Nvidia H100 cluster on Coreweave cloud sets new Graph500 record
Nvidia and Coreweave have set a new Graph500 breadth first search record using a commercially available H100 GPU cluster that more than doubles the performance of rival systems.
AMD and Samsung explore 2 nm foundry deal for future Epyc and Ryzen chips
Samsung is in talks with AMD to manufacture next-generation Epyc and potentially Ryzen processors on its second-generation 2 nm SF2P process, a move that could give AMD a dual-foundry strategy alongside TSMC. The discussions build on a growing Artificial Intelligence hardware partnership that already spans high-bandwidth memory for AMD accelerators.
Nvidia introduces Nemotron 3 open models for multi agent artificial intelligence
Nvidia has launched the Nemotron 3 family of open models, data and libraries to support transparent and specialized multi agent artificial intelligence development, using a hybrid mixture-of-experts architecture. The lineup targets organizations moving from single chatbots to collaborative agent systems while aiming to reduce communication overhead, context drift and inference costs.
HDD prices jump as artificial intelligence storage demand strains supply
Hard disk drive prices are climbing as artificial intelligence and cloud workloads push manufacturers to near full capacity, raising concerns about potential shortages in 2025.
Nvidia acquires SchedMD to bolster open source workload management for Artificial Intelligence and hpc
Nvidia has bought SchedMD, the company behind the open source Slurm workload manager, and plans to keep it vendor neutral while deepening its role in high performance computing and Artificial Intelligence clusters.