Revolutionizing AI and Machine Learning on Arm-based Hardware with Arm Kleidi Integration
If you are looking to enhance AI and machine learning workloads on Arm-based hardware, Arm has some exciting news for you. Arm is integrating its cutting-edge Arm Kleidi AI acceleration technology with PyTorch and ExecuTorch, the new on-device inference runtime from PyTorch, to bring unprecedented performance benefits from the edge to the cloud.
This groundbreaking partnership, announced on September 16, aims to empower the next generation of apps to run large language models (LLMs) on Arm CPUs. By directly integrating Arm Kleidi libraries into PyTorch and TensorFlow, Arm is paving the way for high-performance AI applications on Arm-based hardware.
Alex Spinelli, the vice president of developer technology at Arm, highlighted the significant impact Kleidi has made since its launch four months ago. Kleidi has accelerated development and unlocked major AI performance uplifts on Arm CPUs, making it easier for developers to leverage the power of AI on Arm-based systems.
In the cloud, Kleidi builds upon the work Arm has done to enhance PyTorch with the Arm Compute Libraries (ACL), offering a seamless integration for optimizing AI on Arm. With the upcoming integration of KleidiAI into ExecuTorch in October 2024, developers can expect even greater performance improvements when using these frameworks on Arm hardware.
With Arm’s commitment to advancing AI and machine learning on Arm-based hardware, developers can now harness the full potential of AI technologies without the need for additional optimization steps. By integrating Arm Kleidi technology into leading AI frameworks, Arm is making it easier for developers to build high-performance AI applications for a wide range of use cases.
Stay tuned for more updates on how Arm Kleidi integration is transforming AI and machine learning development on Arm-based hardware!