Jason Knight

Jason Knight

May 14, 2020

Jason Knight

Jason Knight

May 14, 2020

WebGPU powered machine learning in the browser with Apache TVM

We introduced support for WASM and WebGPU backends to the Apache TVM deep learning compiler. Our initial experiments shows that TVM’s WebGPU backend can get close to native GPU performance when deploying models in the browser.

Luis Ceze

Luis Ceze

Apr 3, 2020

Luis Ceze

Luis Ceze

Apr 3, 2020

Announcing OctoML’s Series A, growing our team and Octomizing the World’s ML/AI needs!

We are very excited to announce that six months after our seed funding we have closed a Series A funding round of $15 million

Josh Fromm

Josh Fromm

Mar 31, 2020

Josh Fromm

Josh Fromm

Mar 31, 2020

Riptide: Fast, Full Binarization in TVM

Riptide is a new method for quantizing models down to 1 or 2 bits that can enable end-to-end speedups of up to 12X when optimized using TVM.

Jason Knight

Jason Knight

Mar 24, 2020

Jason Knight

Jason Knight

Mar 24, 2020

OctoML ≔ Easier machine learning

Machine learning and deep learning (ML/DL) are making large impacts across the computing field and the horizon is bright with the rapidly growing capabilities they add to an engineer’s toolbox.

4

5

Accelerate Performance and Deployment Time