ExecuTorch enables on-device inference capabilities across mobile and edge devices and will provide users of Alif’s Ensemble and Balletto devices with a seamless path to design, optimise, train, and deploy machine learning models directly on endpoint devices.
The integration will allow data and decisions to be processed immediately on-device, which enables privacy-aware personalisation, reduces power consumption, and will help to significantly increase the flexibility of on-device AI use-cases.
“Since we launched our Ensemble family of AI-Enabled MCUs into the market three years ago, we have seen a tremendous level of interest in transitioning machine learning closer to the source of the data,” commented Reza Kazerounian, president and co-founder at Alif Semiconductor. “ExecuTorch will significantly broaden the use cases that can be realised by this transition, and Alif is very excited to collaborate with PyTorch on bringing this to microcontroller devices.”
Alif is also collaborating with Arm on bringing support for hardware acceleration of transformer-based models for the first time to microcontroller devices, which will enable a simpler path for language models and other advanced use-cases to be deployed to edge devices using ExecuTorch.
The AI-enabled Ensemble MCUs and fusion processors from Alif Semiconductor are fully mass production qualified. Both evaluation boards and device samples are available.
