Stellar inference speed via AutoNAS (Practical AI #148)
Changelog Master Feed · Changelog Media
September 7, 202142m 15s
Audio is streamed directly from the publisher (op3.dev) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
Yonatan Geifman of Deci makes Daniel and Chris buckle up, and takes them on a tour of the ideas behind his amazing new inference platform. It enables AI developers to build, optimize, and deploy blazing-fast deep learning models on any hardware. Don’t blink or you’ll miss it!
Changelog++ members save 2 minutes on this episode because they made the ads disappear. Join today!
Sponsors:
- RudderStack – Smart customer data pipeline made for developers. RudderStack is the smart customer data pipeline. Connect your whole customer data stack. Warehouse-first, open source Segment alternative.
- SignalWire – Build what’s next in communications with video, voice, and messaging APIs powered by elastic cloud infrastructure. Try it today at signalwire.com and use code
SHIPITfor $25 in developer credit. - 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
Featuring:
- Yonatan Geifman – Website, GitHub, X
- Chris Benson – Website, GitHub, LinkedIn, Bluesky, X
- Daniel Whitenack – Website, GitHub, X
Show Notes:
- Deci
- An Introduction to the Inference Stack and Inference Acceleration Techniques
- Deci and Intel Collaborate to Optimize Deep Learning Inference on Intel’s CPUs
- DeciNets: A New Efficient Frontier for Computer Vision Models
- White paper
Something missing or broken? PRs welcome!