7 Apr 1pm ET: Live Webinar: Introducing the Neural Magic Community Edition

[jeanniefinks]

Live Webinar: Introducing the Neural Magic Community Edition

After years of research and development, we have open sourced our portfolio of tools and made them available here on GitHub. Now anyone can sparsify and quantize deep learning models with ease to minimize footprint and run on CPUs at GPU speeds. Chances are, if you reading this, you may have already checked us out but now here's a live opportunity to interact and/or listen on an overview.

Join our 45-minute webinar on April 7th to ask questions and learn about the four deep learning components that you can take advantage of immediately.

• Sparsify: Easy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint.
• SparseML: Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models.
• SparseZoo: Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes.
• DeepSparse Engine: Neural network inference engine that delivers GPU-class performance for sparsified models on CPUs.

Date: April 7, 2021
Time: 1:00 PM ET (10:00 AM PT)
Speakers: Nir Shavit, Founder, Neural Magic & Mark Kurtz, ML Lead, Neural Magic

Register here. Hope to see you there!

[jeanniefinks]

Missed the webinar but want to catch the recording?

Watch on YouTube!
https://neuralmagic.com/resources/on-demand-webinars/neural-magic-deep-sparse-platform/

An overview of how to use Neural Magic's open-source and free tools available on our repo to sparsify (prune and quantize) deep learning models to minimize footprint and run on CPUs at GPU speeds.