Key Features of ROCm 7.0.0:
1. Expanded Hardware and OS Support:
- The update introduces support for AMD Instinct MI355X and MI350X GPUs, enhancing performance.
- It expands OS compatibility to include Ubuntu 24.04.3 and Rocky Linux 9, while retiring support for older versions like Ubuntu 24.04.2 and SLES 15 SP6.
- New KVM Passthrough support for MI350X and MI355X GPUs, along with VMware ESXi 8 support for MI300X GPUs, facilitates better integration into virtualized environments.
2. Deep Learning and AI Framework Enhancements:
- Compatibility updates for popular frameworks such as PyTorch, TensorFlow, and JAX ensure users can leverage the latest features.
- Introduction of vLLM support with OCP FP8 data type and FP4 precision for Llama 3.1 405B improves performance for large-scale AI tasks.
- Official support for Ray and llama.cpp enhances usability for developers in the AI domain.
3. Compiler and Tooling Improvements:
- The release introduces the AMD Next-Gen Fortran compiler and enhances clang/llvm support.
- Improvements in the HIP API for cross-platform compatibility streamline application development.
4. Library and Data Type Updates:
- New support for Microscaling (MX) data types and OCP FP8 format across multiple libraries, enhancing computational capabilities for AI and machine learning tasks.
- MIGraphX improvements focus on performance enhancements and integration with updated frameworks.
5. Documentation and User Support:
- ROCm 7.0.0 comes with improved documentation, including benchmarking guides, tutorials, and comprehensive release notes detailing the changes and updates.
Future Directions:
As technology advances, ROCm intends to further enhance its support for emerging hardware and software frameworks, ensuring that developers have the tools necessary to build cutting-edge applications in AI, machine learning, and high-performance computing. The independent versioning of the AMD GPU driver suggests a push towards more modular and flexible development environments.
For complete details, users can access the full release notes on the GitHub page linked in the announcement. This robust update positions ROCm as a competitive platform for developers and researchers looking to harness the power of AMD GPUs in their projects
ROCm 7.0.0 released
ROCm 7.0.0 is a major release that brings significant updates and new features across its comprehensive platform, focusing on expanded hardware support, enhanced deep learning framework integration, improved compiler capabilities, and refined tooling. The release introduces support for AMD Instinct MI355X and MI350X GPUs, expands OS compatibility to include Ubuntu 24.04.3 and Rocky Linux 9, and enhances support for popular deep learning frameworks such as PyTorch and TensorFlow. Additionally, ROCm 7.0.0 features improved compiler capabilities, including the introduction of the AMD Next-Gen Fortran compiler and enhanced clang/llvm support. With these improvements, ROCm 7.0.0 offers a strong and adaptable platform for AI, machine learning, and high-performance computing tasks, speeding up the creation of advanced applications.
