A method that is currently trending on Papers with Code is Speculative Decoding. https://preview.redd.it/dm4nh4t71o7h1.png?width=3082&format=png&auto=webp&s=b6468668667d4bcfb6c9248d3af7fd09f21fe0da Speculative decoding is an inference optimization technique that uses a fast, small "draft" model to q
