Michael R. Metel


2024

pdf bib
Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity
Michael R. Metel | Peng Lu | Boxing Chen | Mehdi Rezagholizadeh | Ivan Kobyzev
Findings of the Association for Computational Linguistics: EMNLP 2024

We present a simple on the fly method for faster inference of large language models. Unlike other (self-)speculative decoding techniques, our method does not require fine-tuning or black-box optimization to generate a fixed draft model, relying instead on simple rules to generate varying draft models adapted to the input context. We show empirically that our light-weight algorithm is competitive with the current SOTA for self-speculative decoding, while being a truly plug-and-play method.