AMD buys Taalas and a very different idea about AI inference
AMD adds hard-wired inference to the Instinct toolbox.
AMD Instinct 455X targets Nvidia’s Rubin directly
320 billion transistors, 72-GPU rack scale—Scale up, scale out.
AI demand pushes hardware prices higher
Chips, memory, consoles all cost more
SambaNova could cap AI CapEx
Hybrid inference extends GPU investments.
DeepSeek moves toward its own AI chip
Chip said to be for inference rather than training.
Bolt gets an award at ISC HP 2026
Bolt’s Zeus gets noticed, wins Nimbus award for HPC GPU innovation.
Executive interview: Michael Förtsch on Q.ANT’s photonic computing bet
Photonic NPU plugs into practical AI acceleration.
Imagination gets an automotive chiplet story
Imagination joins CHASSIS’ Automotive Base Die project.
Vortex expands open RISC-V graphics
Version 3.0 adds graphics and AI.
Intel aims Crescent Island at inference
LPDDR5X memory targets practical AI deployment.
Neurophos: Interview with CEO Patrick Bowen
Understanding the math needed for AI is critical.
Alibaba’s T-Head builds China’s Nvidia alternative
The Zhenwu M890 ships at scale—and a two-generation roadmap follows behind it.