The SAKURA-II AI Accelerator is a state-of-the-art energy-efficient AI processing unit designed to meet the demanding needs of generative AI applications. Boasting up to 60 TOPS performance, this accelerator is built on EdgeCortix's patented Dynamic Neural Accelerator architecture that allows high efficiency and low power consumption in edge AI tasks. It supports a wide array of models including Llama 2, Stable Diffusion, ViT, and large transformer and convolutional networks, typically operating within an 8W power envelope.
Offering enhanced DRAM bandwidth and a maximum memory capacity of 32GB, SAKURA-II is optimized for real-time data streaming and efficient handling of large language models (LLMs) and vision-based AI workloads. This accelerator achieves exceptionally high AI compute utilization and provides robust energy-efficient performance, making it ideal for advanced applications in vision, language, audio, and more.
The accelerator is available in modular M.2 and PCIe card formats, facilitating seamless integration into existing systems. These form factors ensure that the SAKURA-II can be effortlessly integrated into space-constrained or power-limited environments, providing the best choice for both development and deployment phases of edge AI initiatives.
