OctoML Provides Apache TVM Support For Snapdragon Platforms And SoCs
Leading machine learning acceleration platform helps enhance Qualcomm Technologies' processors to support ML-powered mobile applications
Sep 16, 2021, 11:08 ET
SEATTLE, Sept. 16, 2021 /PRNewswire/ -- OctoML today announced a collaboration with Qualcomm Technologies, Inc. to provide first-class Apache TVM support for Snapdragon® platforms and SoCs.
As part of this collaboration, OctoML has a strategic agreement to work closely with the Qualcomm's® Tensor Virtual Machine (TVM) compiler team to extend Apache TVM for Qualcomm® Hexagon™ processors. As a result, it is expected that Apache TVM will be enhanced to address the unique characteristics of Hexagon in order to make it a demonstrated leader in AI performance on power-constrained devices. These enhancements will be designed to drive fundamental innovation in Apache TVM that should benefit the entire Apache TVM community.
Built on the Apache TVM open-source framework, OctoML's Platform provides an automation framework that optimizes trained models to achieve optimal performance across a breadth of hardware endpoints and cloud services—without compromising accuracy. The platform readily addresses the challenge of optimizing ML models to match the resources at the edge, which opens up opportunities for a new wave of intelligent apps.
"We are excited to be working with OctoML to further expand Apache TVM coverage to our Qualcomm® AI Engine to help accelerate the deployment of ML applications and optimize models in the future," Jeff Gehlhaar, VP of Technology, Qualcomm Technologies, Inc.
This collaboration is made possible through Qualcomm Technologies' support of Apache TVM. Apache TVM is a software framework that provides a unified layer between the leading machine learning frameworks—like Tensorflow and Pytorch—and the vast array of hardware solutions. This innovation means that ML models can be deployed anywhere from cloud to edge to mobile.
"OctoML's ability to fully utilize hardware capabilities for machine learning, combined with the automation and accessibility of our SaaS platform, will greatly simplify the deployment of ML innovation across Qualcomm Technologies' powerful hardware," said Luis Ceze, CEO and co-founder, OctoML. "We are very excited to work with Qualcomm Technologies to unlock the power of their SoCs on our platform and enable the next-generation of ML applications at the edge."
Visit here to register for OctoML's limited access program.
Qualcomm, Snapdragon, and Hexagon are trademarks or registered trademarks of Qualcomm Incorporated.
Snapdragon, Qualcomm Hexagon, and Qualcomm AI Engine are products of Qualcomm Technologies, Inc. and/or its subsidiaries.
OctoML is a machine learning acceleration platform based in Seattle, Washington. OctoML aims to accelerate model performance while enabling seamless deployment of models across any hardware platform, cloud provider, or edge device. The company's investors include Addition, Madrona Venture Group, and Amplify Partners. OctoML was founded by creators of open-source Apache TVM, CEO Luis Ceze, CTO Tianqi Chen, CPO Jason Knight, Chief Architect Jared Roesch, and VP of Technology Partnerships Thierry Moreau. For more information, please visit https://octoml.ai/
Share this article