VisionFive 2 AI Kit: Pre-Sale Begins -- RISC-V Powered AI Computing
October 24, 2024 -- VisionFive 2 AI Kit can officially purchase on October 24th. The kit is jointly launched by StarFive, the leader of RISC-V software and hardware ecology in China, and Hailo, a leading chip manufacturer of edge AI processors. It aims to provide the most cost-effective high-performance RISC-V AI solutions for applications in edge computing, industrial intelligence, security, robotics, gateway routing, smart home and other fields.
VisionFive 2 and Hailo-8L M.2 AI acceleration module
VisionFive 2 AI Kit bundles the VisionFive 2 high performance RISC-V SBC with a Hailo-8L M.2 AI acceleration module. It provides an low latency and power efficient way to integrate complex AI vision applications and efficiently perform deep learning inference tasks such as object recognition, image segmentation, and pose analysis.
StarFive VisionFive 2 is the world’s first high-performance RISC-V single board computer (SBC) with an 3D integrated GPU. It equipped with JH-7110 multimedia RISC-V boasts a quad-core 64-bit RISC-V CPU JH-7110 , running up to 1.5 GHz. With high performance, rich interfaces, flexible scalability, abundant software resources, and extremely high playability, VisionFive 2 is the best choice for open source enthusiasts to explore the RISC-V world.
The VisionFive 2 SBC, combined with the Hailo-8L M.2 AI acceleration module, can provide up to 13 TOPS of AI computing power and support many out of the box AI applications through a powerful software kit (https://hailo.ai/developer-zone/software-downloads/) and Model Zoo (https://github.com/hailo-ai/hailo_model_zoo/tree/master/docs/public_models/HAILO8L). Users can select trained neural network models, quickly deploy and optimize them, and run them on VisionFive 2 AI Kit.
VisionFive 2 AI Kit Features:
- High performance: Can provide up to 13 TOPS of computing power
- High energy efficiency ratio: The Hailo-8L M.2 AI acceleration module, with its excellent energy efficiency ratio, can release powerful AI processing capabilities in a low-power state
- Real time processing: Supports real-time processing of tasks such as object detection, image classification, and speech recognition, improving the response speed and intelligence level of applications
- Easy to integrate: The M.2 M key interface design of VisionFive 2 can be quickly integrated with the Hailo-8L M.2 AI acceleration module, simplifying the deployment process
- Ready to use: Powerful software kit for rapid deployment of state-of-the-art deep learning models and applications
The VisionFive 2 AI Kit provides powerful inference support for running deep learning models such as YOLOv5, YOLOv8, MobileNet_SSD, significantly enhanced the performance of applications such as object detection, pose recognition, image segmentation, and face recognition. It can be widely applied in various scenarios: as the core of home automation and security systems, this kit can achieve intelligent monitoring, facial recognition, and behavior analysis, creating a safe and convenient smart home environment; in industrial scenarios, this kit can be used for machine vision systems to perform product inspection, quality control, and robot navigation, improving production efficiency and safety; as a high-performance RISC-V platform, this kit is suitable for educational and research purposes, supporting the development and testing of AI applications, and providing strong support for academic research and technological innovation.
- VisionFive 2 AI Kit is now available for pre-sale, StarFive RVspace Community [Buy Now] has launched the purchase link:
https://rvspace.org/en/application/Buy_VF2_AI_Kit
- VisionFive 2 AI Kit [User Guide] will be released to the RVspace community recently，please visit:
- For complete product information on the Hailo-8L M.2 AI acceleration module, please visit:
Related Semiconductor IP
- RISC-V CPU IP
- RISC-V Vector Extension
- RISC-V Real-time Processor
- RISC-V High Performance Processor
- 32b/64b RISC-V 5-stage, scalar, in-order, Application Processor. Linux and multi-core capable. Maps upto ARM A-35. Optimal PPA.
Related News
- Andes Technology Showcases Leadership in AI and Automotive Applications at RISC-V Summit Europe 2024
- ESWIN Computing Pairs SiFive CPU, Imagination GPU and In House NPU in Latest RISC-V Edge Computing SoC
- X-Silicon Introduces the World's First Vulkan Driver Implementation for RISC-V, Enabling an entire Ecosystem of 3D Graphics, AI and Compute for Low-Power, Mobile, Edge and IOT Devices
- JEDEC Unveils Plans for DDR5 MRDIMM and LPDDR6 CAMM Standards to Propel High-Performance Computing and AI
Latest News
- RaiderChip NPU for LLM at the Edge supports DeepSeek-R1 reasoning models
- The world’s first open source security chip hits production with Google
- ZeroPoint Technologies Unveils Groundbreaking Compression Solution to Increase Foundational Model Addressable Memory by 50%
- Breker RISC-V SystemVIP Deployed across 15 Commercial RISC-V Projects for Advanced Core and SoC Verification
- AheadComputing Raises $21.5M Seed Round and Introduces Breakthrough Microprocessor Architecture Designed for Next Era of General-Purpose Computing