About Us
Based in Toronto, Canada and Mountain View, California, CentML offers a customizable platform for AI model deployment with automated compute optimizations, flexible configuration options, and streamlined deployment.
The CentML platform efficiently utilizes hardware resources and supports a range of accelerators, from NVIDIA and AMD GPUs to Google TPUs and AWS Inferentia chips. Our researchers and engineers continually integrate cutting-edge techniques for inference optimization.
CentML gives customers of any size access to a highly performant, cost optimized full stack solution for AI deployment on any cloud or on-premise environment.
Our Mission
CentML was founded by Professor Gennady Pekhimento, head of the EcoSystems research group at the University of Toronto, and other experts from Amazon, Google, Microsoft, Nvidia, Intel, and IBM.
CentML's mission is to accelerate AI adoption by offering a full stack solution for AI/ML inference that abstracts away the complexity of hardware and software optimization.