QNAP® Systems, Inc. today officially launched the TS-2888X, an AI-Ready NAS specifically optimized for AI model training. Built using powerful Intel® Xeon® W processors with up to 18 cores and employing a flash-optimized hybrid storage architecture for IOPS-intensive workloads, the TS-2888X also supports installing up to 4 high-end graphics cards and runs QNAP’s AI developer package “ QuAI”. The TS-2888X packs everything required for machine learning AI, greatly reducing latency, accelerating data transfer, and eliminating performance bottlenecks caused by network connectivity to expedite AI implementation.
Conventional AI workstations usually have massive price tags, and the complexity of configuring hardware and software is an obstacle for most data scientists and developers. The use of public clouds for storage and training may also raise concerns when using sensitive data. QNAP’s TS-2888X introduces an all-in-one AI solution that integrates huge storage potential, powerful computing, a ready-to-use AI environment, and comprehensive data protection to supplement AI workflows. It not only serves as a Training Server for AI models, but can also serve as an Inference Server, thereby further lowering the R&D entry barrier, making AI development more feasible and easily accessible.
“The age of AI is upon us, and we are witnessing its transformative effects throughout a wide range of industries, including healthcare, IT, retail, and surveillance,” said David Tsao, Product Manager of QNAP. “The TS-2888X AI-Ready NAS combines storage, computing, and a user-friendly AI software environment to reduce the time and complexity of implementing and managing AI tasks, while also providing cost-efficient and accessible AI development.”
The AI-Ready TS-2888X features Intel® Xeon® W processors with up to 18 cores and 36 threads and up to 4.5 GHz with Intel® Turbo Boost Technology 2.0 to deliver uncompromising performance. Up to 512 GB DDR4 ECC RDIMM 2666 MHz RAM is supported, providing ample space for huge projects while protecting against potential memory errors. The TS-2888X supports mainstream NVIDIA®, AMD® and Intel® accelerator cards, providing eight PCIe slots and a 2,000 watt 80Plus Platinum PSU that accommodates up to 4 high-end graphics cards to unleash tremendous computing power. To meet the simultaneous needs for scale and performance, the TS-2888X employs a hybrid storage architecture with eight 3.5-inch SATA 6Gb/s drive bays for hard drives, sixteen 2.5-inch SATA 6Gb/s drive bays for SSDs, and four 2.5-inch drive bays that support U.2 PCIe Gen3 x4 NVMe SSDs. This hybrid storage architecture provides the ability to enable SSD caching or auto-tiering to boost performance-demanding applications. There are six smart fans that separately detect temperatures in different zones (CPU, PCIe slots, power supply unit, and storage) to provide smarter, quieter, and energy-efficient cooling.
The TS-2888X introduces a comprehensive software environment for organizations to easily set up and maintain AI applications. The exclusive QuAI – an AI developer package to quickly build, train and optimize AI models running on the NAS – enables a range of open-source tools and frameworks (including Caffe, TensorFlow, AlexNet, FaceNet, and more) for the AI workflows readily available to users. The TS-2888X also features flexible backup tools and snapshot protection to assure data security while also allowing efficient disaster recovery.
QNAP’s AI solution has been put into practice in cooperation with a renowned medical research institute in Taiwan, and successfully realized a healthcare AI diagnostic system for age-related macular degeneration. The AI result not only significantly improves diagnostic accuracy and efficiency, but also creates possibilities to aid organizations that lack medical resources.