The Digital Human for Customer Service NVIDIA AI Blueprint is powered by NVIDIA Tokkio, a workflow based on ACE technologies, to bring enterprise applications to life with a 3D animated digital human interface

Rapidly ingest massive volumes of PDF documents. Extract text, graphs, charts, and tables for highly accurate retrieval.

The NVIDIA BioNeMo Blueprint for generative virtual screening shows how generative AI and accelerated NIM microservices can be used to design optimized small molecules smarter and faster.

A widely used model for predicting the 3D structures of proteins from their amino acid sequences.

AlphaFold2 is a protein structure prediction model from Google DeepMind. AlphaFold2 demonstrates state-of-the-art performance at predicting protein structure form amino acid sequence, besting all other submissions on the Critical Assessment of protein Structure Prediction (CASP).

MolMIM is a transformer-based model developed by NVIDIA for controlled small molecule generation. MolMIM optimizes and samples molecules from the latent space guided by user-defined scoring functions, including functions from other models and functions based on experimental data testing for various chemical and biological properties. MolMIM can be deployed in the cloud or on-prem for enterprise-grade inference in computational drug discovery workflows, including virtual screening, lead optimization, and other lab-in-the-loop approaches.

The NVIDIA GenMol NIM is a BERT-based generalist AI model designed to streamline drug discovery by generating and optimizing molecular structures. It is helpful for a variety of tasks related to controlled molecular generation and multiparameter optimization of small molecules with user-defined oracles, allowing researchers to tailor molecule creation to specific needs. The NVIDIA GenMol can be deployed on-prem or any cloud service provider for enterprise-grade inference in drug discovery workflows, including virtual screening and lead optimization.

ProteinMPNN (Protein Message Passing Neural Network) is a deep learning-based graph neural network designed to predict amino acid sequences for given protein backbones. This network leverages evolutionary, functional, and structural information to generate sequences that are likely to fold into the desired 3D structures.

RFdiffusion (RoseTTAFold Diffusion) is a powerful deep learning model designed to generate novel protein structures and complexes.

The NVIDIA DiffDock NIM is built for high-performance, scalable molecular docking at enterprise scale. It requires protein and molecule 3D structures as input but does not require any information about a binding pocket. Driven by a generative AI model and accelerated 3D equivariant graph neural networks, DiffDock predicts up to 7.6X more poses per second compared to the baseline published model, reducing the cost of computational drug discovery workflows, including virtual screening and lead optimization.

NVIDIA NIM Audio2Face-3D (A2F-3D NIM) delivers state-of-the-art generative AI avatar animation solutions based on audio and emotion inputs. It is a core component of NVIDIA ACE, enabling the creation of intelligent, emotionally expressive digital humans. With support for real-time speech-to-facial animation and emotion-driven expressions, A2F-3D NIM powers interactive, lifelike digital humans for applications across gaming, virtual assistants, education, and more.

Correction Diffusion (CorrDiff) is a generative AI model that downscales surface and atmospheric variables to improve the accuracy and resolution of weather data. CorrDiff is a two-step approach where the mean machine learning model is corrected by another diffusion model. CorrDiff exhibits skillful deterministic and probabilistic predictions and faithfully recovers spectra and distributions for extremes.

FourCastNet (FCN) NIM predicts accurate short to medium-range global predictions at a time-step size of 6 hours with predictive stability for over a year of simulated time (1,460 steps), while retaining physically plausible dynamics. The multivariant forecast includes surface and atmospheric variables such as wind speed, temperature and pressure at various vertical levels.

NIM for LLMs makes it easy for IT and DevOps teams to self-host large language models (LLMs) in their own managed environments while still providing developers with industry standard APIs that enable them to build powerful copilots, chatbots, and AI assistants that can transform their business.

This document provides insights into how to benchmark deployment of Large Language Models (LLMs), popular metrics and parameters, as well as a step-by-step guide.

NIM for LLMs makes it easy for IT and DevOps teams to self-host large language models (LLMs) in their own managed environments while still providing developers with industry standard APIs that enable them to build powerful copilots, chatbots, and AI assistants that can transform their business.

NIM for LLMs makes it easy for IT and DevOps teams to self-host large language models (LLMs) in their own managed environments while still providing developers with industry standard APIs that enable them to build powerful copilots, chatbots, and AI assistants that can transform their business.

NIM for LLMs makes it easy for IT and DevOps teams to self-host large language models (LLMs) in their own managed environments while still providing developers with industry standard APIs that enable them to build powerful copilots, chatbots, and AI assistants that can transform their business.

NIM for LLMs makes it easy for IT and DevOps teams to self-host large language models (LLMs) in their own managed environments while still providing developers with industry standard APIs that enable them to build powerful copilots, chatbots, and AI assistants that can transform their business.

The Maxine eye contact model estimates the gaze direction of the input eye gaze and synthesizes a redirected gaze using a region of interest around one’s eyes known as an eye patch.

Studio Voice NIM leverages state-of-the-art AI models to enhance the input speech recorded through low quality microphones in noisy and reverberant environments to studio-recorded quality speech. This NIM supports 3 modes - Quality mode with 48kHz input, Quality mode with 16kHz input and Low Latency mode with 48kHz input.

NVIDIA MAISI (Medical AI for Synthetic Imaging) is a state-of-the-art three-dimensional (3D) Latent Diffusion Model designed for generating high-quality synthetic CT images with or without anatomical annotations. This AI model excels in data augmentation and creating realistic medical imaging data to supplement limited datasets due to privacy concerns or rare conditions. It can also significantly enhance the performance of other medical imaging AI models by generating diverse and realistic training data.

VISTA-3D is a specialized interactive foundation model for 3D medical imaging. It excels in providing accurate and adaptable segmentation analysis across anatomies and modalities. Utilizing a multi-head architecture, VISTA-3D adapts to varying conditions and anatomical areas, helping guide users’ annotation workflow.

Maintain topical relevance in conversational generative AI applications based on pre-defined policies.

Enhance the safety and moderation capabilities of your LLM applications.

Strengthen your LLM application against jailbreak attempts by classifying and scoring user prompts for unsafe input.

NVIDIA NeMo™ Retriever text embedding NIM microservice bring the power of state-of-the-art text embedding models to your applications, offering unparalleled natural language processing and understanding capabilities. You can use NeMo Retriever embedding NIM microservices for semantic search, retrieval-augmented generation (RAG), or any application that uses text embeddings. NeMo Retriever text embedding NIM microservices are built on the NVIDIA software platform, incorporating NVIDIA® CUDA®, TensorRT™, and Triton™ Inference Server to offer out-of-the-box GPU acceleration.

NVIDIA NeMo™ Retriever text reranking NIM microservice reorder citations by how well they match a query. This is a key step in the retrieval process, especially when the retrieval pipeline involves citations from different datastores that each have their own algorithms for measuring similarity.

Enterprises are sitting on a goldmine of data waiting to be used to improve efficiency, save money, and ultimately enable higher productivity. With generative AI, developers can build and deploy an agentic flow or a retrieval-augmented generation (RAG) chatbot, while ensuring the insights provided are based on the most accurate and up-to-date information.

Generative AI applications have little, or sometimes negative, value without accuracy — and accuracy is rooted in data.

To help developers efficiently fetch the best proprietary data to generate knowledgeable responses for their AI applications, NVIDIA today announced four new NVIDIA NeMo Retriever NIM inference microservices.

Employing retrieval-augmented generation (RAG) is an effective strategy for ensuring large language model (LLM) responses are up-to-date and not hallucinated.

While various retrieval strategies can improve the recall of documents for generation, there is no one-size-fits-all approach. The retrieval pipeline depends on your data, from hyperparameters like the chunk size, and number of documents returned, to retrieval algorithms like semantic search or graph retrieval.

Businesses seeking to harness the power of AI need customized models tailored to their specific industry needs.

NVIDIA AI Foundry is a service that enables enterprises to use data, accelerated computing and software tools to create and deploy custom models that can supercharge their generative AI initiatives.

NVIDIA NIM for NV-CLIP foundation model for image and text embedding generation.

NVIDIA Riva automatic speech recognition (ASR) NIM microservices provide record-setting English language transcriptions. They deliver exceptional accuracy and robustness, adeptly handling diverse speech patterns and noise levels. They enable businesses to advance their voice-based services, ensuring superior user experiences.

NVIDIA Riva Megatron neural machine translation (NMT) NIM provides accurate real-time translation by leveraging extensive training on publicly available datasets featuring millions of parallel sentences. This cutting-edge translation NIM enables organizations to seamlessly integrate multilingual translation into their generative AI pipelines, broadening their global reach, engaging diverse audiences, and enhancing international collaboration.

NVIDIA Riva text-to-speech (TTS) NIM microservices integrate FastPitch and HiFiGAN models to generate high-fidelity speech from text. They enable businesses to create natural-sounding voices, elevating user engagement and delivering immersive experiences, setting a new standard in voice quality.

NVIDIA NIM for Vision Language Models (VLMs) (NVIDIA NIM for VLMs) brings the power of state-of-the-art vision language models (VLMs) to enterprise applications, providing unmatched natural language processing and image and video understanding capabilities.

Operate and manage the lifecycle of the software components and services for running LLM, embedding, and other NIM microservices and models in Kubernetes.

NVIDIA NIM, part of the NVIDIA AI Enterprise software platform available on the Google Cloud Marketplace, is a set of easy-to-use microservices designed for secure, reliable deployment of high performance AI model inferencing, is now integrated with Google Kubernetes Engine (GKE), a managed Kubernetes service that is used to deploy and operate containerized applications at scale using Google’s infrastructure. NIM on GKE streamlines the deployment and management of AI inference workloads. It leverages the robust capabilities of GKE and NVIDIA"s full stack AI platform on Google Cloud to deliver a powerful and flexible solution for AI model inferencing.