ROCm-LS 25.09 release notes#

2 min read time

Applies to Linux

The release notes provide a summary of notable changes since the previous ROCm-LS release.

This early access release serves as a preview and is not intended for production workloads.

ROCm-LS release highlights#

The following are notable new features and improvements in ROCm-LS 25.09 since the release of 25.06.

Introducing MONAI for AMD ROCm#

MONAI (Medical Open Network for AI) is a PyTorch-based, open-source framework designed for deep learning in healthcare imaging. AMD now provides ROCm-enabled MONAI builds optimized for AMD GPUs as a ROCm-LS component, which enables scalable medical AI workflows on AMD hardware.

MONAI for AMD ROCm offers the following advantages:

  • GPU acceleration on AMD Instinct MI300X GPUs.

  • API compatibility with upstream MONAI without requiring any code changes.

  • Validation with hipCIM image processing workflows.

For more information, see MONAI for AMD ROCm documentation

ROCm-LS components#

The following table lists the versions of ROCm-LS components for ROCm-LS 25.09, including any version changes from 25.06 to 25.09. Click the GitHub icon to go to the component’s source code.

Category Component name Version Source code
Imaging hipCIM 1.0.00
AI/ML MONAI for AMD ROCm 1.0.0

Note

The hipCIM version remains unchanged in this release.