HBM4E

FuriosaAI Ditches GPU Playbook For 2nm Broadcom-Built Inference Chip, Claims HBM4/E Bandwidth Beats Even The Most Efficient GPUs

vm_adminMay 27, 2026

By Hassan Mujtaba Publication Date: 2026-05-27 15:40:00 FuriosaAI and Broadcom have partnered to build a high-performance AI accelerator chip featuring…

Nvidia

Samsung accelerates HBM4E development to ship samples to Nvidia- report

vm_adminApril 16, 2026

By Ambar Warrick Publication Date: 2026-04-15 23:38:00 Samsung accelerates HBM4E development to ship samples to Nvidia- report

Nvidia

Nvidia demonstrates Rubin Ultra tray, the world’s first AI GPU with 1TB of HBM4E memory — new chips will slot into Kyber racks

vm_adminMarch 17, 2026

By Anton Shilov Publication Date: 2026-03-17 10:20:00 Nvidia on Monday demonstrated its next-generation tray for its data center GPU known…