Skip to main content
ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator

Search

Search thousands of GPU-optimized Containers, pretrained Models, SDKs, and Helm charts—ready to accelerate AI, digital twins, and HPC from cloud to edge.
Accelerate custom generative AI app deployment using pre-built containers with optimized AI models.

Displaying 22 results

vLLM
NVIDIA
vLLM is a fast and easy-to-use library for LLM inference and serving. The NVIDIA vLLM NGC Container is optimized for GPU acceleration, and contains a validated set of libraries that enable and optimize GPU performance.
Container
meta-llama-2-70b-chat
NVIDIA
NVIDIA NIM for GPU accelerated Llama 2 70B inference through OpenAI compatible APIs
Container
Riva Speech Skills
NVIDIA
Riva Speech Skills is a scalable Conversational AI service platform.
Container
Riva NMT NIM
NVIDIA
Riva NMT NIM provide easy access to state-of-the-art neural machine translation (NMT) models, capable of translating text from one language to another with exceptional accuracy.
Container
SGLang
NVIDIA
SGLang is a fast serving framework for large language models and vision language models. The NVIDIA SGLang NGC Container is optimized for GPU acceleration, and contains a validated set of libraries that enable and optimize GPU performance.
Container
Riva Translate 1.6b
NVIDIA
Riva Translate 1.6b NIM provide easy access to state-of-the-art neural machine translation (NMT) models, capable of translating text from one language to another with exceptional accuracy.
Container
NMT Megatron Riva 1b
NVIDIA
Riva NMT NIM provide easy access to state-of-the-art neural machine translation (NMT) models, capable of translating text from one language to another with exceptional accuracy.
Container
Canary-1B ASR/AST Multilingual Offline Greedy
NVIDIA
RIVA Canary 1b Multilingual ASR NIM delivers accurate speech-to-text transcription for 26 languages and Translations in 34 languages.
Container
NVIDIA Active Speaker Detection ST 2110 Sample Sender
NVIDIA
It transmits uncompressed video (SMPTE ST 2110-20) and PCM audio (SMPTE ST 2110-30) stream per speaker as an input source for the NVIDIA Active Speaker Detection NIM.
Container
riva-translate-4b-instruct-v2
NVIDIA
Riva-Translate-4B-Instruct-v2 Neural Machine Translation NIM
Container
NVIDIA Active Speaker Detection ST 2110 NIM
NVIDIA
NVIDIA Active Speaker Detection NIM supports the detection and identification of multiple speakers in a video stream.
Container
NVIDIA Active Speaker Detection ST 2110 Sample Receiver
NVIDIA
It reference sample SMPTE ST 2110 receiver that ingests active-speaker ancillary data and optional bounding-box video from the ASD ST 2110 NIM, with SRT preview on Holoscan for Media for validation.
Container
NVIDIA Active Speaker Detection ST 2110 Operator
NVIDIA
NVIDIA Active Speaker Detection provides declarative, production-grade lifecycle management for Active Speaker Detection NIM deployments on Holoscan for Media clusters, using the NvidiaActiveSpeakerDetectionMediaFunction custom resource.
Container
NVIDIA Active Speaker Detection ST 2110 Sample
NVIDIA
Umbrella Helm chart for NVIDIA Active Speaker Detection(sender, receiver, nvidia-active-speaker-detection-h4m-service).
Helm Chart
NVIDIA Active Speaker Detection ST 2110 NIM
NVIDIA
Helm charts to deploy Active Speaker Detection NIM- receives video/audios, runs Active Speaker Detection inference, outputs ancillary data and optionally video.
Helm Chart
NVIDIA Active Speaker Detection ST 2110 Operator
NVIDIA
Helm charts to deploy Kubernetes operator and NvidiaActiveSpeakerDetectionMediaFunction Custom Resource Definition.
Helm Chart
SpeechLLM FastConformer Llama2-7B
NVIDIA
A 7B SpeechLLM model trained on speech-to-text recognition (ASR), speech-to-text translation (AST) and audio/speech question answering (SpeechQA, AudioQA) data.
Model
Riva Megatron NMT any2any
NVIDIA
Machine Translation model for Any to Any direction
Model
Deep Learning Frameworks
NVIDIA
This collection contains performance-optimized Deep Learning frameworks.
Collection
NeMo - Natural Language Processing
NVIDIA
This collection contains NeMo models for Natural Language Processing (NLP): Question Answering, Translation, Named Entity Recognition, Punctuation and Capitalization, Base NLP models.
Collection
NVIDIA Active Speaker Detection ST 2110
NVIDIA
It is a real-time AI service that analyzes video and multiple audio streams to detect which on-screen speakers are actively talking.
Collection
Translation
NVIDIA
A collection of easy to use, highly optimized Deep Learning Models for Machine Translation. Deep Learning Examples provides Data Scientist and Software Engineers with recipes to Train, fine-tune, and deploy State-of-the-Art Models
Collection
1-22 of 22 items

Modal Content

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.

Manage Settings