TodayToday's edition
Company we follow
Placeholder for the owner: write a short, sourced introduction to AMD coverage. Published stories are listed below. Do not add unsourced history or figures.
Data centers
Vultr plans a 20 MW supercluster of AMD Instinct MI355X GPUs in Chennai, with 288 GB of HBM3E per GPU, but has not said the GPU count, host site or start date.
Chips & Power Desk
Chips
AMD is moving its ZenDNN CPU inference library into Intel-driven oneDNN and joining the UXL Foundation as a steering member, giving PyTorch a single x86 code path for AI inference.
Chips & Power Desk