AMD Ships ROCm 10.2.0: Stability-Focused Refresh Targets CUDA Reliability

Published by

AMD released ROCm 10.2.0 on November 18, 2026, focusing on stability rather than introducing major new features. This version updates serving engines and training frameworks while claiming that its Instinct MI355X outperformed NVIDIA's B300 by 38.5% in training speed. Additionally, it broadens support for new Ryzen processors and optimizes libraries for reduced footprint and improved performance. AMD aims to establish trust within the developer community by prioritizing predictable, low-friction updates as it competes with CUDA



AMD Ships ROCm 10.2.0: Stability-Focused Refresh Targets CUDA Reliability

AMD shipped ROCm 10.2.0 on November 18, 2026, continuing its six-week release cycle with a stability-focused refresh instead of a major new feature. The upgrade bumps serving engines to vLLM 0.32.0 and SGLang 0.5.21 on Python 3.14, refreshes training frameworks like PyTorch 2.15, and carries AMD's claim that the Instinct MI355X trained DLRM v4 38.5% faster than NVIDIA's B300. It also broadens support to 18 new Ryzen processors and the Radeon PRO W7900D, tunes RCCL for eight-GPU Radeon servers, and trims library footprints with compressed catalogs while adding complex-math and storage I/O improvements. Ultimately, AMD is betting that predictable, low-friction updates build the trust CUDA has earned over a decade, though some newer tools like Hyperloom's Radeon support remain early access.

AMD Ships ROCm 10.2.0: Stability-Focused Refresh Targets CUDA Reliability @ Linux Compatible