Lenovo has put the finishing touches on its ThinkSystem SR685a V3 server, which it says is an optimal solution for both enterprise, private on-premise AI and public AI cloud service providers.
Developed in collaboration with AMD, the server is specifically designed to meet the demanding computing needs associated with GenAI and large language models. With fast acceleration, large memory capacity and I/O bandwidth, the new powerhouse can manage significant data sets used in industries from healthcare and energy to financial services and climate science.
The AI supercomputer is powered by two top-of-the-line 4th generation AMD EPYC processors, each delivering up to 400W of output, coupled with eight AMD Instinct MI300X GPUs. It is fully connected to AMD Infinity Fabric and offers 1.5 TB of high-bandwidth memory capacity (HBM3) and up to 1 TB/s maximum theoretical GPU I/O bandwidth performance.
Up to 16 NVMe SSDs
ThinkSystem SR685a V3 supports up to 3 TB of RAM, consisting of 24 DDR5 DIMMs, and as an alternative to the eight AMD Instinct MI300X GPUs with 896 GB/s Infinity Fabric interconnects, it can support eight Nvidia H100/H200/B100 GPUs with NVLink interconnects processing at 900 GB/s.
The 8U2S rack server can accommodate up to 10x PCIe Gen5 x16 FHHL adapters (eight on the front connected to the PCIe switch for GPU connectivity, and two on the back directly connected to the main CPU). It supports up to sixteen 2.5-inch hot-swappable NVMe SSDs, as well as up to two M.2 drives for booting, with RAID support. In terms of power, eight hot-swappable PSUs ensure complete N+N redundancy, while everything is kept at an acceptable temperature via air cooling with an N+1 hot-swappable fan.
Management is handled by an XClarity Controller2 (XCC2), which provides high-level service processor control, as well as monitoring and alerting functions.
The ThinkSystem SR685a V3 is compatible with a variety of operating systems, including RHEL, Ubuntu, Alma Linux, Rocky Linux, and ESXi.
“Together with Lenovo, we are accelerating the AI transformation for the enterprise in multiple ways – helping customers through this monumental shift in computing while delivering robust end-to-end solutions at scale,” said Forrest Norrod, executive vice president and general manager, Data Center Solutions Group, AMD. “We have a proven track record of bringing great solutions to market together and are excited to add AMD Instinct MI300X to Lenovo’s portfolio, helping companies rapidly adopt AI.”
With applications spanning multiple industries, this new system can accelerate most compute-intensive AI workloads, and Lenovo is focusing its benefits primarily on the world of financial services, where it can help detect and prevent fraud and KYC initiatives ( know your customer). .
The Lenovo ThinkSystem SR685a V3 server can be that ordered nowprices available on request.