Axelera AI develops AI processing units (AIPUs) and associated software like the Voyager SDK to accelerate AI inference workloads. Their hardware solutions, including Metis AIPUs on M.2 and PCIe cards, deliver high performance and power efficiency for edge computing applications. This technology enables customers to deploy complex deep neural networks for computer vision and analytics at a lower cost and power consumption than traditional GPU solutions.
Funding
$135.6M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Many edge computing applications, particularly in generative AI and computer vision, require significant computational power but are constrained by cost and energy consumption. Existing solutions often fail to deliver the necessary performance within these constraints, hindering the deployment of advanced AI at the edge.
Solution
Axelera AI addresses these challenges with the Metis AI Processing Unit (AIPU), a hardware solution designed for efficient AI acceleration at the edge. The Metis AIPU delivers high performance, up to 214 TOPS, with exceptional energy efficiency, achieving 15 TOPS per watt. This allows for cost-effective and energy-efficient deployment of generative AI and computer vision applications in various industries. Axelera AI also provides the Voyager SDK, which simplifies the deployment of deep neural networks on their hardware. The Metis AIPU is available in M.2 and PCIe form factors, as well as complete evaluation systems.
Target Audience
The primary target audience includes developers and integrators in retail, security, industrial automation, and other sectors who require high-performance, low-power AI inference at the edge.
Features
- Metis AIPU: AI accelerator delivering up to 214 TOPS
- Energy efficiency: 15 TOPS per watt
- Voyager SDK: Software development kit for model deployment and optimization
- M.2 AI Accelerator Card: Compact form factor for edge deployment
- PCIe AI Accelerator Card: High-performance card for demanding applications
- Evaluation Systems: Complete systems for rapid prototyping and deployment
- Digital In-Memory Compute (DIMC) architecture for energy efficiency
- Support for CNN-based Computer Vision applications