This project is suspended: no new articles or editions will be published. The archive stays available.
AI chips are specialized processors — GPUs and custom accelerators — built to train and run AI models far more efficiently than general-purpose hardware. This hub covers new chips, the companies designing them, and the supply race behind the AI boom.
OpenAI published its first benchmark results for Jalapeño, an in-house AI chip built with Broadcom, claiming it beats Nvidia's Blackwell and Rubin systems on inference speed and power efficiency.
Read more →Anthropic has hired Amir Salek, who built and led Google's Tensor Processing Unit program for nearly a decade, to help run its own in-house chip effort, Bloomberg reported.
Read more →Marvell issued Google a warrant worth up to $12.2 billion in stock, tied to an expanded deal for custom AI chips in Google's TPU ecosystem, an SEC filing shows.
Read more →Tesla and SpaceX will invest $16.8 billion in the first phase of Terafab, a Texas chip plant meant to supply AI compute for humanoid robots, robotaxis and orbital data centers.
Read more →Anthropic said it is building an internal team to design custom AI chips for Claude, aiming to run its models faster and more cheaply without dropping its other hardware partners.
Read more →
Silicon photonics moves data with pulses of light instead of electricity, letting AI chips exchange far more data using far less power as GPU clusters scale to hundreds of thousands of chips.
Read more →The U.S. Commerce Department is giving GlobalFoundries up to $300 million to build optical links for AI chips, part of an $874 million CHIPS push across seven firms.
Read more →
CXMT is China's biggest DRAM memory-chip maker. Its blockbuster Shanghai IPO made it the country's most valuable listed firm — here's what that means for AI hardware.
Read more →
EUV lithography is the ultra-precise process that etches modern AI chips — and only one company in the world, ASML, can build the machines that do it.
Read more →
Advanced packaging fuses multiple silicon dies into one AI chip. Here's how it works, and why it — not raw chip fabrication — has become the industry's tightest supply bottleneck.
Read more →Samsung Electronics and Broadcom signed a memorandum of understanding worth more than $200 billion covering memory, chip manufacturing and packaging for AI accelerators through 2030.
Read more →
Huawei is a Chinese tech giant now racing to build its own AI chips and cloud infrastructure after US export controls cut off its access to Nvidia's GPUs.
Read more →Nvidia and South Korea's SK Group signed letters of intent for a $500 billion-plus AI infrastructure and memory-chip partnership, including a new 2-gigawatt AI factory.
Read more →Disaggregated inference splits an AI model's two work stages onto separate chips built for each job — a technique now expanding beyond Nvidia to AMD and Cerebras hardware.
Read more →AMD and Cerebras unveiled a joint AI inference system that splits chip work between AMD's Helios servers and Cerebras' wafer-scale engine, claiming up to 5x higher efficiency per watt.
Read more →
Qualcomm built its business on the Snapdragon chips inside most Android phones — and is now challenging Nvidia with AI chips built for data centers.
Read more →
A TPU is Google's custom AI chip, purpose-built to run the matrix math behind neural networks — and now rented out by the gigawatt to power rival labs' models too.
Read more →
AMD Instinct is AMD's line of data-center GPUs built to train and run AI models — the main hardware challenger to Nvidia's dominance in AI computing.
Read more →
AMD unveiled its Instinct MI400 AI chips and Helios rack systems on July 23, claiming 34x faster inference, with OpenAI, Meta and Anthropic on hand.
Read more →
An AI PC pairs a normal processor with a dedicated NPU chip that runs AI features like transcription, translation, and image generation locally, without sending data to the cloud.
Read more →Etched builds a chip that only runs transformer models, betting narrow focus beats Nvidia's flexibility — and investors are reportedly valuing the three-year-old startup at up to $20 billion.
Read more →