News More

• 

  15 Sep 2026

  Cornelis targets inference accelerator utilization with $205M expansion into scale-up

• 

  28 Aug 2026

  Meta bakes networking on-chip in custom silicon designed to cut CPU hops

• 

  26 Jun 2026

  Openchip and SUSE partner to drive European sovereign at the chip level

• 

  27 May 2026

  FuriosaAI partners with Broadcom for development of AI inference chips

• 

  07 May 2026

  AMD debuts MI350 PCIe card to accelerate enterprise AI workloads

• 

  27 Jan 2026

  Microsoft reveals Maia 200 & network architecture pushing scale-up inference efficiency

• 

  17 Nov 2025

  Nvidia enlists Arm as NVLink Fusion partner in major AI interconnect coup