Taalas bets on hard‑wired models to beat GPUs at inference
Toronto start-up Taalas fixes trained LLMs directly in silicon.
Vaire Computing bets on reversible chips
Sunnyvale, CA, start-up tackles AI power problem at the physics level.
SK Hynix backs Semidynamics AI chips
Strategic investment accelerates memory-first AI inference platform.
Snap and Qualcomm expand XR collaboration
Long-term Snapdragon deal advances next-gen intelligent AR glasses.
Socionext’s custom XPU and AI data center chiplet platform
Partners up with Arm’s CPU.
Jon Peddie Research releases its Q1’26 AI Processors Quarterly Update series report
Now 135 companies chasing $493 billion market.
Nvidia announces a pixel-free rendering system
Originally thought impossible, Nvidia creates images without pixels.
Rebellions’ Rebel100 NPU
Designed for servers and pods.
More money poured into AI processors and data centers
Data centers and AI LLM companies aren’t the only ones raising cash.
Fujitsu joins the AIP crowd with an NPU
Targeted at inference servers using advanced Japanese semi production.
AI processor architectures are evolving almost as fast as LLMs are
AGI will not be realized with just more clever software.
Local opposition, not ROI, will determine AI’s build-out pace
Legislation won’t stop it.