New funding: Seattle-based startup OctoML raised a $28 million Series B round. The University of Washington spinout aims to help companies deploy machine learning models on various hardware configurations.
The technology: OctoML is led by the creators of Apache TVM, an open source “deep learning compiler stack” that started as a research project at the UW’s computer science school. The idea is to reduce the amount of cost and time it takes companies to develop and deploy deep learning software for specific hardware such as phones, cars, health devices, etc. — “using ML to optimize ML,” as OctoML CEO Luis Ceze explains.
Traction: OctoML is working with Qualcomm, Microsoft, AMD, Bosch, and many others. It has nearly 1,000 early access sign-ups for the “Octomizer,” its first TVM-based software-as-a-service offering. In December the startup’s tech showed “better model performance on Apple’s M1 chip than Apple’s core inferencing engine.” The company has 45 employees and expects to grow its headcount by more than 50% this year.
Competition: OctoML wants to be a better alternative to the default deployment path from machine learning frameworks such as TensorFlow or PyTorch, or hardware vendor-specific tools. It offers better performance and removes complexity, Ceze said. Amazon’s Sagemaker Neo is also based on Apache TVM, but is restricted to AWS-based deployments. The Octomizer can target any cloud and any edge device.
Leadership: Ceze is a UW professor who previously started Corensic, a debugging startup that F5 Networks acquired in 2012. He’s also a venture partner at Madrona Venture Group.
Ceze’s four co-founders include:
- Tianqi Chen, who received his Ph.D. from the Allen School and is CTO.
- Jason Knight, a former principal engineer and AI leader at Intel who earned a Ph.D. in electrical engineering at Texas A&M.
- Thierry Moreau, who earned his Ph.D. in 2018 from the Allen School and taught a graduate level machine learning class with Ceze.
- Jared Roesch, who earned his Ph.D. last year at the Allen School and previously worked at Zentopy, Invoca, and Mozilla Research.
Investors: Addition led the Series B round, which included participation from Madrona (which led the seed round) and Amplify Partners. OctoML raised a $15 million round in April 2020. Total funding to date is $47 million.
Go deeper: Ceze penned a blog post about the new funding and explained more about how the company’s tech works. From the post:
We aim to enable you to extract the best performance out of your machine learning models and automate the entire process of deploying the model to production: from model optimization, benchmarking, to packaging for deployment. By automating this entire process we accelerate your time-to-market while also significantly reducing your compute costs and enabling edge use cases. The performance optimization magic comes from applying machine learning to machine learning model optimization and compilation.
