
NVIDIA offers Hopper
NVIDIA Hopper is a data-center GPU architecture for AI and high-performance computing workloads.
- Currently Offered

NVIDIA Hopper is a data-center GPU architecture for AI and high-performance computing workloads.
NVIDIA Hopper is a GPU architecture built for data-center AI training and inference, as well as high-performance computing.
Hopper introduces hardware and software optimizations for large-scale AI models and accelerated scientific computing.


Tenstorrent PCIe accelerator card family for AI training and inference workloads.



AMD Instinct is a family of data-center accelerators for AI and high-performance computing.


RDU is SambaNova's Reconfigurable Dataflow Unit, the company's AI chip family for inference and training at scale.


Broadcom designs and supplies semiconductors for networking, wireless, broadband, and industrial markets.



Trainium is AWS's purpose-built AI accelerator chip family for training and inference of large generative models.


Cerebras Wafer-Scale Engine is a family of wafer-scale AI processors.

Tenstorrent PCIe accelerator card family for AI training and inference workloads.

Intel Gaudi is a data-center AI accelerator product family.

AMD Instinct is a family of data-center accelerators for AI and high-performance computing.

RDU is SambaNova's Reconfigurable Dataflow Unit, the company's AI chip family for inference and training at scale.

Broadcom designs and supplies semiconductors for networking, wireless, broadband, and industrial markets.

TPU is Google's custom AI accelerator ASIC family delivered through Google Cloud TPU Pods for ML training and inference.

Trainium is AWS's purpose-built AI accelerator chip family for training and inference of large generative models.

Cerebras Wafer-Scale Engine is a family of wafer-scale AI processors.





PowerVR is Imagination's licensable GPU IP for graphics and AI inference at the edge.


Marvell OCTEON 10 DPU is a family of data processing units for cloud and carrier data centers.


Corsair combines memory-centric hardware and software for low-latency AI inference in data centers.


Sohu is a purpose-built inference chip designed for high-performance AI model serving.

PowerVR is Imagination's licensable GPU IP for graphics and AI inference at the edge.

Marvell OCTEON 10 DPU is a family of data processing units for cloud and carrier data centers.

Corsair combines memory-centric hardware and software for low-latency AI inference in data centers.

Custom AI model builder for enterprise infrastructure.

Groq LPU is a custom inference chip with on-chip SRAM and deterministic scheduling delivering low-latency AI inference for LLMs.

MatX One is a high-throughput chip for large language model training and inference.
