Support Matrix

Server Hardware

Data Center

	Hardware Compatibility
Operating System	Riva server requires Linux x86_64.
GPU Model	Preferred Deployment Platforms: NVIDIA H100 GPU NVIDIA A100 GPU NVIDIA L40 GPU Note Riva is supported on any NVIDIA Volta or later GPU (Compute Capability >= 7.0) for development purposes. Care must be taken to not exceed the memory available when selecting models to deploy. 16+ GB VRAM is recommended.

Software

NVIDIA Driver

Release 1.2.0 uses Triton Inference Server 24.06. Please refer to the Release Notes for Triton on NVIDIA driver support, including the CUDA and TensorRT versions used within the Docker container.

NVIDIA Container Toolkit

Your Docker environment must support NVIDIA GPUs. Please refer to the NVIDIA Container Toolkit for more information.