Researchers baked 3x inference speedups directly into LLM weights — without speculative decoding

Researchers from the University of Maryland, Lawrence Livermore, Columbia and TogetherAI have developed a training technique that triples LLM inference speed without auxiliary models or infrastructure ...
Tech Xplore on MSN

Adaptive drafter model uses downtime to double LLM training speed

Reasoning large language models (LLMs) are designed to solve complex problems by breaking them down into a series of smaller steps. These powerful models are particularly good at challenging tasks ...
InfoWorld

Multi-token prediction technique triples LLM inference speed without auxiliary draft models

With reported 3x speed gains and limited degradation in output quality, the method targets one of the biggest pain points in production AI systems: latency at scale.