QNAP launches an affordable, Lite-Managed 10GbE switch designed for creators.
Cisco Introduces 8223 High-Performance Fixed-Port Router, Built to Handle AI Data Traffic
Cisco introduces its 8223 high-performance fixed router, based on the Silicon One P200 chip, which is said to deliver 51.2Tb/s.
AI ◇
Enterprise
Next-Gen Cooling: ZutaCore Debuts Server and OmniTherm Tech
Waterless cooling has been redefined for AI with a turnkey server and cold plate, thanks to the collaboration between ZutaCore and ASRock Rack on B300 clusters.
Intel VROC Finds a New Home with Graid Technology
Graid licenses Intel VROC to unify CPU and GPU RAID, delivering high-performance protection for NVMe-heavy AI, HPC, and enterprise workloads.
Intel Targets AI inference at OCP 2025 with Crescent Island GPU and Gaudi 3 Racks
With an emphasis on AI inference, Intel unveiled a new data center GPU and a rack-scale reference design for Gaudi 3.
HPE Sharpens iLO 7 and Gen12 Servers at OCP 2025
At OCP 2025, HPE upgrades iLO 7 and Gen12 servers with stronger security, modular designs, NVIDIA support, and MLPerf-leading AI results.
Broadcom Thor Ultra: UEC-Compliant 800G AI Ethernet NIC for 100K+ XPU Scale-Out
Broadcom’s Thor Ultra 800G AI Ethernet NIC is designed for clusters with more than 100,000 XPUs.
AI ◇
Enterprise
NVIDIA Offers a Preview of What’s Next for Gigawatt-Scale AI Factories at the OCP Global Summit
NVIDIA previews Vera Rubin NVL144, an MGX-generation open-architecture rack server.
Intel Unwraps Core Ultra Series 3 “Panther Lake” and Xeon 6+ “Clearwater Forest” on Intel 18A
Intel Panther Lake and Clearwater Forest processors are built on an 18A process node.
IBM Spyre Accelerator: Low-Latency Inference for Generative and Agentic AI on IBM Z, LinuxONE, and Power
IBM’s low-latency inference engine, Spyre Accelerator, will be generally available beginning October 28 for z17 and LinuxONE 5. Power 11 system users will get access shortly thereafter.
Amazon