Latest about AI
Microsoft Azure CTO claims distribution of AI training is needed as AI datacenters approach power grid limits
Microsoft, other AI giants could take a page from Chinese researchers, who trained an AI model using multiple datacenters at once.
Arm's partners develop 2nm AI processor using Arm's Neoverse
Arm's Total Design ecosystem is now a year old and has grown to include 30 participants all working on AI chiplet platforms based on Arm's Neoverse CSS V3
TSMC could build more fabs in Europe - Chairman of Taiwan's National Science Council
Head of Taiwan's National Science Council says TSMC is planning additional fabs in Europe. TSMC denies that such a decision has been made.
Microsoft Azure flaunts world's first custom Nvidia Blackwell racks
Non-Nvidia servers running Blackwell are up and running.
Supermicro's datacenter-scale liquid cooling solution sets the stage for Nvidia Blackwell
Supermicro develops datacenter-scale liquid cooling solution for next-generation AI servers based on Nvidia Blackwell GPUs.
Chinese company claims breakthrough in developing domestic silicon photonics chip
JFS Laboratory develops silicon photonics for China's next-generation of AI and HPC datacenters.
CUDA-beating ZLUDA breathes new life with financial backing from unknown party — pivots to AI workloads across multiple GPU vendors
ZLUDA, a CUDA translation layer, gets new funding and therefore refocuses to AI software and multiple GPU vendors support.
BrainChip unveils AI NPU that consumes less than a milliwatt
BrainChip's Akida Pico has sub-milliwatt power consumption which opens up a world of small, battery-powered AI applications for healthcare and military use
