OctoML Accelerates ML Innovation Across Arm Hardware and Embedded Environments
October 21, 2021
OctoML announced a collaboration with Arm to deploy next-generation machine learning (ML) applications and models across its suite of hardware.
The partnership is designed to enable Arm partners to upload machine learning models to the OctoML platform and receive optimized and packaged versions of the model fine-tuned to Arm hardware.
Arm is also contributing engineering effort to Apache TVM which provides companies developing ML on Arm technology one unified software stack to deploy models seamlessly across microcontrollers, GPUs, NPUs, and CPUs.
Apache TVM is a software framework that provides a unified layer between the machine learning frameworks—like PyTorch, TensorFlow—and the array of hardware solutions available. According to the companies, this means that ML models can be deployed anywhere from cloud to edge to mobile.
Arm's open source efforts in providing Apache TVM support to Arm Cortex-A processors, Cortex-M processors, Arm Mali-GPUs and Arm Ethos-NPUs, is designed to ensures that data scientists, software and embedded developers can now use a single software stack that works on the chips based on Arm technology.
Built on the Apache TVM open source framework, OctoML's Platform provides an automation framework that optimizes trained models to achieve optimal performance across hardware endpoints and cloud services—without compromising accuracy. The platformis enabled to address the challenge of optimizing ML models to match the resources at the edge, which opens up opportunities for a new wave of intelligent apps.
For more information, visit here.