MTIA
MTIA (Meta Training and Inference Accelerator) is a family of custom silicon chips that Meta designs for use in its own data centers rather than for sale.
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 61-120 of 133 articles
Meta Compute
Meta Compute is a top-level organization that Meta created in January 2026 to plan, build, and run the gigawatt-scale data center capacity behind its push toward artificial general intelligence and what the…
Meta MTIA
MTIA (Meta Training and Inference Accelerator) is a family of custom AI chips that Meta designs in-house to run its largest artificial intelligence workloads, beginning with the deep learning recommendation…
Microscaling formats
Microscaling (MX) formats are a family of low-precision number formats for machine learning in which a small block of values, normally 32 of them, shares one common scale factor while each value is stored in a…
Microsoft Azure
Microsoft Azure is the public cloud computing platform operated by Microsoft, and the world's second-largest cloud provider, behind Amazon Web Services (AWS) and ahead of Google Cloud.
Microsoft Fairwater
Fairwater is Microsoft's name for a class of large AI datacenter built to train and serve frontier artificial intelligence models.
Microsoft Maia 200
Microsoft Maia 200 is a custom artificial intelligence accelerator designed by Microsoft for inference workloads in the Azure cloud.
Modal (platform)
Modal is a serverless cloud computing platform that lets developers run compute-intensive artificial intelligence, machine learning, and data-processing workloads on cloud GPUs by writing ordinary Python, with…
NVHBM
NVHBM is an announced custom high-bandwidth memory architecture from NVIDIA for custom AI accelerators that participate in the company's NVLink Fusion platform. NVIDIA introduced it on August 26, 2026.
NVIDIA AI compute infrastructure financing platforms
The NVIDIA AI compute infrastructure financing platforms are a set of proposed, independently run financing vehicles that NVIDIA announced on August 10, 2026, together with Apollo, BlackRock, Blackstone…
NVIDIA B200
The NVIDIA B200 is a data center GPU based on the NVIDIA Blackwell microarchitecture, announced by Jensen Huang at NVIDIA's GTC conference in San Jose on March 18, 2024.
NVIDIA DGX
NVIDIA DGX is NVIDIA's line of integrated artificial-intelligence supercomputers: systems that package the company's highest-end data-center GPUs, CPUs, high-speed NVLink and NVSwitch interconnects…
NVIDIA DGX B300
The NVIDIA DGX B300 is an 8-GPU AI supercomputer node built around NVIDIA's Blackwell Ultra architecture.
NVIDIA DGX Cloud
NVIDIA DGX Cloud is a managed AI-supercomputing-as-a-service offering from Nvidia that rents enterprises access to multi-node clusters of NVIDIA DGX infrastructure plus the NVIDIA AI software stack over the…
NVIDIA DGX Station
NVIDIA DGX Station is a line of deskside artificial intelligence workstations from NVIDIA, each marketed as a "personal AI supercomputer" that puts data-center-class compute next to a developer's desk rather…
NVIDIA DGX SuperPOD
The NVIDIA DGX SuperPOD is a reference-architecture artificial intelligence supercomputer designed and sold by Nvidia.
NVIDIA Exemplar Cloud
NVIDIA Exemplar Cloud is a validation program run by NVIDIA that certifies cloud providers whose GPU clusters reproduce at least 95% of the training throughput NVIDIA measures on its own reference architecture…
NVIDIA GB300 NVL72
The NVIDIA GB300 NVL72 is a liquid-cooled, rack-scale AI computing system that integrates 72 NVIDIA Blackwell Ultra (B300) GPUs and 36 Arm-based NVIDIA Grace CPUs into a single NVLink fabric, delivering 1.1…
NVIDIA GH200 Grace Hopper Superchip
The NVIDIA GH200 Grace Hopper Superchip is a single-module processor from NVIDIA that combines a 72-core Grace Arm CPU with a Hopper-generation H100-class GPU on one package
NVIDIA H100
NVIDIA H100 (also called the H100 Tensor Core GPU) is a data-center graphics processing unit built by NVIDIA on the Hopper microarchitecture, fabricated with over 80 billion transistors on a custom TSMC 4N (4…
NVIDIA HGX
NVIDIA HGX is a family of accelerated-server platform designs built around tightly connected data-center GPUs. It is not one immutable board specification.
NVIDIA MGX
NVIDIA MGX is a modular reference architecture that NVIDIA publishes so that server makers and contract manufacturers can build accelerated systems around NVIDIA GPUs, CPUs, DPUs and networking without…
NVIDIA Quantum-X Photonics
NVIDIA Quantum-X Photonics is a family of co-packaged-optics network switches that NVIDIA announced at its GTC conference on March 18, 2025.
NVIDIA Rubin Ultra
NVIDIA Rubin Ultra is a planned data-center GPU platform from Nvidia, the mid-cycle "Ultra" refresh of the Rubin generation.
NVIDIA Spectrum-6
NVIDIA Spectrum-6 is an Ethernet switch ASIC and system architecture for large AI infrastructure.
NVIDIA Spectrum-X Photonics
NVIDIA Spectrum-X Photonics is a co-packaged optics (CPO) Ethernet switch platform from Nvidia, announced at the company's GPU Technology Conference (GTC) on March 18, 2025.
NVIDIA Spectrum-XGS
NVIDIA Spectrum-XGS, marketed in full as NVIDIA Spectrum-XGS Ethernet, is a networking technology from NVIDIA designed to link several geographically separated data centers into a single
NVIDIA Vera (CPU)
NVIDIA Vera is a custom Arm-based data center central processing unit from NVIDIA, marketed by the company as "the CPU for agents," a processor designed first for agentic AI workloads rather than the…
NVLink Fusion
NVLink Fusion is a program and silicon technology from NVIDIA that opens its NVLink high speed interconnect to third party chips.
Nebius
Nebius is an AI cloud company incorporated in the Netherlands and listed on the Nasdaq stock exchange under the ticker symbol NBIS
Neocloud
A neocloud is a cloud computing company whose business is renting out GPU capacity for artificial intelligence workloads, rather than selling the broad catalogue of storage, database, networking and…
Nscale
Nscale is a British AI infrastructure company, usually described as a neocloud, that builds GPU-dense data center capacity and rents large-scale compute to hyperscalers, AI labs, and governments.
Nvidia-OpenAI partnership
The Nvidia-OpenAI partnership is a strategic agreement announced on September 22, 2025, under which NVIDIA said it intends to invest up to $100 billion in OpenAI as OpenAI builds out a large amount of new…
Open Compute Project
The Open Compute Project (OCP) is a community that develops and shares designs, specifications, and related engineering work for computing infrastructure.
OpenAI-Broadcom AI accelerators
The OpenAI-Broadcom collaboration is a strategic partnership, announced on October 13, 2025, under which OpenAI designs its own custom AI inference accelerators and Broadcom co-develops, manufactures, and…
Oracle Cloud Infrastructure
Oracle Cloud Infrastructure (OCI) is the public cloud of Oracle Corporation. Oracle made it generally available on October 20, 2016 under the name Oracle Bare Metal Cloud Services
Oracle Corporation
Oracle Corporation is an American multinational technology company, founded in 1977 and headquartered in Austin, Texas
Ornn
Ornn (legally Ornn AI Inc., with an index subsidiary named Ornn Data LLC) is a New York startup that builds pricing and trading infrastructure for GPU compute.
PORTS Technology Campus
The PORTS Technology Campus, also called the PORTS-Pike Technology Campus, is a planned AI infrastructure and power-generation complex in Pike County, Ohio.
Prime Intellect
Prime Intellect is a San Francisco based artificial intelligence company building infrastructure for decentralized AI development, with a focus on training large models across heterogeneous
Project Rainier
Project Rainier is a distributed artificial intelligence supercomputer built by Amazon Web Services around its in-house AWS Trainium accelerators, created principally to train and serve the Claude models of…
Project Suncatcher
Project Suncatcher is a long-term research "moonshot" at Google that studies whether machine learning compute could one day be hosted in space, on constellations of solar-powered satellites carrying Google…
Prometheus (Meta data center)
Prometheus is a roughly 1-gigawatt AI supercluster built by Meta at its data center campus in New Albany, Ohio.
Reliance Jamnagar AI data center
The Reliance Jamnagar AI data center is a planned gigawatt-scale artificial intelligence computing campus that Reliance Industries, India's largest company by market value
Research SuperCluster (RSC)
The Research SuperCluster (RSC) is an AI supercomputer built by Meta AI, the artificial intelligence research division of Meta Platforms (the company formerly known as Facebook).
RunPod
RunPod is a globally distributed GPU cloud computing platform that provides on-demand and serverless GPU compute for artificial intelligence training, fine-tuning, and inference.
SambaNova SN40L
The SambaNova SN40L is a reconfigurable dataflow AI accelerator designed by SambaNova Systems and unveiled on September 19, 2023.
SambaNova SN50
The SambaNova SN50 is a reconfigurable dataflow accelerator that SambaNova Systems unveiled in late February 2026 as the successor to its SN40L chip.
SemiAnalysis
SemiAnalysis is an independent research and analysis firm covering the semiconductor and artificial intelligence industries.
Snowflake-AWS chip deal
The Snowflake-AWS chip deal is a five-year, roughly $6 billion infrastructure commitment that the data-cloud company Snowflake made to Amazon Web Services (AWS), announced on May 27, 2026.
Space-based data centers
Space-based data centers are data centers launched into Earth orbit (or, in some proposals, placed on the Moon), where satellites carrying AI accelerators draw power from solar arrays and reject heat by…
SpaceX Starmind
SpaceX Starmind is SpaceX's planned constellation of solar-powered artificial intelligence compute satellites, intended to function as orbital data centers that run AI workloads in space and beam results back…
Starcloud
Starcloud, Inc. is an American space infrastructure startup that builds space-based data centers: satellites carrying data-center-class GPUs that are powered by solar arrays and cooled by radiating waste heat…
Stargate Argentina
Stargate Argentina is an announced, early-stage plan to build a large artificial intelligence data center of up to 500 megawatts (MW) in Argentina
Stargate Michigan
Stargate Michigan is an artificial intelligence data center campus under construction in Saline Township, Michigan, about 10 miles southwest of Ann Arbor in Washtenaw County.
Stargate Project
The Stargate Project is a private American AI infrastructure joint venture, announced at the White House on January 21, 2025, under which SoftBank, OpenAI, Oracle and MGX said they intended to invest $500…
Stargate UAE
Stargate UAE is a large artificial intelligence data center cluster being built in Abu Dhabi, United Arab Emirates, and is the first site of the Stargate Project located outside the United States.
TPU Ironwood
TPU Ironwood (listed as TPU7x in Google Cloud's documentation and also called TPU v7) is Google's seventh-generation Tensor Processing Unit
TPU Pod
A TPU Pod is a single Google supercomputer built from many Tensor Processing Unit (TPU) chips wired directly to each other by a high-speed Inter-Chip Interconnect (ICI) fabric arranged as a 2D or 3D torus, so…
Tensor Core
A Tensor Core is a specialized execution unit inside NVIDIA GPUs that computes a small matrix multiplication and accumulation, D = A x B + C