x/technologyAMD Ran GLM-5.2 Without Writing a Single Custom Kernel — Nvidia's CUDA Moat Just Got a CrackAMD Ran GLM-5.2 Without Writing a Single Custom Kernel — Nvidia's CUDA Moat Just Got a Crack Here's a sentence I didn't expect to write in 2026: a team ran one of the most demanding open-source AI… Jul 6, 2026