Alif Semiconductor, a global leader in secure, connected, and energy-efficient AI and ML microcontrollers (MCUs) and fusion processors, announced that its Ensemble E4, E6, and E8 series now support the ExecuTorch Runtime—a quantization extension of the widely used PyTorch machine learning framework.
This integration allows developers to create lightweight AI models optimized for resource-limited hardware like MCUs, enabling low-latency and high-accuracy inference at the edge. With the built-in Arm Ethos-U85 NPU—capable of running transformer-based ML networks—developers can now leverage PyTorch with ExecuTorch Runtime to design and deploy generative AI applications directly on battery-powered edge devices. These include applications in smart glasses, human-computer interaction, healthcare and diagnostics, robotics, transportation, toys and education, smart homes, and smart city systems.
At the PyTorch Conference (Moscone West, San Francisco CA, 22-23 October), Arm demonstrated examples of generative AI applications compiled with ExecuTorch and running on Alif’s Ensemble E8 fusion processor, including:
- A small language model running on the Ensemble E8, capable of generating stories suitable for children in response to visual prompts, and extendable to verbal prompts.
- Real-time on-device speech-to-text models, suitable for integration into wearables such as smart glasses. The demo performs real-time transcription of speech to enable live captioning.
Reza Kazerounian, President of Alif Semiconductor, said: “Alif’s continuous innovation keeps us at the forefront of edge AI, now extending into the era of generative AI. With native support for the ExecuTorch Runtime on our Ensemble microcontrollers, we’re expanding what’s possible for AI at the MCU level. For embedded device manufacturers building next-generation intelligent products, Alif remains the trusted leader in bringing AI to the edge.”
Paul Williamson, Senior Vice President and General Manager, IoT Business at Arm said: “Generative AI at the edge is enabling a new class of intelligent, battery-powered devices that can understand and respond in real time. Using the ExecuTorch framework, developers can efficiently deploy PyTorch models on Alif’s Ensemble MCUs for low-power, on-device inference. This collaboration demonstrates how a unified ecosystem can scale intelligence across the edge, accelerating real-world AI innovation.”
The Alif DK-E8 development board used in the PyTorch Conference demonstrations, which supports development on the entire E4/E6/E8 series, is available to purchase now.
