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.

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 ...
GitHub

Moshi: a speech-text foundation model for real time dialogue

Finally, the code for the web UI client used in the Moshi demo is provided in the client/ directory. If you want to fine tune Moshi, head out to kyutai-labs/moshi ...

Using bat speed, swing shape to find potential MLB breakout stars

How the swing metrics Bat Speed, Swing Tilt and Intercept Point can help identify potential breakout hitters for the 2026 ...

American Jordan Stolz speedskates to a third Olympic medal — silver this time

U.S. speedskater Jordan Stolz had a lot of hype accompanying him in these Winter Olympic Games. He's now got two gold medals, one silver, with one event to go.