Slingshot AI’s Post

View organization page for Slingshot AI, graphic

1,213 followers

Our latest #Slingtalk episode explores LLM inference speeds and its impact on how models are deployed and how software is built. Some questions I’m left thinking about: - Is fast model inference the real moat for the biggest LLM companies? - Will “async” flows introduce entirely new software approaches, compared to real-time? - How far away are hardware and software from being edge-inference ready? Watch the full episode on Spotify (https://buff.ly/3ROpIZU)

To view or add a comment, sign in

Explore topics