Skip to navigation

Support Matrix

View as MarkdownOpen in Claude

Models

Model NameModel IDPublisher
LipSynclipsyncNVIDIA

Supported Languages

The LipSync NIM provides a generic, language-agnostic model (default) and language-specific fine-tuned models. Select a model at deployment time with the NIM_TAGS_SELECTOR environment variable; refer to Selecting a Language-Specific Model.

LanguageCodeModel
Language-agnostic (default)(none)Generic
GermandeFine-tuned
SpanishesFine-tuned
FrenchfrFine-tuned

Optimized Configurations

Server GPUPrecision
T4FP16
A2, A10, A16, A40FP16
L4, L40, L40sFP16
B40FP16

Other architectures (Consumer RTX GPUs)

Consumer GPUPrecision
RTX 4090FP16
RTX 5090, 5080FP16

The LipSync NIM is compatible with professional and consumer GPUs that have Tensor cores and are based on the following NVIDIA architectures: Blackwell, Ada, Ampere, and Turing. The RTX-based GPUs are also supported.

The NIM requires NVENC/NVDEC hardware. GPUs without NVENC/NVDEC hardware support are not supported, including A100, H100, and B100 products. For details about supported GPUs and H264 YUV formats, refer to the Video Encode and Decode GPU Support Matrix.

Software

NVIDIA Driver and Prerequisites

NVIDIA driver requirements and other prerequisites for LipSync NIM:

PrerequisiteVersionDownload and install steps
NVIDIA Graphic Drivers for Linux571.21+https://www.nvidia.com/en-us/drivers/unix/
DockerlatestUbuntu, CentOS, and Debian: https://docs.docker.com/engine/install/; Rocky Linux: https://docs.rockylinux.org/gemstones/containers/docker/
NVIDIA Container ToolkitlatestInstallation and configuration instructions: https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html

LipSync NIM uses the following NVIDIA software platforms:

ComponentsVersion
CUDA12.8.1
cuDNN9.7.1.26
TRT10.9.0.34
Triton Inference Serverv2.56.0
DeepStream8.0