Tensor Processing Unit (TPU)
A Tensor Processing Unit (TPU) is a family of custom application-specific integrated circuits developed by Google to accelerate machine-learning computation.
AI Infrastructure
Explore AI Infrastructure through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: AI Compute
Articles that also belong to these categories. Counts cover all of AI Infrastructure.
All articles (329)AI Compute (133)AI Hardware (109)AI Companies (64)Data Centers (57)Developer Tools (47)NVIDIA (46)Open Source AI (46)AI Inference (32)Machine Learning (29)Chinese AI (19)Google (14)AI Agents (13)AI Energy (12)MLOps (11)Enterprise AI (10)Training & Optimization (10)Computer Science (8)Information Retrieval (8)OpenAI (8)Deep Learning (7)Large Language Models (7)AI Policy & Regulation (6)Meta AI (6)People (6)AI Tools & Products (5)Artificial Intelligence (5)Microsoft (5)Finance AI (4)Robotics (4)AI Code Generation (3)AI Research (3)Anthropic (3)Generative AI (3)Mixture of Experts (3)Reinforcement Learning (3)Venture Capital (3)AI Events (2)AI Models (2)AI Safety (2)Model Architecture (2)Model Evaluation (2)Physical AI (2)Programming Languages (2)Software Development (2)AI in Cybersecurity (1)AI in Gaming (1)Agentic Commerce (1)Algorithms (1)Data & Datasets (1)Data Science (1)Edge computing (1)Embodied AI (1)Image Generation (1)Mathematics (1)Neural Networks (1)Research Organizations (1)Robotics Companies (1)Video Generation (1)
Showing 121-133 of 133 articles
Tenstorrent
Tenstorrent is a North American artificial intelligence hardware and intellectual property company that designs processors for AI training and inference on the basis of the open-standard RISC-V instruction set…
Three-Body Computing Constellation
The Three-Body Computing Constellation (Chinese: 三体计算星座) is a planned network of computing satellites led by Zhejiang Lab, a Zhejiang provincial laboratory in Hangzhou, China.
UALink
UALink (Ultra Accelerator Link) is an open industry standard for scale-up interconnect between AI accelerators that lets up to 1,024 accelerators inside a single pod read and write each other's memory directly…
Ultra Ethernet
Ultra Ethernet is an open networking specification that reworks Ethernet into a high performance fabric for large AI training clusters and high performance computing, giving operators an interoperable
Vast.ai
Vast.ai is a cloud-based GPU rental marketplace that connects independent hardware operators (called hosts) with developers, researchers and companies looking to rent compute by the second.
Voltage Park
Voltage Park is a United States cloud computing company that operates a fleet of NVIDIA H100 graphics processing units for artificial intelligence training and inference workloads.
Wormhole (Tenstorrent)
Wormhole is the second-generation AI accelerator application-specific integrated circuit (ASIC) designed by Tenstorrent, a Toronto-based hardware startup led by chip architect Jim Keller.
bfloat16
bfloat16 (short for Brain Floating Point Format, sometimes written BF16) is a 16-bit floating-point number format that uses one sign bit, eight exponent bits, and seven mantissa bits
d-Matrix
d-Matrix is a privately held American semiconductor company headquartered in Santa Clara, California that builds accelerators, I/O cards and software for AI inference in data centers.
d-Matrix Raptor
Raptor is the second-generation AI inference accelerator from d-Matrix, a Santa Clara semiconductor startup, and the first commercial chip built on the company's 3D stacked digital in-memory compute technology
xAI Colossus
Colossus is an artificial-intelligence supercomputer and GPU training cluster in Memphis, Tennessee, built by xAI and owned since February 2026 by SpaceX, which acquired xAI.
xAI Colossus 2
xAI Colossus 2 is the second-generation AI supercomputer and data-center complex built by xAI, the artificial intelligence company founded by Elon Musk, in the Memphis, Tennessee, metropolitan area.