LLM-D, with Clayton Coleman and Rob Shaw
Kubernetes Podcast from Google
00:00
Future of AI Models in Kubernetes
This chapter delves into the evolving landscape of AI model serving within Kubernetes, predicting advancements over the next five to ten years. It emphasizes key aspects like KV cache management, multimodality in AI, and the importance of engaging with the machine learning community amidst rapid technological innovation.
Transcript
Play full episode
