrate state-of-the-art speedups improving EAGLE-2 by 9.5% and its acceptance length by 25%.
In a client-server setting, our experiments demonstrate: 1) state-of-the-art latencies with minimal calls to the server for different network conditions, and 2) in the event of a complete disconnection, our approach can maintain higher accuracy compared to other SD methods and demonstrates advantages over API calls to LLMs, which would otherwise be unable to continue the generation process.
Supplementary Material: zip
Primary Area: generative models
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 11328
Loading