# NVIDIA Networking

NVIDIA networking is a range of highly scalable connectivity solutions used in enterprise, large cloud, and supercomputing data centers to accelerate AI and scientific computing workloads.

Find networking software and drivers:

[Download](https://developer.nvidia.com/networking/ethernet-software)

## Key Topics:

- AI Training
- AI Inference
- Agentic AI

## NVIDIA Networking Platforms

NVIDIA’s end-to-end accelerated networking platforms offer organizations the choice of NVIDIA Quantum InfiniBand and Spectrum™ Ethernet connectivity to provide the highest performance for AI training and inference workloads. Innovations such as adaptive routing and telemetry-based congestion control enable consistent, predictable performance with zero tail latency for AI workloads scaling to 100K+ GPUs.

## Accelerated Networking Platforms

### Quantum InfiniBand Platform

- Highest networking performance and scale up to 800Gb/s
- [Adapters](https://www.nvidia.com/en-us/networking/infiniband-adapters/) and [switches](https://www.nvidia.com/en-us/networking/infiniband-switching/) accelerate AI, ML, HPC, and data analytics
- Develop solutions with in-network computing, custom topologies, and self-healing fabrics

[Learn More](https://www.nvidia.com/en-us/networking/products/infiniband/)

### Spectrum Ethernet Platform

- Accelerated, high-performance Ethernet up to 800Gb/s
- Leverage [Spectrum-X](https://www.nvidia.com/en-us/networking/spectrumx/) as the world’s first Ethernet platform built for AI
- Enable software-driven automation, simulation, and validation for operational efficiency

[Learn More](https://www.nvidia.com/en-us/networking/products/ethernet/)

### BlueField Platform

- Leverage smart offloads for cloud, **security**, timing, [video](https://developer.nvidia.com/networking/rivermax), and storage
- Integrate with open-source tools including [DPDK](https://developer.nvidia.com/networking/dpdk), [OvS](https://www.nvidia.com/en-us/networking/products/ethernet/), Kubernetes, **RoCE**, **Spark**, and **OpenStack**
- Accelerate applications at speeds up to 400 Gb/s

[Learn More](https://www.nvidia.com/en-us/networking/products/ethernet/)

## Accelerated Networking Software and Tools

### NVIDIA DOCA

NVIDIA DOCA™ unlocks the potential of the NVIDIA® BlueField® networking platform. DOCA enables the rapid creation of applications and services that offload, accelerate, and isolate data center workloads.

[Get Started With DOCA](https://developer.nvidia.com/networking/doca)

### NVIDIA Rivermax

NVIDIA® Rivermax® offers a unique IP-based solution for any media and data streaming use case. Rivermax unlocks innovation for a wide range of applications in media and entertainment (M&E), broadcast, healthcare, smart cities, and more.

[Get Started With Rivermax](https://developer.nvidia.com/networking/rivermax)

### NVIDIA HPC-X

NVIDIA® HPC-X® is a comprehensive software package that enables MPI and SHMEM/PGAS programming languages to achieve high performance, scalability, and efficiency. HPC-X also ensures that communication libraries are fully optimized by NVIDIA Quantum InfiniBand networking solutions.

[Get Started With HPC-X](https://developer.nvidia.com/networking/hpc-x)

### NVIDIA Magnum IO SDK

The NVIDIA Magnum IO™ software development kit (SDK) enables developers to remove input/output (IO) bottlenecks in AI, high-performance computing (HPC), data science, and visualization applications, reducing the end-to-end time of their workflows.

[Get Started With Magnum IO SDK](https://developer.nvidia.com/magnum-io)

## Latest Networking News

##### NVIDIA NVbandwidth: Your Essential Tool for Measuring GPU Interconnect and Memory Performance

[Read more](https://developer.nvidia.com/blog/nvidia-nvbandwidth-your-essential-tool-for-measuring-gpu-interconnect-and-memory-performance/)

##### Running Large-Scale GPU Workloads on Kubernetes with Slurm

[Read more](https://developer.nvidia.com/blog/running-large-scale-gpu-workloads-on-kubernetes-with-slurm/)

##### Running AI Workloads on Rack-Scale Supercomputers: From Hardware to Topology-Aware Scheduling

[Read more](https://developer.nvidia.com/blog/running-ai-workloads-on-rack-scale-supercomputers-from-hardware-to-topology-aware-scheduling/)

##### Accelerating Vision AI Pipelines with Batch Mode VC-6 and NVIDIA Nsight

[Read more](https://developer.nvidia.com/blog/accelerating-vision-ai-pipelines-with-batch-mode-vc-6-and-nvidia-nsight/)