CPUs and Processors | News, how-tos, features, reviews, and videos
Nvidia may have to make other customers wait if it wants to fulfill a reported $16 billion in outstanding orders from Chinese customers for its H20 chips before a possible US government ban on sale of them to China takes effect.
IBM is making Intel Gaudi 3 AI accelerators available on IBM Cloud to help customers scale gen AI workloads and optimize performance for AI inferencing and fine-tuning.
Its GB200 NVL72 system delivered up to 30 times higher throughput on the Llama 3.1 405B workload compared to firm’s H200 NVL8, Nvidia said.
AMD says its ZT acquisition will further the combination of AMD CPU, GPU and networking silicon, and its deal with Rapt will bolster AI inference and training applications.
The silicon photonics startup has announced new products to tackle interconnect bottlenecks costing enterprises millions in wasted computing power.
Networking, liquid cooling, infrastructure plans, and partners will all play a big role in Nvidia’s future.
Nvidia is known for chips, but it's repositioning itself as an infrastructure provider.
The move follows Arm’s recent foray into direct chip sales with the Meta deal, signaling a major shift in the data center processor landscape.
In the age of AI, high-speed optical networking is more important than ever. Co-packaged optics removes the need for pluggable optics, simplifying network design while increasing resiliency.
HPE news from Nvidia GTC includes a new Private Cloud AI developer kit, Nvidia AI blueprints, GPU optimization capabilities, and servers built with Nvidia Blackwell Ultra and Blackwell architecture.
Sponsored Links