Inference is splitting in two — Nvidia’s $20B Groq bet explains its next act

Nvidia’s $20 billion strategic licensing deal with Groq represents one of the first clear moves in a four-front fight over ...
Guru3D

NVIDIA Feynman GPUs Rumored to Add Stacked SRAM for AI Workloads

Leaks suggest that NVIDIA’s future Feynman GPU architecture, expected around 2028, could introduce stacked SRAM memory blocks ...
Semiconductor Engineering

The Uncertain Future Of In-Memory Compute

Experts at the Table — Part 2: Semiconductor Engineering sat down to talk about AI and the latest issues in SRAM with Tony Chan Carusone, chief technology officer at Alphawave Semi; Steve Roddy, chief ...
Semiconductor Engineering

Mixed SRAM And eDRAM Cell For Area And Energy-Efficient On-Chip AI Memory (Yale Univ.)

“AI chips commonly employ SRAM memory as buffers for their reliability and speed, which contribute to high performance. However, SRAM is expensive and demands significant area and energy consumption.
Forbes

d-Matrix Emerges From Stealth With Strong AI Performance And Efficiency

Startup launches “Corsair” AI platform with Digital In-Memory Computing, using on-chip SRAM memory that can produce 30,000 tokens/second at 2 ms/token latency for Llama3 70B in a single rack. Using ...
ZDNet

Could a strange new memory chip unlock mysteries of AI?

Modern artificial intelligence lacks a strong theoretical basis, and so it's often a shrug of the shoulders why it works at all (or, oftentimes, doesn't entirely work). One of the deepest mysteries of ...