In this quick virtual lightboard video, we walk through an intro to the llm-d open source project which is a distributed inference serving framework for Kubernetes. llm-d uses the Inference extensions to the Kubernetes Gateway API which I did a video about here:
- 835Просмотров
- 6 месяцев назадОпубликованоChristian Posta
Introduction to llm-d Distributed Inference on Kubernetes
Похожее видео
Популярное
Новини