AI Briefing#skymizer
The latest AI and developer news about #skymizer, with the original source and a short summary.
The latest AI and developer news about #skymizer, with the original source and a short summary.
Taiwan's Skymizer has unveiled the HTX301, a PCIe AI accelerator that uses older-generation chips and memory to run a 700B-scale LLM at low power.
Skymizer has announced the HTX301 PCIe inference card, featuring 384GB of memory and around 240W power draw.
The HTX301-based PCIe card supports 700B LLM inference at about 240W.