Self-hosting & scaling models (Practical AI #243)

Changelog Master Feed

We’re excited to have Tuhin join us on the show once again to talk about self-hosting open access models. Tuhin’s company Baseten specializes in model deployment and monitoring at any scale, and it was a privilege to talk with him about the trends he is seeing in both tooling and usage of open access models. We were able to touch on the common use cases for integrating self-hosted models and how the boom in generative AI has influenced that ecosystem.

Join the discussion

Changelog++ members save 1 minute on this episode because they made the ads disappear. Join today!

Sponsors:

• Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com
• Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs.
• Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster!

Featuring:

• Tuhin Srivastava – GitHub, X
• Chris Benson – Website, GitHub, LinkedIn, X
• Daniel Whitenack – Website, GitHub, X

Show Notes:

• Baseten

Something missing or broken? PRs welcome!

فصل ها

1. Welcome to Practical AI (00:00:00)

2. Overview of Baseten (00:00:43)

3. We've come a long way (00:07:45)

4. Infrastructure & drones (00:09:06)

5. Hosting vs making a product (00:12:45)

6. Baseten's users (00:15:54)

7. Keep your data (00:18:55)

8. The approach to Baseten (00:19:50)

9. Difference in day to day (00:22:28)

10. Convenient auto-scaling (00:25:51)

11. Gotta go fast (00:27:02)

12. Where trends are going (00:29:05)

13. Running on the edge (00:33:09)

14. Solving future problems (00:35:25)

15. Wrapping up (00:39:39)