Yesterday, AMD released the new AMD ROCm 5.6 open software platform. Vamsi Boppana, the SVP of the AMD AI group, has a blog that highlights some of the new features of ROCm 5.6

For AI and LLM workloads, ROCm 5.6 brings:

• Integration of the Hugging Face unit test suite into ROCm QA
• Incremental support for OpenAI Triton in PyTorch 2.0 inductor mode
• Support for the broader community to enable OpenXLA support through ROCm for PyTorch, TensorFlow and JAX.

For HPC applications, ROCm 5.6 introduces improvements to several math libraries like FFT, BLAS, and solvers that form the basis for HPC applications and enhancements to ROCm development and deployment tools, including install, ROCgdb (the CPU-GPU integrated debugger), ROCm profiler and documentations.

In the coming months, AMD will also further optimize frameworks and backend compilers for optimal performance that include MLIR infrastructure improvements, underpinning AMD support for OpenAI Triton and OpenXLA compilers. Customers can also expect additional open-source AI models optimized for AMD solutions on the AMD hub on Hugging Face.

Additionally, AMD revealed that later this year, formal support for AMD ROCm will begin rolling out for select AMD RDNA 3-based GPUs.  Formal support for RDNA 3-based GPUs on Linux is planned to begin rolling out this fall, starting with the 48GB Radeon PRO W7900 and the 24GB Radeon RX 7900 XTX, with additional cards and expanded capabilities to be released over time.

Please view the blog here: https://community.amd.com/t5/rocm/new-rocm-5-6-release-brings-enhancements-and-optimizations-for/ba-p/614745/jump-to/first-unread-message