

Lamb Labs이란?
Lamb Labs is building custom chips for AI inference and the world's fastest LLM model at the lowest power. We've developed a new post-training technique that converts existing models to a diffusion-based architecture that delivers 2× faster inference on existing GPUs. We then build the hardware, custom silicon chips targeting up to 20,000+ tok/s and a 63× higher intelligence per watt.
?
아직 댓글이 없어요. 가장 먼저 남겨보세요!
Lamb Labs에 대한 X의 실제 대화
X에 게시
