Build and Deploy GPU-Accelerated 5G Virtual Radio Access Networks (vRAN)

NVIDIA Aerial, an Application framework for building high-performance, software-defined, cloud-native 5G applications, to address increasing consumer demand. Optimised results with parallel processing on GPU for Baseband signals and data flow.

Get Started

100% Software Defined

NVIDIA Aerial is a highly-programmable PHY layer and has the capability to support L2+ functions seamlessly.

High Performance and AI Ready

With GPU-accelerated processing, complex computations run 20 times faster than existing L1 processing solutions. AI-based algorithms for L1 functions give improved performance results.


100% commercial off-the-shelf (COTS) hardware support with Aerial SDK makes it easier to deploy cloud-native services.


NVIDIA Aerial is a set of SDKs that enables GPU-accelerated, software-defined 5G wireless RANs. Today, NVIDIA Aerial provides two critical SDKs: cuVNF and cuBB.

The NVIDIA cuVNF SDK provides optimized inputoutput (IO) with memory allocations and support for network data flow and processing use cases. cuVNF improves performance for signal processing with NVIDIA GPU multi-core compute capability. For signal transmission and conversion, XX. It provides speed at line rate for I/O for packet flow. It enables developers to create other VNFs e.g. Deep packet inspection, firewall, vRAN, etc. A newly GPU enabled DPDK (Data Plane Development Kit) helps developers easily add GPU acceleration to their existing RAN architecture and NVIDIA CUDA-X signal processing libraries like cuFFT and NPP offer drop-in APIs and over 5000 primitives for image and signal processing.

The NVIDIA cuBB SDK provides a fully-offloaded 5G PHY layer processing pipeline (5G L1) which delivers unprecedented throughput and efficiency by keeping entire all processing within the GPU’s high-performance memory. With 5G NR based uplink and downlink channels running on GPUs, cuBB SDK provides high performance for latency and bandwidth utilisation. NVIDIA cuPHY SDK provides beamforming, LDPC encode/decode and other functionalities for PHY pipeline and interfacing fronthaul as well as Evoled Packet Core(EPC).

NVIDIA Aerial is Kubernetes based

Aerial SDK implements on COTS as well as cloud-native platforms such as EGX. It is the single software programming model that goes from Pico cells to CRAN to DRAN.

NVIDIA Aerial SDK is cloud native providing resources for faster execution of RAN functions. Aerial SDK is Kubernetes based to support provides container-orchestration for ease of container deployment and management. Cross platform support with NVIDIA EGX stack give wide range of services that can run edge applications giving high performance. NVIDIA EGX is an enterprise-grade accelerated computing platform that enables companies to run real-time low-latency applications at the edge. To achieve the highest level of reliability, Aerial SDKs and libraries undergo extensive testing against the EGX software stack with an emphasis on performance and long-term stability.

Learn More

Announcing the NVIDIA Aerial Developer Kit

Designed to jumpstart performance evaluation and benchmarking for RAN development, the NVIDIA Aerial™ Developer Kit will include preconfigured software and test vectors to deliver an out-of-the-box guided experience.

Learn More

Aerial vRAN partners

“SoftBank Corp. has been focused over the past decade on building centralized radio access networks that guarantee high capacity and stability. We believe that our 5G network will be completed through a software approach, or softwarization, and that NVIDIA’s Aerial SDKs will play an instrumental role in this effort. It enables an open ecosystem for software-defined 5G networks delivering both flexibility and high performance, which will help SoftBank Corp. drive the digital transformation of the telco industry.”

Ryuji Wakikawa, vice president and head of the Advanced Technology Division, SoftBank Corp.

“The telco industry is eagerly adopting cloud-native architecture to meet the growing compute demands of 5G. We are learning firsthand how the remarkable compute performance of NVIDIA GPUs, together with NVIDIA’s Aerial SDKs, can address the challenges of building flexible, high-performance virtualized telecom networks. We look forward to Aerial’s continued development.”

Yasuyuki Nakajima, president and CEO, KDDI Research, Inc.

Aerial SDK in-action

We announced the first NVIDIA Aerial™ Developer Kit. Designed to jumpstart the execution of 5G PHY functions for performance evaluation and benchmarking...

Read More

5G CloudRAN is the cloud-native architecture that supports PHY layer processing for high-speed, low bandwidth, software-defined network applications.

Read More

NVIDIA Mellanox 5T for 5G technology provides a real-time and high-performance solution for building an efficient, time-synchronized CloudRAN infrastructure.

Read More

NVIDIA announced a new technology embedded in its NVIDIA Mellanox ConnectX-6 Dx SmartNIC and BlueField-2 I/O Processing Unit to optimize 5G networks.

Read More

See More

Fifth-generation networks (5G) are ushering in a new era in wireless communications that delivers 1000X the bandwidth and 100X the speed at 1/10th the latency of 4G.

Read More

NVIDIA Aerial is a set of SDKs that enables GPU-accelerated, software-defined 5G wireless RANs. Today, NVIDIA Aerial provides two critical SDKs...

Watch Now

In this webinar, we walk through key features of the Aerial software developer kit and how it can be used to execute complex mathematical computations for L1 processing.

Watch Now

NVIDIA Aerial provides two critical new SDKs: CUDA Virtual Network Functions (cuVNF) and CUDA Baseband (cuBB). These SDKs simplify building highly programmable and scalable...

Read More

Speeding the mass adoption of AI at the 5G edge, NVIDIA has introduced Aerial, a software developer kit enabling GPU-accelerated, software-defined wireless radio access networks.

Read More

Additional Resources

Getting Started

To request access to NVIDIA Aerial SDK, please join our Aerial early access program.

Join Now