AMD has launched ROCm 10.0, celebrating the tenth anniversary of its open-source GPU compute stack with a focus on "Built for the Age of Agentic AI." The new release introduces ROCm.AI, which features a unified CLI, AI coding assistant tools, and Hyperloom, an automation system designed to optimize inference workflows significantly faster than manual methods. Additionally, AMD has streamlined its backend with TheRock build pipeline and unified SDKs for Windows and Linux to mitigate past fragmentation issues. Enhanced framework support, communication libraries, and developer tools are also included, indicating AMD's commitment to automation and user-friendliness for future developments in ROCm

AMD Ships ROCm 10.0: A Decade of Open Compute, Now Built for Agentic AI

AMD shipped ROCm 10.0, marking the tenth anniversary of its open-source GPU compute stack and introducing a release branded "Built for the Age of Agentic AI." The update centers on ROCm.AI, which bundles a unified CLI, AMD Skills for AI coding assistants, and Hyperloom, an agentic system that automates end-to-end inference optimization. AMD has consolidated its backend with the production-ready TheRock build pipeline and unified Windows and Linux SDKs under the new ROCm Core SDK to address historical fragmentation. The release also delivers vLLM v0.2x support, advances RCCL to NCCL 2.30.4 with GPU-initiated networking, and expands Roofline analysis to RDNA 3 hardware.

AMD Ships ROCm 10.0: A Decade of Open Compute, Now Built for Agentic AI @ Linux Compatible