Support Matrix
Model Name |
Model ID |
Publisher |
|---|---|---|
| FastPitch Hifi-GAN Riva | fastpitch-hifigan-riva | NVIDIA |
GPU |
GPU Memory (GB) |
Precision |
# of GPUs |
|---|---|---|---|
| H100 | 2 | FP16 | 1 |
| A100 | 2 | FP16 | 1 |
| L40 | 2 | FP16 | 1 |
GPU |
GPU Memory (GB) |
Precision |
# of GPUs |
|---|---|---|---|
| Any NVIDIA GPU with sufficient GPU memory and compute capability > 7.0 | 2 | FP16 | 1 |
NVIDIA Driver
Release 1.0.0 uses Triton Inference Server 23.11. See the Release Notes for information about 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.