Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity

Abstract: We present a simple on the fly method for faster inference of LLMs. 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.