
NVIDIA's CUDA-on-RISC-V Plus NVLink Fusion Opens Path to Non-x86, Non-ARM GPU Hosts
At Hot Chips 2026, NVIDIA presented CUDA-on-RISC-V requirements alongside NVLink Fusion, which licenses NVLink IP to third-party silicon. Combined, a RISC-V server CPU with a licensed NVLink controller could host NVIDIA GPUs over a coherent fabric — running CUDA workloads without x86 or ARM. NVIDIA did not address whether any RISC-V vendor currently ships qualifying silicon.
Published