Category: Misc

In the operating room, the latency and reliability of surgical video streams can make all the difference for patient outcomes. Ultra-high-speed frame rates from…

In the operating room, the latency and reliability of surgical video streams can make all the difference for patient outcomes. Ultra-high-speed frame rates from sensor inputs that enable next-generation AI applications can provide surgeons with new levels of real-time awareness and control.

To build real-time AI capabilities into medical devices for use cases like surgical navigation, image-guided intervention such as endoscopy, and medical robotics, developers need AI pipelines that allow for low-latency processing of combined sensor data from multiple channels.

As announced at GTC 2022, NVIDIA Clara Holoscan SDK v0.3 now provides a lightning-fast frame rate of 240 Hz for 4K video. This enables developers to combine data from more sensors and build AI applications that can provide surgical guidance. With faster data transfer enabled through high-speed Ethernet-connected sensors, developers have even more tools to build accelerated AI pipelines.

Real-time AI processing of frontend sensors

NVIDIA Clara Holoscan enables high-speed sensor input through the ConnectX SmartNIC and NVIDIA Rivermax SDK with GPUDirect RDMA that bypasses the CPU. This allows for high-speed Ethernet output of data from sensors into the AI compute system. The result is unmatched performance for edge AI.

While traditional GStreamer and OpenGL-based endoscopy pipelines have an end-to-end latency of 220 ms on a 1080p 60 Hz stream, high-speed pipelines with Clara Holoscan boast an end-to-end latency of only 10 ms on a 4K 240 Hz stream.

Streaming data at 4K 60 Hz at under 50 ms on NVIDIA RTX A6000, teams can run 15 concurrent AI video streams and 30 concurrent models.

NVIDIA Rivermax SDK

The NVIDIA Rivermax SDK, included with NVIDIA Clara Holoscan, enables direct data transfers to and from the GPU. Bypassing host memory and using the offload capabilities of the ConnectX SmartNIC, it delivers best-in-class throughput and latency with minimal utilization for streaming workloads. NVIDIA Clara Holoscan leverages the Rivermax functionalities to bring scalable connectivity for high-bandwidth network sensors and support very fast data transfer.

NVIDIA G-SYNC

NVIDIA G-SYNC enables high display performance by synchronizing display refresh rates to the GPU, thus eliminating screen tearing and minimizing display stutter and input lag. As a result, the AI inference can be shown with very low latency.

NVIDIA Clara HoloViz

Clara HoloViz is a module in Holoscan for visualizing data. Clara HoloViz composites real-time streams of frames with multiple different other layers like segmentation mask layers, geometry layers, and GUI layers.

For maximum performance, Clara HoloViz makes use of Vulkan, which is already installed as part of the NVIDIA driver.

Clara HoloViz uses the concept of the immediate mode design pattern for its API. No objects are created and stored by the application. This makes it easy to quickly build and change the visualization in an Holoscan application.

Improved developer experience

The NVIDIA Clara Holoscan SDK v0.3 release brings significant improvements to the development experience. First, the addition of a new C++ API for the creation of GXF extensions gives developers an additional pathway to building their desired applications. Second, the support for x86 processors allows developers to quickly get started with developing AI applications which can then be easily deployed on IGX development kits. Third, the Bring Your Own Model (BYOM) support has been enriched in this latest version.

Holoscan C++ API

The Holoscan C++ API provides a new convenient way to compose GXF workflows, without the need to write YAML files. The Holoscan C++ API enables a more flexible and scalable approach to creating applications. It has been designed for use as a drop-in replacement for the GXF Framework’s API and provides a common interface for GXF components.

Application: An application acquires and processes streaming data. An application is a collection of fragments where each fragment can be allocated to execute on a physical node of a Holoscan cluster.

Fragment: A fragment is a building block of the application. It is a directed acyclic graph (DAG) of operators. A fragment can be assigned to a physical node of a Holoscan cluster during execution. The run-time execution manages communication across fragments. In a fragment, operators (graph nodes) are connected to each other by flows (graph edges).

Operator: An operator is the most basic unit of work in this framework. An operator receives streaming data at an input port, processes it, and publishes it to one of its output ports. A codelet in GXF would be replaced with an operator in the framework. An operator encapsulates receivers and transmitters of a GXF entity as I/O ports of the operator.

Resource: Resources such as system memory or a GPU memory pool that an operator needs to perform its job. Resources are allocated during the initialization phase of the application. The resource matches the semantics of the GXF Memory Allocator or any other components derived from the component class in GXF.

Condition: A condition is a predicate that can be evaluated at runtime to determine if an operator should execute. This matches the semantics of the GXF Scheduling Term class.

Port: An interaction point between two operators. Operators ingest data at input ports and publish data at output ports. Receiver, transmitter, and MessageRouter in GXF are replaced with the concept of I/O port of the operator.

Executor: An executor manages the execution of a fragment on a physical node. The framework provides a default executor that uses a GXF scheduler to execute an application.

You can find more information about the new C++ API in the SDK documentation. See an example of a full AI application for endoscopy tool tracking using the new C++ API in the public source code repository.

Support for x86 systems

The NVIDIA Clara Holoscan SDK has been designed with various hardware systems in mind. It supports using the SDK on x86 systems, in addition to the NVIDIA IGX DevKit and the Clara AGX DevKit. With x86 support, researchers and developers who do not have a DevKit can use the Holoscan SDK on their x86 machines to quickly build AI applications for medical devices.

Bring Your Own Model

The Holoscan SDK provides AI libraries and pretrained AI models to jump-start the timeline to build your own AI applications. You can also reference applications for endoscopy and ultrasound with Bring Your Own Model (BYOM) support.

As a developer, you can quickly build AI pipelines by dropping your own models in the reference applications provided as part of the SDK. Finally, the SDK also includes sensor I/O integration options and performance tools that optimize AI applications for production deployment.

Software stack updates

The NVIDIA Clara Holoscan SDK v0.3 release also integrates an upgrade from NVIDIA JetPack HP1 to Holopack 1.1, running the Tegra Board Support Package (BSP) version 34.1.3, as well as an upgrade for GXF from version 2.4.2 to version 2.4.3.

Get started building AI for medical devices

From training AI models to verifying and validating AI applications and ultimately deploying for commercial production, Clara Holoscan helps streamline AI development and deployment. 

Visit the Clara Holoscan SDK web page to access healthcare-specific acceleration libraries, pretrained AI models, sample applications, documentation, and more to get started building software-defined medical devices.

You can also request a free hands-on lab with NVIDIA LaunchPad to experience how Clara Holoscan simplifies the development of AI pipelines for endoscopy and ultrasound.

Deploying AI models in production to meet the performance and scalability requirements of the AI-driven application while keeping the infrastructure costs low…

Deploying AI models in production to meet the performance and scalability requirements of the AI-driven application while keeping the infrastructure costs low is a daunting task.

This post provides you with a high-level overview of AI inference challenges that commonly occur when deploying models in production, along with how NVIDIA Triton Inference Server is being used today across industries to solve these cases.

We also examine some of the recently added features, tools, and services in Triton that simplify the deployment of AI models in production, with peak performance and cost efficiency.

Challenges to consider when deploying AI inference

AI inference is the production phase of running AI models to make predictions. Inference is complex but understanding the factors that affect your application’s speed and performance will help you deliver fast, scalable AI in production.

Challenges for developers and ML engineers

• Many types of models: AI, machine learning, and deep learning (neural network–based) models with different architectures and different sizes.
• Different inference query types: Real-time, offline batch, streaming video and audio, and model pipelines make meeting application service level agreements challenging.
• Constantly evolving models: Models in production must be updated continuously based on new data and algorithms, without business disruptions.

Challenges for MLOps, IT, and DevOps practitioners

• Multiple model frameworks: There are different training and inference frameworks like TensorFlow, PyTorch, XGBoost, TensorRT, ONNX, or just plain Python. Deploying and maintaining each of these frameworks in production for applications can be costly.
• Diverse processors: The models can be executed on a CPU or GPU. Having a separate software stack for each processor platform leads to unnecessary operational complexity.
• Diverse deployment platforms: Models are deployed on public clouds, on-premises data centers, at the edge, and on embedded devices on bare metal, virtualized, or a third-party ML platform. Disparate solutions or less than optimal solutions to fit the given platform leads to poor ROI.  This might include slower rollouts, poor app performance, or using more resources.

A combination of these factors makes it challenging to deploy AI inference in production with the desired performance and cost efficiency.

New AI inference use cases using NVIDIA Triton

NVIDIA Triton Inference Server (Triton), is an open source inference serving software that supports all major model frameworks (TensorFlow, PyTorch, TensorRT, XGBoost, ONNX, OpenVINO, Python, and others). Triton can be used to run models on x86 and Arm CPUs, NVIDIA GPUs, and AWS Inferentia. It addresses the complexities discussed earlier through standard features.

Triton is used by thousands of organizations across industries worldwide. Here’s how Triton helps solves AI inference challenges for some customers.

NIO Autonomous Driving

NIO uses Triton to run their online services models in the cloud and data center. These models process data from autonomous driving vehicles. NIO used the Triton model ensemble feature to move their pre– and post-processing functions from client application to Triton Inference Server. The preprocessing was accelerated by 5x, increasing their overall inference throughput and enabling them to cost-efficiently process more data from the vehicles.

GE Healthcare

GE Healthcare uses Triton in their Edison platform to standardize inference serving across different frameworks (TensorFlow, PyTorch, ONNX, and TensorRT) for in-house models. The models are deployed on a variety of hardware systems from embedded (for example, an x-ray system) to on-premises servers.

Wealthsimple

The online investment management firm uses Triton on CPUs to run their fraud detection and other fintech models. Triton helped them consolidate their different serving software across applications into a single standard for multiple frameworks.

Tencent

Tencent uses Triton in their centralized ML platform for unified inference for several business applications. In aggregate, Triton helps them process 1.5M queries per day. Tencent achieved low cost of inference through Triton dynamic batching and concurrent model execution capabilities.

Alibaba Intelligent Connectivity

Alibaba Intelligent Connectivity is developing AI systems for their smart speaker applications.  They use Triton in the data center to run models that generate streaming text to speech for the smart speaker. Triton delivered the lowest first packet latency needed for a good audio experience.

Yahoo Japan

Yahoo Japan uses Triton on CPUs in the data center to run models to find similar locations for the “spot search” functionality in the Yahoo Browser app. Triton is used to run the complete image search pipeline and is also integrated into their centralized ML platform to support multiple frameworks on CPUs and GPUs.             

Airtel

The second largest wireless provider in India, Airtel uses Triton for automatic speech recognition (ASR) models for contact center application to improve customer experience. Triton helped them upgrade to a more accurate ASR model and still get a 2x throughput increase on GPUs compared to the previous serving solution.

How Triton Inference Server addresses AI inference challenges

From fintech to autonomous driving, all applications can benefit from out-of-box functionality to deploy models into production easily.

This section discusses a few key new features, tools, and services that Triton provides out-of-box that can be applied to deploy, run, and scale models in production.

Model orchestration with new management service

Triton brings a new model orchestration service for efficient multi-model inference. This software application, currently in early access, helps simplify the deployment of Triton instances in Kubernetes with many models in a resource-efficient way. Some of the key features of this service include the following:

• Loading models on demand and unloading models when not in use.
• Efficiently allocating GPU resources by placing multiple models on a single GPU server wherever possible
• Managing custom resource requirements for individual models and model groups

For a short demo of this service, see Take Your AI Inference to the Next Level. The model orchestration feature is in private early access (EA). If you are interested in trying it out, sign up now.

Large language model inference

In the area of natural language processing (NLP), the size of models is growing exponentially (Figure 1). Large transformer-based models with hundreds of billions of parameters can solve many NLP tasks such as text summarization, code generation, translation, or PR headline and ad generation.

But these models are so large that they cannot fit in a single GPU. For example, Turing-NLG with 17.2B parameters needs at least 34 GB of memory to store weights and biases in FP16 and GPT-3 with 175B parameters needs at least 350 GB. To use them for inference, you need multi-GPU and increasingly multi-node execution for serving the model.

Triton Inference Server has a backend called FasterTransformer that brings multi-GPU multi-node inference for large transformer models like GPT, T5, and others. The large language model is converted to FasterTransformer format with optimizations and distributed inference capabilities and is then run using Triton Inference Server across GPUs and nodes.

Figure 2 shows the speedup observed with Triton to run the GPT-J (6B) model on a CPU or one and two A100 GPUs.

For more information about large language model inference with the Triton FasterTransformer backend, see Accelerated Inference for Large Transformer Models Using NVIDIA Triton Inference Server and Deploying GPT-J and T5 with NVIDIA Triton Inference Server.

Inference of tree-based models

Triton can be used to deploy and run tree-based models from frameworks such as XGBoost, LightGBM, and scikit-learn RandomForest on both CPUs and GPUs with explainability using SHAP values. It accomplishes that using the Forest Inference Library (FIL) backend that was introduced last year.

The advantage of using Triton for tree-based model inference is better performance and standardization of inference across machine learning and deep learning models. It is especially useful for real-time applications such as fraud detection, where bigger models can be used easily for better accuracy.

For more information about deploying a tree-based model with Triton, see Real-time Serving for XGBoost, Scikit-Learn RandomForest, LightGBM, and More. The post includes a fraud detection notebook.

Try this NVIDIA Launchpad lab to deploy an XGBoost fraud detection model with Triton.

Optimal model configuration with Model analyzer

Efficient inference serving requires choosing optimal values for parameters such as batch size, model concurrency, or precision for a given target processor. These values dictate throughput, latency, and memory requirements. It can take weeks to try hundreds of combinations manually across a range of values for each parameter.

The Triton model analyzer tool reduces the time that it takes to find the optimal configuration parameters, from weeks to days or even hours. It does this by running hundreds of simulations of inference with different values of batch size and model concurrency for a given target processor offline. At the end, it provides charts like Figure 3 that make it easy to choose the optimal deployment configuration. For more information about the model analyzer tool and how to use it for your inference deployment, see Identifying the Best AI Model Serving Configurations at Scale with NVIDIA Triton Model Analyzer.

Model pipelines with business logic scripting

With the model ensemble feature in Triton, you can build out complex model pipelines and ensembles with multiple models and pre– and post-processing steps. Business logic scripting enables you to add conditionals, loops, and reordering of steps in the pipeline.

Using the Python or C++ backends, you can define a custom script that can call any other model being served by Triton based on conditions that you choose. Triton efficiently passes data to the newly called model, avoiding unnecessary memory copying whenever possible. Then the result is passed back to your custom script, from which you can continue further processing or return the result.

Figure 4 shows two examples of business logic scripting:

• Conditional execution helps you use resources more efficiently by avoiding the execution of unnecessary models.
• Autoregressive models, like transformer decoding, require the output of a model to be repeatedly fed back into itself until a certain condition is reached. Loops in business logic scripting enable you to accomplish that.

For more information, see Business Logic Scripting.

Auto-generation of model configuration

Triton can automatically generate config files for your models for faster deployment. For TensorRT, TensorFlow, and ONNX models, Triton generates the minimum required config settings to run your model by default when it does not detect a config file in the repository.

Triton can also detect if your model supports batched inference. It sets max_batch_size to a configurable default value.

You can also include commands in your own custom Python and C++ backends to generate model config files automatically based on the script contents. These features are especially useful when you have many models to serve, as it avoids the step of manually creating the config files. For more information, see Auto-generated Model Configuration.

Decoupled input processing

While many inference settings require a one-to-one correspondence between inference requests and responses, this isn’t always the optimal data flow.

For instance, with ASR models, sending the full audio and waiting for the model to finish execution may not result in a good user experience. The wait can be long. Instead, Triton can send back the transcribed text in multiple short chunks (Figure 5), reducing the latency and time to the first response.

With decoupled model processing in the C++ or Python backend, you can send back multiple responses for a single request. Of course, you could also do the opposite: send multiple small requests in chunks and get back one big response. This feature provides flexibility in how you process and send your inference responses. For more information, see Decoupled Models.

For more information about recently added features, see the NVIDIA Triton release notes.

Get started with scalable AI model deployment

You can deploy, run, and scale AI models with Triton to effectively mitigate AI inference challenges that you may have with multiple frameworks, a diverse infrastructure, large language models, optimal model configurations, and more.

Triton Inference Server is open-source and supports all major model frameworks such as TensorFlow, PyTorch, TensorRT, XGBoost, ONNX, OpenVINO, Python, and even custom frameworks on GPU and CPU systems. Explore more ways to integrate Triton with any application, deployment tool, and platform, on the cloud, on-premises, and at the edge.

For more information, see the following resources:

• Get started with NVIDIA Triton and access a variety of beginner to advanced resources.
• Uncover the features that you need in an inference platform when building a real-time or continuous data streaming application, Fast and Scalable AI Model Deployment with NVIDIA Triton Inference Server.
• Find out why traditional computing infrastructure is no longer enough to support large-scale AI, The secret to rapid and insightful AI–GPU-accelerated computing.
• Looking for a hands-on skills lab? Deploy an AI support chatbot or train your own AI model for image classification of online products on NVIDIA LaunchPad.

Whether for virtual assistants, transcriptions or contact centers, voice AI services are turning words and conversations into bits and bytes of business magic. Today at GTC, NVIDIA announced new additions to NVIDIA Riva, a GPU-accelerated software development kit for building and deploying speech AI applications. Riva’s pretrained models are now offered in seven languages, including Read article >

The post Now You’re Speaking My Language: NVIDIA Riva Sets New Bar for Fully Customizable Speech AI appeared first on NVIDIA Blog.

The cellular industry spends over $50 billion on radio access networks (RAN) annually, according to a recent GSMA report on the mobile economy. Dedicated and…

The cellular industry spends over $50 billion on radio access networks (RAN) annually, according to a recent GSMA report on the mobile economy. Dedicated and overprovisioned hardware is primarily used to provide capacity for peak demand. As a result, most RAN sites have an average utilization below 25%. 

This has been the industry reality for years as technology evolved from 2G to 4G. But it is set to become even more pronounced in 5G as the push for densification, combined with the use of mmWave, leads to a near doubling of the number of cell sites by 2027 to over 17 million. The implication is that RAN capital expenditures, as a share of overall network total cost of ownership (TCO), will grow to as much as 65% in 5G, compared to 45-50% in 4G. 

A new game-changing approach turns underutilization into an opportunity: leverage the same cloud and data center infrastructure used for AI to dynamically load share with 5G virtual RAN (vRAN). This approach creates a new opportunity for cloud providers and helps reduce operational costs. 

Figure 1 shows how NVIDIA is enabling the CloudRAN solution with the NVIDIA A100X converged card, Spectrum SN3750SX Switch, NVIDIA Aerial SDK, and containerized DU.

The opportunity of RAN underutilization 

By pooling baseband computing resources into a cloud-native environment, the CloudRAN solution delivers significant improvements in asset utilization, creating efficiency gains for telcos and revenue opportunities for cloud service providers (CSPs). The solution achieves this by dynamically orchestrating resources between 5G and 5G RAN off-peak workloads. 

Examples of 5G RAN off-peak workloads are AI workloads such as drive mapping, federated learning, offline video analytics, predictive maintenance, factory digital twins, and many more. 5G compute capacity is mapped to changes in traffic demands from 5G radios, while the remaining compute is used for AI workloads. For telcos, this can increase RAN operational efficiency by more than 2x for an estimated 25% or more impact on the operating margin. 

For CSPs, running 5G vRAN as a workload alongside AI workloads within their existing data center architecture is a significant opportunity. To look at a specific example, the United States wireless market includes about 420,000 cell sites. If the telcos are using Centralized-RAN (C-RAN) for 50% of their network (mostly urban areas) and running a 4:1 configuration, then they will be using 52,000 GPUs to run their network. 

In a typical data center, the hourly GPU compute rate is $2. A C-RAN configuration using dynamic orchestration to combine 5G and AI workloads and the CSP’s monetization of 52,000 GPUs will lead to a $500 million revenue opportunity. Globally, this is a multi-billion dollar opportunity. 

Figure 2 shows the off-peak AI workloads that can dynamically share the C-RAN GPU with the 5G workload during off-peak periods. 

To provide an example, the combination of in-vehicle AI supercomputer and GPU resources in the cloud enables offline processing for self-driving cars. The system incorporates deep learning algorithms to detect lanes, signs, and other landmarks using a combination of AI and visual simultaneous localization and mapping (VSLAM). 

The industry recognizes the general trend to pull softwarized RAN resources together in a few centralized hub locations. While this improves RAN TCO by more than 30% over distributed-RAN topology, it does not solve RAN underutilization. Why? The unused RAN compute resource goes to waste during off-peak periods. 

NVIDIA CloudRAN: Five building blocks 

To realize the CloudRAN solution, current vRANs will need to evolve in the following five key focus areas. 

First, there is a need for a software-defined fronthaul (SD-FH) with an optimal timing mechanism. Second, the RAN hardware needs to evolve from bespoke, dedicated, and (in many cases) non-cloud-native architecture, to COTS-based and cloud-native hardware. Third, the softwarized 5G RAN needs to be programmable in real time and capable of running on cloud infrastructure. Fourth, the lifecycle management (LCM) of the 5G RAN needs to be dynamic and based on open APIs. 

Finally, there is a need for an end-to-end (E2E) network and service orchestrator that can dynamically manage RAN and other off-peak workloads based on network and infrastructure utilization information. E2E service orchestration executes service intent by dynamically composing the workflow based on service models, policy, and context and using closed-loop control to automate the entire service and network.

NVIDIA CloudRAN identifies and offers an enabling solution for each of the five identified evolution needs of vRAN, as shown in Figure 3.

• SD-FH switch: NVIDIA SN3750-SX is a new 200G Ethernet switch based on the Spectrum-2 ASIC. It was purpose-built to provide the network fabric for CloudRAN-converged infrastructure where it runs AI training workloads alongside 5G networking. It has software-defined and hardware-accelerated 5G fronthaul capabilities to steer 5G traffic available DUs to RUs based on orchestrator mapping. It offers 5G time sync protocols with PTP telco profiles, SyncE, and PPS in/out. The switch also supports the NetQ validation toolset.
• General purpose computing hardware: The NVIDIA A100X converged card combines the power of the NVIDIA A100 Tensor Core GPU with the advanced networking capabilities of the NVIDIA BlueField-2 DPU in a single, unique platform. This convergence delivers unparalleled performance for GPU-powered, I/O-intensive workloads, such as distributed AI training in the enterprise data center and 5G vRAN processing as another workload within existing data center architecture. 
• Programmable and cloud-native 5G software: The NVIDIA Aerial SDK provides the 5G workload in the CloudRAN solution. NVIDIA Aerial is a fully cloud-native virtual 5G RAN solution running on COTS servers. It realizes RAN functions as microservices in containers over bare-metal servers, using Kubernetes and applying DevOps principles. It provides a 5G RAN solution, with inline L1 GPU acceleration for 5G NR PHY processing and supports a full stack framework for a gNB integration L2/L3 (MAC, RLC, PDCP), along with manageability and orchestration.
• Open API lifecycle management: The O-RAN disaggregated, software-centric approach can help automate and orchestrate RAN complexity, irrespective of multi-vendor or multi-technology networks. Ultimately, the service management orchestration (SMO) will provide open and Kubernetes cluster APIs for RAN automation.
• E2E network and service orchestrator: E2E orchestration enables dynamic applications and services by consolidating an E2E view in real time across all technology and cloud domains. A single pane of glass enables automation of all aspects of cross-domain services and manages lifecycle management, optimization, and assurance of various workloads. The E2E orchestrator will also have an interface to interact with the cloud infrastructure manager. 

Delivering the CloudRAN solution

The NVIDIA CloudRAN solution delivers a compelling value proposition with an SD-FH, general purpose data center compute, cloud-native architecture, RAN domain orchestrator, and E2E service and network orchestrator. 

NVIDIA and its ecosystem partners are building a Kubernetes-based SMO and E2E service orchestrator to support dynamic workload management. With telcos, NVIDIA is working on COTS-based and cloud-native vRAN software. With CSPs, NVIDIA is working to optimize data center hardware to support 5G workloads. 

Join us for the GTC 2022 session, Using AI Infrastructure in the Cloud for 5G vRAN to learn more about the CloudRAN solution. 

Dentists get a bad rap. Dentists also get more people out of more aggravating pain than just about anyone. Which is why the more technology dentists have, the better. Overjet, a member of the NVIDIA Inception program for startups, is moving fast to bring AI to dentists’ offices. On this episode of the NVIDIA AI Read article >

The post A Podcast With Teeth: How Overjet Brings AI to Dentists’ Offices appeared first on NVIDIA Blog.

The field of computational biology relies on bioinformatics tools that are fast, accurate, and easy to use. As next-generation sequencing (NGS) is becoming…

The field of computational biology relies on bioinformatics tools that are fast, accurate, and easy to use. As next-generation sequencing (NGS) is becoming faster and less costly, a data deluge is emerging, and there is an ever-growing need for accessible, high-throughput, industry-standard analysis.

At GTC 2022, we announced the release of NVIDIA Clara Parabricks v4.0, which brings significant improvements to how genomic researchers and bioinformaticians deploy and scale genome sequencing analysis pipelines.

• Clara Parabricks software is now free to researchers on NGC as individual tools or as a unified container. A licensed version is available through NVIDIA AI Enterprise for customers requiring enterprise-grade support.
• Clara Parabricks is now easily integrated into common workflow languages such as Workflow Description Language (WDL) and NextFlow, for the interweaving of GPU-accelerated and third-party tools, and scalable deployment on-premises and in the cloud. The Cromwell workflow management system from the Broad Institute is also supported. 
• Clara Parabricks can now be deployed on the Broad Institute’s Terra SaaS platform, making it available to the 25,000+ Terra scientists. Genome analysis is reduced to just over one hour with Clara Parabricks compared to 24 hours in a CPU environment, while reducing costs by 50% for whole genome sequencing analysis.
• Clara Parabricks continues to focus on GPU-accelerated, industry-standard, and deep-learning-based tools and has included the latest DeepVariant v1.4 germline caller. Development in the areas of sequencer-agnostic tooling and deep learning approaches are a focus of Clara Parabricks.
• Clara Parabricks is now available through more cloud providers and partners, including Amazon Web Services, Google Cloud Platform, Terra, DNAnexus, Lifebit, Agilent Technologies, UK Biobank Research Analysis Platform (RAP), Oracle Cloud Infrastructure, Naver Cloud, Alibaba Cloud, and Baidu AI Cloud.

License-free use for research and development

Clara Parabricks v4.0 is now available entirely free of charge for research and development. This means fewer technical barriers than ever before, including the removal of the install scripts and the enterprise license server present in previous versions of the genomic analysis software. 

This also means significant simplification in deployment, with the ability to pull and run Clara Parabricks Docker containers quickly and easily, on any NVIDIA-certified systems, with maximum ease of use on-premises or in the cloud.

Commercial users that require enterprise-level technical and engineering support for their production workflows, or to work with NVIDIA experts on new features, applications, and performance optimizations, can now subscribe to NVIDIA AI Enterprise Support. This support will be available for Parabricks v4.0 with the upcoming release of NVIDIA AI Enterprise v3.0.

An NVIDIA AI Enterprise Support subscription comes with full-stack support (from container-level, through to full on-premises and cloud deployment), access to NVIDIA Parabricks experts, security notifications, enterprise training in areas such as IT or data science, and deep learning support for TensorFlow, PyTorch, NVIDIA TensorRT, and NVIDIA RAPIDS. Learn more about NVIDIA AI Enterprise Support Services and Training. 

Deploying in WDL and NextFlow workflows

You can now pull Clara Parabricks directly from NGC collection containers with no licensing server, meaning that it can easily be run as part of scalable and flexible bioinformatics workflows on a variety of systems and platforms.

This includes popular bioinformatics workflow managers WDL and NextFlow that are available on the new Clara-Parabricks-Workflows GitHub repo for general use by the bioinformatics community. You can find WDL and NextFlow workflows or modules for the following:

• BWA-MEM alignment and processing with Clara Parabricks FQ2BAM
• A germline calling workflow running accelerated HaplotypeCaller and DeepVariant, with the option to apply the GATK best practices
• A BAM2FQ2BAM workflow to extract reads and realign to new reference genomes (such as the T2T completed human genome)
• A somatic workflow using accelerated Mutect2, with an optional panel of normals
• A workflow to generate a new panel of normals for somatic variant calling from VCFs
• A workflow to build reference indexes (required for several of the workflows and tasks listed earlier)

In addition, a workflow for calling de novo mutations in trio data developed in collaboration with researchers at the National Cancer Institute will be available later this year.

These workflows bring impressive flexibility, enabling users to interweave the GPU-accelerated tools of Clara Parabricks with third-party tooling. They can specify individual compute resources for each task, before deploying at a massive scale on local clusters (on SLURM, for example) or on cloud platforms. See the Clara-Parabricks-Workflows GitHub repo for example configurations and recommended GPU instances.

Run on-premises or in the cloud

Clara Parabricks is well-suited to cloud deployment. It is available to run on several cloud platforms, including Amazon Web Services, Google Cloud Services, DNAnexus, Lifebit, Baidu AI Cloud, Naver Cloud, Oracle Cloud Infrastructure, Alibaba Cloud, Terra, and more.

Clara Parabricks v4.0 WDL workflows are now integrated into the Broad Institute’s Terra platform for its 25,000+ scientists to run accelerated genomic analyses. Terra’s scalable platform runs on top of Google Cloud, which hosts a fleet of NVIDIA GPUs. A FASTQ to VCF analysis on a 30x whole genome takes 24 hours in a CPU environment compared to just over one hour with Clara Parabricks in Terra. In addition, costs are reduced by over 50%, from $5 to $2 (Figure 3).

In the Terra platform, researchers can gain access to a wealth of data much more easily than in an on-premises environment. They can access the Clara Parabricks workspace at the push of a button, rather than manually managing and configuring the hardware. Get started at the Clara Parabricks page on the Terra Community Workbench.

Runtimes and compute cost (preemptible pricing) for germline analysis of a 30x whole genome (including BWA-MEM, MarkDuplicates, BQSR, and HaplotypeCaller) are greatly reduced when using Clara Parabricks and NVIDIA GPUs.

Clara Parabricks v4.0 tools and features

Clara Parabricks v4.0 is a more focused genomic analysis toolset than previous versions, with rapid alignment, gold standard processing, and high accuracy variant calling. It offers the flexibility to freely and seamlessly intertwine GPU and CPU tasks and prioritize the GPU-acceleration of the most popular and bottlenecked tools in the genomics workflow. Clara Parabricks can also integrate cutting-edge deep learning approaches in genomics.

The individual Clara Parabricks tools are also now offered in individual containers in the Clara Parabricks collection on NGC or as a unified container that encompasses all tools in one. For the individual containers, bioinformaticians can access lean containers, and the Clara Parabricks team can push more frequent agile per-tool releases to give access to the latest versions. 

The first of these releases is for DeepVariant v1.4. This latest version of DeepVariant increases accuracy across multiple genomics sequencers. There is an additional read insert size feature for Illumina whole genome and whole exome models, which reduces errors by 4-10%, and direct phasing for more accurate variant calling in PacBio sequencing runs. This means that you can now perform the high-accuracy process of phased variant calling for PacBio data directly in DeepVariant, with pipelines such as DeepVariant-WhatsHap-DeepVariant or PEPPER-Margin-DeepVariant.

DeepVariant v1.4 is also compatible with multiple custom DeepVariant models for emerging genomics sequencing instruments. The models have been GPU-accelerated in collaboration with the NVIDIA Clara Parabricks team to provide rapid and high-accuracy variant calls across sequencing instruments. DeepVariant v1.4 is now available in the Clara Parabricks collection on NGC.

Deep learning approaches to genomics and precision medicine is a big focus for Clara Parabricks and is highlighted in the GTC 2022 NVIDIA and Broad Institute announcement on further developments on the Genome Analysis Toolkit (GATK) and large language models for DNA and RNA.

Get started with Clara Parabricks v4.0 

To start using Clara Parabricks for free, visit the Clara Parabricks collection on NGC. You can also request a free Clara Parabricks NVIDIA LaunchPad lab to get hands-on experience running accelerated industry-standard tools for germline and somatic analysis for an exome and whole genome dataset.

For more information about Clara Parabricks, including technical details on the tools available, see the Clara Parabricks documentation.

Developing for the medical imaging AI lifecycle is a time-consuming and resource-intensive process that typically includes data acquisition, compute, and…

Developing for the medical imaging AI lifecycle is a time-consuming and resource-intensive process that typically includes data acquisition, compute, and training time, and a team of experts who are knowledgeable in creating models suited to your specific challenge. Project MONAI, the medical open network for AI, is continuing to expand its capabilities to help make each of these hurdles easier no matter where developers are starting in their medical AI workflow. 

A growing open-source platform for better medical AI

MONAI is the domain-specific, open-source medical AI framework that drives research breakthroughs and accelerates AI into clinical impact. It unites doctors with data scientists to unlock the power of medical data for deep learning models and deployable applications in medical AI workflows. MONAI features domain-specific tools in data labeling, model training, and application deployment that enable you to develop, reproduce, and standardize on medical AI lifecycles. 

The release of MONAI v1.0 brings a number of exciting new updates and tools for developers, including:

• Model Zoo
• Active Learning in MONAI Label
• Auto-3D Segmentation
• Federated Learning

MONAI is the fastest growing open-source platform that provides deep learning infrastructure and workflows optimized for medical imaging in a native PyTorch paradigm. Freely available and optimized for supercomputing scale, MONAI is backed by 12 of the top Academic Medical Centers (AMCs) and has 50,000 downloads per month. From research to clinical products, the launch of MONAI v1.0 allows researchers and developers to build models and applications in a quick and standardized way. 

Jump-start training workflows with MONAI Model Zoo

Training and constructing your own AI models takes significant time, data, compute power, and knowledge of training algorithms. MONAI Model Zoo enables developers to quickly discover pretrained and openly available models specific to medical imaging. By using the MONAI Bundle Format, you can get started with these models in just a few commands.

MONAI Model Zoo offers a curated collection of medical imaging AI models. It is also a framework for you as a developer to create and publish your own models, resulting in an open-source collection of pretrained medical imaging models that can be used to speed up the development process. 

Driven by the community, Model Zoo makes cutting-edge medical AI tasks accessible and helps you get started quickly in your workflows with plug-and-play documentation, examples, and bundles. Among the main contributors to Model Zoo are NVIDIA, KCL, Kitware, Vanderbilt, and Charite, including more than 15 models across imaging modalities such as CT, pathology, ultrasound, and endoscopy to perform segmentation, classification, annotation tasks, and more.

Build better datasets with active learning

The process of labeling data can be time consuming, and experts who can annotate these images may not have time to annotate every image. MONAI Label has enhanced active learning capabilities, which is a process that aims to use the least amount of data to achieve the highest possible model performance. Choosing data that will have the greatest influence on your overall model accuracy allows human annotators to focus on the annotations that will have the highest impact on the model performance.

MONAI Label provides a clinician-friendly application to expertly label data in a fraction of the time while simultaneously training a model at the push of a button. With approaches like active learning, AI-powered algorithms can intelligently select the most difficult images for clinical inputs and increase the performance of the AI model as it learns from the expert. This enables human annotators to focus on the annotations that will provide the highest gain in model performance and address areas with model uncertainty. 

Active learning serves to build better datasets in a fraction of the time it would take humans to curate. MONAI Label can now automatically review and label large datasets, flag image data that requires human input, and then query the clinician to label it before it is added back into the training data. 

Developers can see up to 75% reduction in training costs with active learning in MONAI Label with increased labeling and training efficiency while achieving better model performance. With active learning, only 25% of the actual training dataset was used to achieve the same result of 0.82 Dice Score as training on 100% of the training dataset.

Accelerate 3D segmentation

The process of model training to achieve a state-of-the-art 3D segmentation model takes significant time, compute, and developer and researcher expertise. To help accelerate this process, MONAI now offers a low-code 3D medical image segmentation framework that speeds up model training time without human interaction.

The MONAI Auto-3D Segmentation tool is a low-code framework that allows developers and researchers of any skill level to train models that can quickly delineate regions of interest in data from 3D imaging modalities like CT and MRI. It accelerates training time for developers from one week to two days with effective models, efficient workflows, and customizability to user needs.

Features include:

• Data analysis tool
• Automated configuration
• Model training in a MONAI bundle
• Model ensemble tool
• Workflow manager
• Trained model weights

Federated learning on MONAI

MONAI v1.0 includes the federated learning (FL) client algorithm APIs that are exposed as an abstract base class for defining an algorithm to be run on any federated learning platform.

NVIDIA FLARE, the federated learning platform, has already built the integration piece with these new APIs. Using MONAI Bundle configurations with new federated learning APIs, any bundle can be seamlessly extended to a federated paradigm. We welcome other federated learning toolkits to integrate with MONAI FL APIs, building a common foundation for carrying out collaborative learning in medical imaging.

Get started with MONAI

To get started with MONAI v1.0, visit the MONAI website. Access Python libraries, Jupyter notebooks, and MONAI tutorials on the Project MONAI GitHub repo.

You can also request a free hands-on lab through NVIDIA LaunchPad to get started annotating and adapting medical imaging models with MONAI Label.

At GTC 2022, NVIDIA revealed major updates to its suite of NVIDIA AI frameworks for building real-time speech AI applications, designing high-performing…

At GTC 2022, NVIDIA revealed major updates to its suite of NVIDIA AI frameworks for building real-time speech AI applications, designing high-performing recommenders at scale, applying AI to cybersecurity challenges, creating AI-powered medical devices, and more.

Showcased real-world, end-to-end AI frameworks highlighted the customers and partners leading the way in their industries and domains. When organizations put their AI frameworks into production, enterprise support with NVIDIA AI Enterprise ensures the success of these AI applications.

Watch the keynote from founder and CEO Jensen Huang to explore the latest AI technology advancements from NVIDIA and learn new ways to put AI into production.

---

NVIDIA Riva

NVIDIA announced new updates to Riva, an accelerated SDK for enabling speech AI frameworks. Build and deploy fully customizable real-time AI pipelines with world-class automatic speech recognition (ASR) and text-to-speech (TTS): in the cloud, at the edge, on-premises, or on embedded devices.

Highlights:

• World-class ASR in two new languages: Hindi and French.
• 5–30% out-of-the-box accuracy improvement for English, Spanish, Mandarin, Russian, and German.
• Easy voice emphasis, volume, and pause control at inference time with the SSML API.
• Compact and simple one TTS model with multiple synthetic voices allowing voice selection at inference time.
• Embedded Riva with seven ASR languages and two out-of-the-box female and male English TTS voices below 100 ms latency.
• Access to NVIDIA AI experts, training, and knowledge-based resources through NVIDIA Enterprise Support with the purchase of NVIDIA AI Enterprise software.

Get started with downloading Riva, try guided Riva labs on ready-to-run infrastructure in LaunchPad, or get support for large-scale Riva deployments with NVIDIA AI Enterprise software.

Add these GTC sessions to your calendar:

• How to Make Your Conversational Application Talk
• Speech-to-Text at Scale
• Speech AI Demystified 
• AI Development Platform Helps on Conversational AI
• Building Conversational AI Applications DLI course (additional session)

---

NVIDIA Morpheus

At GTC, NVIDIA announced updates to Morpheus, a GPU-accelerated cybersecurity framework that enables developers to create optimized AI pipelines for filtering, processing, and classifying large volumes of real-time data.

New data visualizations included with the latest Morpheus release aid security analysts in pinpointing anomalies, with built-in explainability, enabling them to quickly determine a set of actionable next steps to remediate.

Additional new features:

• Digital fingerprinting workflow including fine-tunable explainability and thresholding to customize for your environment.
• A new visualization tool for digital fingerprinting provides massive data reduction for analyzed events so that security analysts can more quickly investigate and remediate.
• Visual graph-based explainer for sensitive information detection use cases enables security analysts to identify leaked sensitive data more easily.
• Multi-process pipeline support enables new workflows to be intelligently batched to reduce latency.

Learn more about the latest release of NVIDIA Morpheus. Get started with NVIDIA Morpheus on the nv-morpheus/Morpheus GitHub repo or NGC, or try it on NVIDIA LaunchPad.  

Add these GTC sessions to your calendar:

• Learn About the Latest Developments with AI-Powered Cybersecurity
• Deriving Cyber Resilience from the Data Supply Chain
• Accelerating the Next Generation of Cybersecurity Research

---

NVIDIA cuOpt

NVIDIA announced the worldwide open availability of its cuOpt AI logistics software framework. cuOpt offers near real-time routing optimizations, empowering businesses to make use of larger data sets with faster processing.

Companies can now employ new capabilities such as dynamic rerouting, simulations, and subsecond solver response time for last-mile delivery, supply chain management, and warehouse picking.

Major updates:

• New containerized server API
• Availability on major public clouds such as GCP, AWS, Azure, and more
• Solving 700 variants of routing problems with top accuracy, speed, and scale to 10K locations per GPU
• Ability to connect with NVIDIA Isaac Sim to discover the speed of light in your next intralogistics design
• Leverage cuOpt’s world-record accuracy, based on benchmarks of Gehring and Homberger​’s vehicle routing (CVRPTW) and Li&Lim’s pick up and deliveries (PDPTW) benchmark

For more information, download NVIDIA cuOpt on the /nvidia/cuopt-resources GitHub repo or try it on NVIDIA LaunchPad.

Add these GTC sessions to your calendar:

• Solving the Largest Optimization Problems in Seconds with Parallel Heuristics
• Optimizing Digital Twins to Reduce Intra-Factory Costs up to 20%
• How AT&T Supercharged their Data Science Efforts

---

NVIDIA Merlin

Today, NVIDIA announced updates to NVIDIA Merlin, an end-to-end recommender systems framework designed to accelerate data processing, training, inference, and deployment at scale.

With the latest release, data scientists and machine learning engineers can quickly build and deploy models on CPU and GPU, as well as scaling to terabyte (TB) size model training and inference.

Noted features:

• Easily build and compare common popular retrieval and ranking models across TensorFlow, XGBoost, and Implicit.
• Ability to build sequential and session-based recommendations by leveraging Hugging Face transformer-based architectures.
• Discovering model-parallelism for distributed embeddings that optimize TB model training for scalability and flexibility.
• Scaling inference to TB models with low latency and high throughput.

Ease your recommender experimentation frameworks and download it from the NVIDIA-Merlin GitHub repo today.

Add these GTC sessions to your calendar:

• Cross-Framework Model Evaluation and Accelerated Training with NVIDIA Merlin
• A Transformer-Powered Recommendation Engine for Personalized Online Advertising

---

NVIDIA Tokkio

At GTC, NVIDIA presented how NVIDIA Avatar Cloud Engine (ACE) is being used to put together incredibly complex avatar applications, including Tokkio, a reference application for building immersive, avatar-powered customer experiences.

Try out Tokkio today on NGC.

---

NVIDIA Maxine

At GTC, NVIDIA announced the early-access release of Maxine audio effects microservices, as well as two new audio SDK features. NVIDIA also shared the general availability of Eye Contact, Facial Expression Estimation, and other enhanced versions of existing SDKs.

The following NVIDIA Maxine microservices are in early access:

• Audio Super Resolution: Improves real-time audio quality by upsampling the audio input stream from 8 kHz to 16 kHz and the sampling rate from 16 kHz to 48 kHz.
• Acoustic Echo Cancellation: Cancels real-time acoustic device echo from input-audio stream, eliminating mismatched acoustic pairs and double-talk. With AI-based technology, more effective cancellation is achieved than with traditional digital signal processing.
• Background Noise Removal: Enables noise removal on users’ microphones as well as the audio feed of counterparts to make conversations easier to understand.
• Room Echo Removal: Removes audio of the voice that is heard by a microphone.

Get started with NVIDIA Maxine today. 

Add this GTC session to your calendar:

• The Future of Work Requires a Next-Gen AI platform

---

MONAI 1.0 

Project MONAI, the medical open network for AI, is continuing to expand its capabilities to accelerate medical AI training no matter where developers are starting in their medical AI framework.

The release of MONAI 1.0 brings exciting new updates:

• Model Zoo to jumpstart AI training frameworks
• Active Learning in MONAI Label for building better datasets
• Auto-3D Segmentation
• Federated Learning

For more about MONAI 1.0, see Open-Source Healthcare AI Innovation Continues to Expand with MONAI 1.0 or try it on NVIDIA LaunchPad.

Add these GTC sessions to your calendar:

• AI-Assisted Annotation for Continuous Learning with MONAI Label
• Take Medical AI from Research to Clinical Production with MONAI and Clara Holoscan
• Design, Train, and Evaluate Domain-Specialized Healthcare Imaging AI Models with MONAI
• Creating Inference Applications for the Medical AI Project Lifecycle using MONAI Deploy

---

NVIDIA Clara Holoscan

Announced at GTC, NVIDIA Clara Holoscan SDK 0.3 now provides a lightning-fast frame rate of 240 Hz for 4K video that enables you to combine data from more sensors and build AI applications that can provide surgical guidance. With faster data transfer enabled through high-speed, Ethernet-connected sensors, you have even more tools to build accelerated AI pipelines for medical devices.

Highlights:

• End-to-end latency of only 10 ms on a 4K 240 Hz stream
• Streaming data at 4K 60 Hz at under 50 ms on NVIDIA RTX A6000, teams can run 15 concurrent video streams and 30 concurrent models.
• Faster data transfer and scalable connectivity for high-bandwidth network sensors.
• Developer tools to build accelerated AI pipelines for versatile medical device applications.

Seeking a hands-on lab? Try Clara Holoscan on LaunchPad.

Add this GTC session to your calendar:

• Take Medical AI from Research to Clinical Production with MONAI and Clara Holoscan

---

NVIDIA Metropolis

At GTC, NVIDIA announced that Siemens, the largest industrial automation company in the world, is adopting NVIDIA Metropolis and the IGX industrial edge AI platform. Metropolis on IGX will help Siemens connect entire fleets of robots and IoT devices to work together and proactively identify safety risks on factory floors and product defects on assembly lines with higher accuracy.

 Additional benefits:

• Metropolis enables Siemens to integrate next-level perception with new and existing industrial inspection systems.
• With Metropolis and IGX, Siemens can connect a simulated digital twin factory to the physical twin, a huge step toward self-driving factories of the future.

Add these GTC sessions to your calendar:

• Tracking Objects Across Multiple Cameras Made Easy with Metropolis Microservices
• All You Need to Know About Implementing Parallel Pipelines with DeepStream
• AI Models Made Simple using NVIDIA TAO

---

NVIDIA Isaac

Today, NVIDIA introduced NVIDIA Isaac Sim on the cloud, providing three options to access photo-real, physically accurate robotics simulation using the newly released Omniverse Cloud, AWS RoboMaker, or self-managed instances. NVIDIA also announced NVIDIA Isaac Nova Orin as a modular and scalable compute and sensor platform for OEMs and ISVs working on autonomous mobile robots (AMRs).

Here’s how NVIDIA Isaac Sim and NVIDIA Isaac Nova Orin are helping to advance the robotics industry:

• Simulate robots anywhere and on any device.
• Scale simulations to meet the most compute-intensive simulation tasks like CI/CD and synthetic data generation.
• Accelerate AMR development with an interoperable sensor and compute platform.

Be sure to attend the two-hour, hands-on NVIDIA Isaac Sim on AWS Robomaker workshop.

Add these GTC sessions to your calendar:

• A Perspective on the Future of Robotics and Its Use Cases in Logistics and Smart Transportation
• Leveraging Simulation Tools to Develop AI-Based Robots
• OV: How to Build a Digital Twin: Bringing in Robotics
• Re-imagining Robot Autonomy with Neural Environment Representations

---

NVIDIA DRIVE Thor

Today, NVIDIA introduced NVIDIA DRIVE Thor, its next-generation centralized computer to ensure safe and secure autonomous vehicles.

NVIDIA DRIVE Thor is a superchip that achieves 2,000 teraflops of performance and can unify intelligent functions into a single architecture for greater efficiency and lower overall system cost. Smart functions include automated and assisted driving, parking, driver and occupant monitoring, digital instrument cluster, in-vehicle infotainment (IVI), and rear-seat entertainment.

New features:

• Multi-domain computing support
• FP8 precision
• Inference transformer engine, improving DNN performance by 9x
• NVLink-C2C chip interconnect technology

For more information about NVIDIA DRIVE Thor capabilities, see NVIDIA DRIVE Thor Strikes AI Performance Balance, Uniting AV and Cockpit on a Single Computer.

Add these GTC sessions to your calendar:

• Developing Software-Defined Vehicles for the New Era of Transportation
• Elevating the Passenger Experience with Intelligent In-Vehicle Infotainment
• Turbocharging DNN Development and Testing for Autonomous Vehicles with DGX SuperPOD
• Accelerating AV Development and Validation with Synthetic Data Generation

---

NVIDIA BioNeMo

Just as AI is learning to understand human languages with transformer models, it’s also learning the languages of biology and chemistry. At GTC, NVIDIA introduced BioNeMo, a new framework and service for training large-scale transformer models using bigger datasets. This results in better-performing neural networks.

Larger models can store more predictive information on amino acid sequences and properties of different proteins. You can connect these insights to biological properties, functions, and even human health conditions.

Highlights:

• Pretrained large language models (LLMs) for chemistry and biology
• Optimized inference at supercomputing scale, enabling you to deploy LLMs with billions or trillions of parameters
• Turnkey cloud service for AI drug discovery pipelines

Try MegaMolBART, a generative chemistry model in the BioNeMo framework, with a guided lab on LaunchPad.

Add this GTC session to your calendar:

• AI-Powered Drug Discovery for Generative Chemistry and Proteins

---

NVIDIA AI Enterprise

NVIDIA AI Enterprise is a powerful cloud-native software suite that streamlines the entire AI framework and unlocks the full potential of the NVIDIA AI platform.

As the operating system of the NVIDIA AI platform, NVIDIA AI Enterprise provides production-ready support for applications built with the extensive NVIDIA library of frameworks.

Whether it’s creating more engaging chatbots and AI virtual assistants with Riva, building smarter recommendations to help consumers make better purchasing decisions with NVIDIA Merlin, or developing AI-powered medical imaging and genomics with NVIDIA Clara, and more, NVIDIA AI Enterprise supports NVIDIA domain-specific frameworks that developers can use to design new business solutions.

Add these GTC sessions to your calendar:

• Deep Dive into What’s New in the NVIDIA AI Enterprise Software Suite
• From Development to Scaling in Production: An IT Playbook for Modern Applications
• Expert Panel: Leveraging MLOps to Put AI in Production

At GTC 2022, NVIDIA revealed major updates to its suite of NVIDIA AI software for developers. The updates accelerate computing in several areas, such as machine…

At GTC 2022, NVIDIA revealed major updates to its suite of NVIDIA AI software for developers. The updates accelerate computing in several areas, such as machine learning research with NVIDIA JAX, AI imaging and computer vision with NVIDIA CV-CUDA, and data science workloads with RAPIDS.

To learn about the latest SDK advancements from NVIDIA, watch the keynote from CEO Jensen Huang.

---

JAX on NVIDIA AI

Just today at GTC 2022, NVIDIA introduced JAX on NVIDIA AI, the newest addition to its GPU-accelerated deep learning frameworks. JAX is a rapidly growing library for high-performance numerical computing and machine learning research.

Highlights:

• Efficient scaling across multi-node, multi-GPU
• Easy workflow to train large language models on GPU with GPU-optimized T5X and GPT scripts
• Built for all major cloud platforms

A ready-to-use JAX container will be available during Q4’2022 in early access. Apply now for early access to JAX and get notified when it is available.

Add this GTC session to your calendar:

• Seamlessly Scale Out Complex Compute Workloads with JAX

---

NVIDIA CV-CUDA

NVIDIA introduced CV-CUDA, a new open source project enabling developers to build highly efficient, GPU-accelerated pre– and post-processing pipelines in cloud-scale artificial intelligence (AI) imaging and computer vision (CV) workloads.

Highlights:

• Specialized set of 50+ highly performant CUDA kernels as standalone operators
• Batching support with variable shape images in one batch

For more CV-CUDA updates, see the CV-CUDA early access interest page.

---

NVIDIA Triton

NVIDIA announced key updates to NVIDIA Triton, open-source, inference-serving software bringing fast and scalable AI to every application in production. Over 50 features were added in the last 12 months.

Notable feature additions:

• Model orchestration using the NVIDIA Triton Management Service that automates deployment and management of multiple models on Triton Inference Server instances in Kubernetes. Apply for early access.
• Large language model inference with multi-GPU, multi-node execution with the FasterTransformer backend.
• Model pipelines (ensembles) with advanced logic using business logic scripting.
• Auto-generation of minimal required model configuration for fast deployment is on by default.

Kick-start your NVIDIA Triton journey with immediate, short-term access in NVIDIA LaunchPad without setting up your own environment.

You can also download NVIDIA Triton from the NGC catalog, access code and documentation on the /triton-inference-server GitHub repo, and get enterprise-grade support.

Add these GTC sessions to your calendar:

• Take Your AI Inference to the Next Level
• Simplifying Inference for Every Model with Triton and TensorRT
• Accelerating and Scaling Inference with NVIDIA GPUs
• Efficient Cloud-based Deployment of Deep Learning Models using Triton Inference Server and TensorRT

---

NVIDIA RAPIDS

At GTC 2022, NVIDIA announced that RAPIDS, the data science acceleration solution chosen by 25% of Fortune 100 companies, is now further breaking down adoption and usability barriers. It is making accelerated analytics accessible to nearly every organization, whether they’re using low-level C++ libraries, Windows (WSL), or cloud-based data analytics platforms. New capabilities will be available mid-October.

Highlights:

• Support for WSL and Arm SBSA now generally available
  • Supporting Windows brings the convenience and power of RAPIDS to nine million new Python developers who use Windows.
• Easily launch multi-node workflows on Kubernetes and Kubeflow
  • Estimating cluster resources in advance for interactive work is often prohibitively challenging. You can now conveniently launch Dask RAPIDS clusters from within your interactive Jupyter sessions and burst beyond the resources of your container for combined ETL and ML workloads.

For more information about the latest release, download and try NVIDIA RAPIDS.

Add these GTC sessions to your calendar:

• A Deep Dive into RAPIDS for Accelerated Data Science and Data Engineering
• Advances in Accelerated Data Science

---

NVIDIA RAPIDS Accelerator for Apache Spark

New capabilities of the NVIDIA RAPIDS accelerator for Apache Spark 3.x were announced at GTC 2022. The new capabilities bring an unprecedented level of transparency to help you speed up your Apache Spark DataFrame and SQL operations on NVIDIA GPUs, with no code changes and without leaving the Apache Spark environment. Version 22.10 will be available mid-October.

The new capabilities of this release further the mission of accelerating your existing Apache Spark workloads, no matter where you run them.

Highlights:

• The new workload acceleration tool analyzes Apache Spark workloads and recommends optimized GPU parameters for cost savings and performance.
• Integration with Google Cloud DataProc.
• Integration with Delta Lake and Apache Iceberg.

For more information about the latest release, download and try NVIDIA RAPIDS Accelerator for Apache Spark

Add these GTC sessions to your calendar:

• How AT&T Supercharged their Data Science Efforts
• Advances in Accelerated Data Science

---

PyTorch Geometric and DGL on NVIDIA AI

At GTC 2022, NVIDIA introduced GPU-optimized graph neural network (GNN) frameworks designed to help developers, researchers, and data scientists working on graph learning, including large heterogeneous graphs with billions of edges. With NVIDIA AI-accelerated GNN frameworks, you can achieve end-to-end performance optimization, making it the fastest solution to preprocess and build GNNs.

Highlights:

• Ready-to-use containers for GPU-optimized PyTorch Geometric and Deep Graph Library
• Up to 90% lower end-to-end execution time compared to CPUs for ETL, sampling, and training
• End-to-end reference examples for GraphSage, R-GCN, and SE3-Transformer

For more information about NVIDIA AI-accelerated PyTorch Geometric and DGL and its availability, see the GNN Frameworks page.

Add these GTC sessions to your calendar:

• Accelerating GNNs with PyTorch Geometric and GPUs
• Accelerating GNNs with Deep Graph Library and GPUs
• Accelerate and Scale GNNs with Deep Graph Library and GPUs
• Introduction to Graph Neural Networks

---

NVIDIA cuQuantum and NVIDIA QODA

At GTC 2022, NVIDIA announced the latest version of the NVIDIA cuQuantum SDK for accelerating quantum circuit simulation. cuQuantum enables the quantum computing ecosystem to solve problems at the scale of future quantum advantage, enabling the development of algorithms and the design and validation of quantum hardware. 

NVIDIA also announced ecosystem updates for NVIDIA QODA, an open, QPU-agnostic platform for hybrid quantum-classical computing. This hybrid, quantum/classical programming model is interoperable with today’s most important scientific computing applications. We are opening up the programming of quantum computers to a massive new class of domain scientists and researchers.

cuQuantum highlights:

• Multi-node, multi-GPU support in the DGX cuQuantum appliance
• Support for approximate tensor network methods
• Adoption of cuQuantum continues to gain momentum, including CSPs and industrial quantum groups

QODA private beta highlights:

• Single-source C++ and Python implementations as well as a compiler toolchain for hybrid systems and a standard library of quantum algorithmic primitives
• QPU-agnostic, partnering with quantum hardware companies across a broad range of qubit modalities
• Delivering up to a 300X speedup over a leading Pythonic framework also running on an A100 GPU

Add these GTC sessions to your calendar:

• An Introduction to cuQuantum
• Accelerating Quantum Computing Research with GPUs
• Scaling Quantum Circuit Simulations with cuQuantum for Quantum Algorithm
• Quantum Computing Simulation in Pharmaceuticals Research
• Defining the Quantum-Accelerated Supercomputer
• A Deep Dive into the Latest HPC Software

South Korea’s most popular AI voice assistant, GiGA Genie, converses with 8 million people each day. The AI-powered speaker from telecom company KT can control TVs, offer real-time traffic updates and complete a slew of other home-assistance tasks based on voice commands. It has mastered its conversational skills in the highly complex Korean language thanks Read article >

The post No Hang Ups With Hangul: KT Trains Smart Speakers, Customer Call Centers With NVIDIA AI appeared first on NVIDIA Blog.