News
EveryChip

AI training and inference

Accelerators for training and running neural networks. 129 chips on EveryChip so far.

AI chips train neural networks and run them, a task called inference. Training a large language model takes thousands of accelerators running for weeks; inference runs every time someone uses the model. Nvidia's data centre GPUs have led since the deep-learning revival of 2012, while Google's TPU, AMD's Instinct, Amazon's Trainium and many start-up chips compete. Phones and laptops now carry small AI engines too.

Training and inference

Training adjusts billions of weights by passing data through the network and back, again and again, so it needs huge amounts of arithmetic and memory bandwidth and fast links between chips. Inference runs the finished model, often at lower precision, and is spread across data centres and devices. Many chip designs specialise in one or the other.

Why Nvidia led

In 2012 a neural network called AlexNet, trained on two Nvidia gaming GPUs, won the ImageNet image recognition contest by a wide margin. Nvidia's CUDA software, available since 2007, made its GPUs the default for researchers. Its A100 (2020), H100 (2022) and Blackwell (2024) chips became the main tools of the AI industry, and demand outran supply in 2023 and 2024.

Famous AI training and inference chips

Further reading

Pixel Visual Core 🇺🇸 United StatesPixel Visual Core Google’s programmable image and vision processor for Pixel phonesSoC · Arm · 2017 Nvidia BlueField 🇺🇸 United StatesNvidia BlueField Nvidia data processing units with their own CPU cores and memoryNetwork chip · Arm · 2020 🇺🇸 United StatesApple A11 Bionic Six-core phone SoC with a Neural Engine, used in iPhone 8 and iPhone XSoC · Arm · 2017 🇺🇸 United StatesApple M3 Apple's 3 nm Mac and iPad SoC family with CPU, GPU and Neural EngineSoC · Arm · 2023 🇺🇸 United StatesTensor Processing Unit Google custom chip for neural network machine learningAI accelerator · Other · 2015 🇺🇸 United StatesNvidia RTX Spark ARM system on chip for Windows laptops and desktopsSoC · Arm · 2026 🇺🇸 United StatesNvidia Drive System on a chip family for autonomous vehiclesSoC · Arm · 2015 Dimensity 9500 🇹🇼 TaiwanDimensity 9500 Flagship 5G mobile system on a chip with AI and gaming focusSoC · Arm · 2025 Dimensity 9300 🇹🇼 TaiwanDimensity 9300 All-Big-Core 5G smartphone system on a chipSoC · Arm · 2023 GB200 Grace Blackwell 🇺🇸 United StatesGB200 Grace Blackwell Superchip Nvidia AI superchip linking Grace CPUs and Blackwell GPUsSoC · Arm GB300 Grace Blackwell 🇺🇸 United StatesGB300 Grace Blackwell Ultra Superchip AI superchip combining Grace CPUs and Blackwell Ultra GPUsSoC · Arm Microsoft Cobalt 200 🇺🇸 United StatesMicrosoft Cobalt 200 132-core Arm server CPU for Microsoft Azure cloud workloadsCPU · Arm · 2025 DRIVE Thor 🇺🇸 United StatesDRIVE Thor System-on-chip for autonomous vehicles and robotaxisSoC · Arm Google Tensor G5 🇺🇸 United StatesGoogle Tensor G5 Custom mobile processor for Pixel 10 phonesSoC · Arm · 2025 Dimensity 9400 🇹🇼 TaiwanDimensity 9400 Flagship 5G system on a chip for Android smartphonesSoC · Arm · 2024 GB10 Grace Blackwell S 🇺🇸 United StatesGB10 Grace Blackwell Superchip AI superchip for desktop workstationsSoC · Arm Grace CPU Superchip 🇺🇸 United StatesGrace CPU Superchip Dual-chip Arm module for AI data centresCPU · Arm · 2023

Photo credits on this page

The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.

The weekly digest

Every Monday: the chip of the day, new pages on EveryChip, and the conferences and anniversaries of the week ahead.