NVIDIA
"National investment in compute capacity is a new economic imperative... countries are awakening to the need to invest in sovereign AI infrastructure" says Jensen Huang
An eight-way HGX H200 provides over 32 petaflops of FP8 deep learning compute and 1.1TB of aggregate high-bandwidth memory
"Cache misses have this weird massive non-linear effect into how much work the GPUs are doing, because we suddenly need to start recomputing all this stuff."
NVIDIA A100 80GB powered GPU instances are “immediately available" and a range more coming very soon.
The chipmaker says it can double the speed of inference on its H100 GPUs
Nvidia says the booming AI market has helped it turn in record financial results as its datacenter business remains strong
Nvidia has announced a new "superchip" design dubbed Grace Hooper as well as a service called AI-Workbench as part of a renewed push into the artificial intelligence space
A fully standards-based Ethernet with support for open Ethernet stacks (SONiC, Linux Switch) at cloud scale...
Harder, faster, stronger...