Jason Knight

Jason Knight

CPO, Co-Founder

7 Articles

Jason Knight

Jason Knight

Mar 4, 2021

Jason Knight

Jason Knight

Mar 4, 2021

Up to 9x performance improvements with TVM’s new auto-scheduler

Autoscheduling enables higher performance end to end model optimization from TVM, while also enabling users to write custom operators even easier than before.

Jason Knight

Jason Knight

Feb 25, 2021

Jason Knight

Jason Knight

Feb 25, 2021

Compiling classical ML for performance gains (up to 30x) and hardware portability

Today, machine learning engineers and data scientists use popular frameworks such as Scikit-learn, XGBoost, and LightGBM to train and deploy classical ML models such as linear and logistic regression, decision trees and gradient boosting.

Jason Knight

Jason Knight

Jan 15, 2021

Jason Knight

Jason Knight

Jan 15, 2021

In the cloud — Sparsity on GPUs provides 5X speedup

As AI models get larger, the importance of each weight for a typical inferencing decreases...

Jason Knight

Jason Knight

Jul 17, 2020

Jason Knight

Jason Knight

Jul 17, 2020

Leveraging block sparsity with Apache TVM to halve your cloud bill for NLP

The natural language processing (NLP) community has been transformed by the recent performance and versatility of transformer models from the deep learning research community...

Jason Knight

Jason Knight

Jun 4, 2020

Jason Knight

Jason Knight

Jun 4, 2020

TinyML: TVM taming the final (ML) frontier

Optimizing and deploying machine learning workloads to bare metal devices today is difficult, and Apache TVM is laying the open source foundation to making this easy and fast for anyone.

1

2

Maximize performance. Simplify deployment.

Ready to get started?