On the latest Gestalt IT Rundown, Tom Hollingsworth is joined by Stephen Foskett where they dive into the newly released ML Commons MLPerf Training v2.0 results. This benchmark suite measures how fast systems can train models to a target quality metric. NVIDIA, Intel Habana, Google, and Graphcore all submitted at least partial results. How do we make sense of all this ML training hardware? Head to GestaltIT.com for shownotes.
Deep Learning Training With Intel Habana Gaudi
In this post, Liselotte Foverskov, a Field Day delegate, gives her insight on the presentation from Habana, an Intel company, at this past AI Field Day. Check out her thoughts on Habana’s developmental focus of disruptive solutions that are shaping the future of AI and Deep Learning.
Training More for Less With Habana Gaudi
In this post from Gestalt IT, Sulagna Saha talks about Intel’s Habana Labs presentation on Gaudi at May’s Ai Field Day. She goes into detail on how this AI training processor makes DL model training affordable for a change. Check out Sulagna’s thoughts here!
