Moore Thread's first kilo-card intelligent computing center is launched to comprehensively accelerate the development of large models from computing power to ecology
The unveiling ceremony of Moore Thread’s KUAE Intelligent Computing Center, the first nationally produced 1,000-kilo-watt model training platform, was successfully held in Beijing. Announced the official launch of China’s first large-scale computing cluster based on domestically produced full-featured GPUs. At the same time, Moore Thread and many domestic partners initiated and established the Moore Thread PES-KUAE Intelligent Computing Alliance and the Moore Thread PES-Large Model Ecological Alliance to jointly consolidate domestic large models from intelligent computing infrastructure to large model training and inference. The integrated ecology continues to accelerate the development of my country's large model industry.
Moore Thread CEO Zhang Jianzhong brought major announcements in the keynote speech, including the large-model intelligent computing accelerator MTT S4000, and the Moore Thread KUAE platform, which is designed to provide powerful support for training and inference of large models with hundreds of billions of parameters. He said: "Moore Thread The official opening of the KUAE Intelligent Computing Center is an important milestone in the company's development. Moore Thread has built an intelligent computing product line from chips to graphics cards to clusters, relying on the multiple computing advantages of full-featured GPUs to meet the growing needs of large model training and Reasoning needs, with green and safe intelligent computing power, vigorously promote the implementation of multi-modal applications such as AIGC, digital twins, physical simulation, metaverse and the high-quality development of thousands of industries."
Intelligent computing accelerator card MTT S4000Both training and promotion Specially designed for large models
The Moore thread large model intelligent computing accelerator card MTT S4000 uses the third-generation MUSA core. A single card supports 48GB of video memory and 768GB/s of video memory bandwidth. Based on Moore Thread's self-developed MTLink1.0 technology, MTT S4000 can support multi-card interconnection and help accelerate distributed computing of hundreds of billions of large models. At the same time, MTT S4000 provides advanced graphics rendering capabilities, video encoding and decoding capabilities, and ultra-high-definition 8K HDR display capabilities to help implement comprehensive application scenarios such as AI computing, graphics rendering, and multimedia. What is particularly important is that with the help of Moore Thread's self-developed MUSIFY development tool, the MTT S4000 computing card can make full use of the existing CUDA software ecosystem and realize zero-cost migration of CUDA code to the MUSA platform.
KUAE Intelligent Computing Center solution integrates software and hardwareReady to use out of the box
The Moore Thread KUAE Intelligent Computing Center solution is based on a full-featured GPU and is a full-stack solution integrating software and hardware, including infrastructure with the KUAE computing cluster as the core, the KUAE Platform cluster management platform and the KUAE ModelStudio model service. Solve the construction and operation management problems of large-scale GPU computing power in an integrated delivery manner. This solution can be used out of the box, greatly reducing the time cost of traditional computing power construction, application development and operation and maintenance platform construction, and achieving rapid launch on the market for commercial operations.
