154: Serving Up AI with Sean Moriarity
Thinking Elixir Podcast
00:00
How to Operationalize Machine Learning Workflows
There are still some challenges with using llama in elixir so we don't support like quantized inference which helps people run these models on smaller machines. Some of the more technically challenging things that that arise with these super massive models we don't necessarily have support for. Shawn moire will be speaking at empex in brooklyn on june 9th about large language models and what the future looks like. He also has a book coming out next year to talk about operationalized machine learning workflows, vector databases or other tangential aspects of this ecosystem.
Transcript
Play full episode
