Support Matrix#
Models#
Model Name |
Model ID |
Publisher |
|---|---|---|
Audio2Face-2D |
maxine-audio2face-2d |
NVIDIA |
Optimized Configurations#
Server GPU |
Precision |
|---|---|
V100 |
FP16 |
T4 |
FP16 |
A2, A10, A16, A40 |
FP16 |
L4, L40 |
FP16 |
RTX 5090, 5080, 5070 |
FP16 |
The A2F2D NIM is compatible with professional and consumer GPUs that have Tensor cores and are based on the following NVIDIA architectures: Blackwell, Ada, Ampere, Turing, and Volta. The RTX-based GPUs are also supported.
GPUs without NVENC/NVDEC hardware support are not supported, including A100/H100 products.
Software#
NVIDIA Driver and Prerequisites#
NVIDIA driver requirements and other prerequisites for Audio2Face-2D NIM:
Prerequisite |
Version |
Download and install steps |
|---|---|---|
NVIDIA Graphic Drivers for Linux |
571.21+ |
|
Docker |
latest |
Ubuntu, CentOS, Debian: https://docs.docker.com/engine/install/ Rocky Linux: https://docs.rockylinux.org/gemstones/containers/docker/ |
NVIDIA Container Toolkit |
latest |
Installation and configuration instructions: https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html |
Audio2Face-2D NIM uses the following NVIDIA software platforms:
Components |
Version |
|---|---|
CUDA |
12.1.1 |
cuDNN |
8.9.7.29 |
TRT |
10.4.0.26 |
Triton Inference Server |
v2.50.0 |
DeepStream |
7.1 |