Application Layer Software#

NVIDIA AI Enterprise application software—including AI frameworks, SDKs, NIMs, and pre-trained models—is distributed through three release branch types, each offering a different balance of innovation speed, API stability, and support duration.

Note

The release cadence of each NVIDIA AI Enterprise release branch type is provided for general guidance only. The actual security update and release cadence can change at NVIDIA’s discretion.

NVIDIA AI Enterprise Release Cadence

Feature Branch (FB)#

An FB contains the latest versions of NVIDIA NIMs, AI frameworks, workflows, and SDKs. FBs are typically supported for one month. Some products follow different release cycles depending on the software product. Bug fixes and security updates are made available in future FBs.

A new FB is released monthly for most products and can change at NVIDIA’s discretion.

All FB components are listed in the NGC Catalog.

Feature Branch - Latest#

For the NVIDIA AI Enterprise Feature Branch, use the latest NVIDIA AI Enterprise Infra 7 or NVIDIA AI Enterprise Infra 6 collections as your supported configuration.

Because FB releases are superseded monthly, there is no archived product table for Feature Branch. The NGC Catalog collection always reflects the current FB release. For guidance on choosing a release branch, refer to Choosing the Right Release Branch.

Production Branch (PB)#

A PB contains production-ready AI frameworks and SDK branches to provide API stability and a secure environment for building mission-critical AI applications. Each PB is supported for 9 months. During a PB’s support period, it receives monthly bug fixes and security updates for high and critical software vulnerabilities.

A new PB is released every 6 months.

Products available as a PB can be found in the PB Collections section in the NGC Catalog.

Production Branch - October 2025 (PB 25h2)#

The following table provides release information and support timelines for Production Branch - October 2025 (PB 25h2):

Table 7 Production Branch - October 2025 (PB 25h2)#

PB Collection on NGC

Production Branch - October 2025 (PB 25h2)

Government Ready PB Collection

Production Branch Government Ready - October 2025 (PB 25h2)

First planned release [3]

October 2025

Last planned release

June 2026

Planned End of Life (EOL)

July 2026

Government Ready Versions

STIG hardened, FIPS enabled versions are available for some products. Refer to the table below.

Compatible Infrastructure Release

Use the latest NVIDIA AI Enterprise Infra Release 7 on the NGC Catalog.

Support Matrix

NVIDIA AI Enterprise Infrastructure Support Matrix 7 [4]

The following table lists all products included in Production Branch - October 2025 (PB 25h2) with their versions, Government Ready availability, and product documentation links:

Table 8 Products Included in Production Branch - October 2025 (PB 25h2)#

Name

Version

Government Ready Versions

Product Documentation

CUDA Deep Learning

25.08

Yes for x86

Release 25.08

Multi-LLM NIM

1.14

Yes for x86

Release 1.14.0

NVIDIA NIM Llama-3.1-70b-instruct

1.14

Yes for x86

Release 1.14.0-pb5.1

NVIDIA NIM Llama-3.3-nemotron-super-49b-v1.5 [5]

1.14

Yes for x86

Release 1.14.0-pb5.1

NVIDIA Holoscan SDK

3.3

No

Release 3.3.0

NVIDIA Retrieval QA Llama 3.2 1B Embedding v2 [5]

1.11.0

Yes for x86

Release 1.11.0 (PB)

NVIDIA Retrieval QA Llama 3.2 1B Reranking v2 [5]

1.9.0

Yes for x86

Release 1.9.0 (PB)

NVIDIA TensorRT

25.08-py

Yes for x86

Release 25.08

NVIDIA Triton Inference Server

  • 25.08-py3

  • 25.08-py3-sdk

  • 25.08-py3-vllm

  • 25.08-py3-trtllm

Yes for x86

Release 25.08

NVIDIA TAO

  • 6.0-python

  • 6.0-deploy

  • 6.0-data-services

Yes for x86

Release 6.0

PyTorch

25.08-py

Yes for x86

Release 25.08

RAPIDS [5]

25.08.02-runtime

Yes for x86

RAPIDS Documentation

RAPIDS Accelerator for Apache Spark [5]

v25.10

No

Release v25.10.0

New Features - Government Ready

This release introduces a significant new baseline for security, Government Ready, for most x86 container images. Government Ready containers meet software security requirements for use within FedRAMP High or equivalent Sovereign use cases while providing matching functionality with standard NVIDIA software.

Government Ready containers are built on Canonical’s Ubuntu 24.04 STIG-hardened base image and include FIPS-enabled versions of common cryptography libraries. These containers can be deployed the same as normal containers and require a FIPS-enabled Linux kernel on the host machine to utilize FIPS mode.

For detailed information about Government Ready containers, including technical implementation details, STIG and FIPS 140-3 standards, deployment instructions, and verification procedures, refer to Government Ready Containers.

EOL - Production Branch#

Production Branch - May 2025 (PB 25h1) - EOL#

Important

This branch reached end-of-life in January 2026. No further updates will be provided.

The following table provides release information and support timelines for Production Branch - May 2025 (PB 25h1):

Table 9 Production Branch - May 2025 (PB 25h1)#

PB Collection on NGC

Production Branch - May 2025 (PB 25h1)

First planned release

May 2025

Last planned release

December 2025

Planned End of Life (EOL)

January 2026

Compatible Infrastructure Release

Use the latest NVIDIA AI Enterprise Infra Release 6 on the NGC Catalog.

Support Matrix

NVIDIA AI Enterprise Infrastructure Support Matrix 6

The following table lists products that were included in Production Branch - May 2025 (PB 25h2):

Table 10 Products Included in Production Branch - May 2025 (PB 25h1)#

Name

Version

Product Documentation

NVIDIA NIM Llama-3.1-8b-instruct [2]

1.10

Release 1.10

NVIDIA NIM Llama-3.1-70b-instruct [2]

1.10

Release 1.10

NVIDIA DeepStream SDK [2]

N/A

DEEPSTREAM SDK

NVIDIA Holoscan SDK [2]

3.3.0

Release 3.3.0

NVIDIA Morpheus

25.02-runtime

Release 25.02

NVIDIA TensorRT

25.03-py

Release 25.03

NVIDIA Triton Inference Server

  • 25.03-py3

  • 25.03-py3-sdk

  • 25.03-py3-min

  • 25.03-py3-vllm

  • 25.03-py3-trtllm

Release 25.03

NVIDIA NIM Retrieval QA E5 Embedding v5 [2]

1.8.0

Release 1.8.0

PyTorch

25.03-py

Release 25.03

RAPIDS

25.02-runtime

RAPIDS Documentation

RAPIDS Accelerator for Apache Spark

25.02.1

Release v25.02.1

Production Branch - October 2024 (PB 24h2) - EOL#

Important

This branch reached end-of-life in July 2025. No further updates will be provided.

The following table provides archived release information for Production Branch - October 2024 (PB 24h2):

Table 11 Production Branch - October 2024 (PB 24h2)#

PB Collection on NGC

Production Branch - October 2024 (PB 24h2)

First planned release

October 2024

Last planned release

June 2025

Planned End of Life (EOL)

July 2025

Compatible Infrastructure Release

Use the latest NVIDIA AI Enterprise Infra Release 6 or NVIDIA AI Enterprise Infra Release 5 on the NGC Catalog.

Support Matrix

The following table lists products that were included in Production Branch - October 2024 (PB 24h2):

Table 12 Products Included in Production Branch - October 2024 (PB 24h2)#

Name

Version

Product Documentation

Deep Graph Library (DGL)

24.08-py3

Release 24.08

NVIDIA NIM Llama-3.1-8b-instruct [1]

1.3

Release 1.3.0

NVIDIA NIM Llama-3.1-70b-instruct [1]

1.3

Release 1.3.0

NVIDIA DeepStream SDK

7.1-triton-x86

DEEPSTREAM SDK 7.1 FOR NVIDIA DGPU/X86

NVIDIA Holoscan SDK

24.08

Release 2.6.0

NVIDIA Morpheus

24.06-runtime

Release 24.06

NVIDIA TensorRT

24.08-py3

Release 24.08

NVIDIA Triton Inference Server

  • 24.08-py3

  • 24.08-py3-sdk

  • 24.08-py3-min

Release 24.08

NVIDIA NIM Retrieval QA E5 Embedding v5 [1]

1.2

Release 1.2.0

PyTorch

24.08-py3

Release 24.08

PyTorch Geometric (PyG)

24.08-py3

Release 24.08

RAPIDS

24.06-runtime

RAPIDS Documentation

RAPIDS Accelerator for Apache Spark

24.06.02

Release v24.06.1

TensorFlow 2

24.08-tf2-py3

Release 24.08

Production Branch - May 2024 (PB 24h1) - EOL#

Important

This branch reached end-of-life in January 2025. No further updates will be provided.

The following table provides archived release information for Production Branch - May 2024 (PB 24h1):

Table 13 Production Branch - May 2024 (PB 24h1)#

PB Collection on NGC

Production Branch - May 2024 (PB 24h1)

First planned release

May 2024

Last planned release

December 2024

Planned End of Life (EOL)

January 2025

Compatible Infrastructure Release

Use the latest NVIDIA AI Enterprise Infra Release 5 as a supported configuration.

Support Matrix

NVIDIA AI Enterprise Infrastructure Support Matrix 5

The following table lists products that were included in Production Branch - May 2024 (PB 24h1):

Table 14 Products Included in Production Branch - May 2024 (PB 24h1)#

Name

Version

Product Documentation

NVIDIA MONAI Toolkit

24.03-py3

Project MONAI

NVIDIA Morpheus

24.02-runtime

Morpheus Documentation

NVIDIA TensorRT

24.03-py3

Release 24.03

NVIDIA Triton Inference Server

  • 24.03-py3

  • 24.03-py3-sdk

  • 24.03-py3-min

Release 24.03

PyTorch

24.03-py3

Release 24.03

RAPIDS

24.02-runtime

RAPIDS Documentation

RAPIDS Accelerator for Apache Spark

24.02

Release v24.02.0

TensorFlow 2

24.03-tf2-py3

Release 24.03

Production Branch - October 2023 (PB 23h2) - EOL#

Important

This branch reached end-of-life in July 2024. No further updates will be provided.

The following table provides archived release information for Production Branch - October 2023 (PB 23h2):

Table 15 Production Branch - October 2023 (PB 23h2)#

PB Collection on NGC

Production Branch - October 2023 (PB 23h2)

First planned release

October 2023

Last planned release

June 2024

Planned End of Life (EOL)

July 2024

Compatible Infrastructure Release

Use the latest NVIDIA AI Enterprise Infra Release 5 as a supported configuration.

The following table lists products that were included in Production Branch - October 2023 (PB 23h2):

Table 16 Products Included in Production Branch - October 2023 (PB 23h2)#

Name

Version

Product Documentation

NVIDIA Holoscan SDK

23.10

Release 1.0.3

NVIDIA TensorRT

23.08-py3

Release 23.08

NVIDIA Triton Inference Server

  • 23.08-py3

  • 23.08-py3-sdk

  • 23.08-py3-min

  • 23.08-pyt-python-py3

  • 23.08-tf2-python-py3

Release 23.08

PyTorch

23.08-py3

Release 23.08

RAPIDS

23.06-runtime

RAPIDS Documentation

TensorFlow 2

23.08-tf2-py3

Release 23.08

Long-Term Support Branch (LTSB)#

An LTSB contains selected AI frameworks and SDKs for highly regulated industries that require longer application lifecycle management. Each LTSB is supported for 3 years and receives quarterly bug fixes and security updates for high- and critical software vulnerabilities.

A new LTSB is released every 30 months.

Products available as an LTSB can be found in the LTSB Collections section of the NGC Catalog.

Long-Term Support Branch 2 (LTSB 2)#

The following table provides release information and support timelines for Long-Term Support Branch 2 (LTSB 2):

Table 17 Long-Term Support Branch 2 (LTSB 2)#

LTSB Collection on NGC

Long-Term Support Branch 2 (LTSB 2)

First planned release

November 2024

Last planned release

August 2027

Planned End of Life (EOL)

October 2027

Compatible Infrastructure Release

Use the latest NVIDIA AI Enterprise Infra Release 4 as a supported configuration.

The following table lists all products included in Long-Term Support Branch 2 (LTSB 2) with their versions and product documentation links:

Table 18 Products included in Long-Term Support Branch 2 (LTSB 2)#

Name

Version

Product Documentation

NVIDIA TensorRT

  • 23.08-py3

  • 23.08-py3-igpu

Release 23.08

NVIDIA Triton Inference Server

  • 23.08-py3-base

  • 23.08-py3-sdk

  • 23.08-py3-base-min

  • 23.08-py3-base-igpu

  • 23.08-py3-sdk-igpu

  • 23.08-py3-min-igpu

Release 23.08

PyTorch

  • 23.08-py3

  • 23.08-igpu

Release 23.08

RAPIDS

23.06-runtime

RAPIDS Documentation

Long-Term Support Branch 1 (LTSB 1) - EOL#

Important

This branch reached end-of-life in June 2024. No further updates will be provided.

The following table provides archived release information for Long-Term Support Branch 1 (LTSB 1):

Table 19 Long-Term Support Branch 1 (LTSB 1)#

First planned release

August 2021

Last planned release

February 2024

Planned End of Life (EOL)

June 2024

The following table lists products that were included in Long-Term Support Branch 1 (LTSB 1):

Table 20 Products included in Long-Term Support Branch 1 (LTSB 1)#

Name

Version

Product Documentation

NVIDIA TensorRT

21.08

Release 21.08

NVIDIA Triton Inference Server

21.08

Release 21.08

PyTorch

21.08-py3

Release 21.08

RAPIDS

21.08

RAPIDS Documentation

TensorFlow

21.08

Release 21.08

Government Ready Containers#

NVIDIA AI Enterprise offers Government Ready container images that meet software security requirements for use within FedRAMP High or equivalent Sovereign use cases, while maintaining matching functionality with standard NVIDIA software.

What is Government Ready?#

Government Ready designation indicates that container images:

  • Meet software security requirements for use within FedRAMP High or equivalent Sovereign use cases

  • Provide matching functionality with NVIDIA software without the Government Ready designation

  • Are built on Canonical’s Ubuntu 24.04 STIG-hardened base image

  • Include FIPS-enabled versions of common cryptography libraries, such as OpenSSL

Technical Implementation#

Security Technical Implementation Guides (STIGs)

Security Technical Implementation Guides (STIGs) are configuration standards consisting of cybersecurity requirements for specific products developed by the U.S. Department of Defense. STIGs provide a methodology for standardized secure installation and maintenance of DOD IA and IA-enabled devices and systems, helping organizations harden their systems against security vulnerabilities through detailed technical configuration guidance.

FIPS 140-3

FIPS 140-3 is the U.S. government computer security standard used to approve cryptographic modules, with FIPS 140-3 superseding FIPS 140-2 for new submissions as of April 1, 2022. The goal of the CMVP is to promote the use of validated cryptographic modules and provide Federal agencies with a security metric to use in procuring equipment containing validated cryptographic modules. These standards ensure that cryptographic implementations meet rigorous security requirements for government and regulated environments.

Deployment#

Government Ready containers can be deployed the same as normal containers. To make use of FIPS mode, your host machine must have a FIPS-enabled Linux kernel.

If you run into problems integrating your application with FIPS-enabled libraries, check the documentation for each library whether FIPS mode can be toggled. For example, for OpenSSL you can use OPENSSL_FORCE_FIPS_MODE=0 to disable FIPS mode if needed for testing.

Verifying FIPS Mode on Your Host System#

To verify that your host machine is running in FIPS mode, check the /proc/sys/crypto/fips_enabled file and ensure it is set to 1. If it is set to 0, the FIPS modules will not run in FIPS mode. If the file is missing, the FIPS kernel is not installed. You can verify this with the shell command:

cat /proc/sys/crypto/fips_enabled

Additionally, you can check your kernel version using uname -a to confirm you’re running a FIPS-enabled kernel. Refer to Canonical’s FIPS documentation as an example of setting up a FIPS kernel. Any Linux distribution with a FIPS-enabled kernel should provide similar verification methods through the /proc/sys/crypto/fips_enabled flag.

Additional Resources#

Learn more about NVIDIA’s hardened image in the AI Software for Regulated Environments white paper.

Footnotes