NVIDIA Developer
NVIDIA Developer
  • Видео 859
  • Просмотров 20 920 222
JETSON AI LAB | Agent Studio - Multimodal VLM + Function-calling LLM
Quickly design and experiment with your own bots and multimodal agents in the interactive Agent Studio tool (www.jetson-ai-lab.com/agent_studio.html , running on Jetson Orin with locally-hosted models for deploying genAI to the edge. See the links to the open-source tutorials, models, and containers for running this in the description below.
Models: Efficient-Large-Model/VILA1.5-3b, NousResearch/Hermes-2-Pro-Llama-3-8B, clip-vit-large-patch14-336, rhasspy/piper
Stack: JetPack 6.0, PyTorch 2.2, NanoLLM, MLC, AWQ, torch2trt, jetson-containers
Tutorial: www.jetson-ai-lab.com/agent_studio.html
Containers: github.com/dusty-nv/jetson-containers
Просмотров: 1 572

Видео

JETSON AI LAB | Research Group Meeting (6/25/2024)
Просмотров 371День назад
www.jetson-ai-lab.com/research.html Topics Covered: * Agent Studio * Jetson Copilot (Chitoku Yato - www.jetson-ai-lab.com/tutorial_jetson-copilot.html) * Jetson Platform Services (Sammy Ochoa - docs.nvidia.com/jetson/jps/moj-overview.html) * On-device Fine-tuning (Nurgaliyev Shakhizat - www.hackster.io/shahizat/fine-tuning-llms-using-nvidia-jetson-agx-orin-b17c4d) * Open Q&A
Getting Started: NVIDIA cuOpt on AWS Marketplace
Просмотров 599День назад
Learn how to launch NVIDIA cuOpt from AWS Marketplace in three easy steps. The NVIDIA cuOpt offer on AWS includes a VMI, which provides a standard, optimized runtime for easy cuOpt access. This ensures development compatibility between clouds and on-premises infrastructure. Optimize and solve complex problems with routing, supply chain, and more. 00:00 - Part 1: Introduction 00:54 - Part 2: API...
Setting Up a RAG Demo on NVIDIA AI Workbench
Просмотров 1,9 тыс.14 дней назад
Walk through a complete start-to-finish installation of a generative AI retrieval-augmented generation (RAG) system with Lee Bushen, solutions architect at NVIDIA. You can use this system to create a RAG project on your own computer (no local GPU required) in about 1 hour. This approach uses NVIDIA AI Workbench to install the system. NVIDIA AI Workbench is an easy-to-use developer toolkit for d...
JETSON AI LAB | Research Group Meeting (6/11/2024)
Просмотров 81614 дней назад
www.jetson-ai-lab.com/research.html Topics Covered: * Agent Studio * Home Assistant 2024.6 * AWS IoT Greengrass (Romil Shah) * Open Q&A
Getting Started: NVIDIA cuOpt on Microsoft Azure Marketplace
Просмотров 95221 день назад
Learn how to launch NVIDIA cuOpt from Microsoft Azure Marketplace in three easy steps. The NVIDIA cuOpt offer on Microsoft Azure includes a VMI, which provides a standard, optimized runtime for easy cuOpt access. This ensures development compatibility between clouds and on-premises infrastructure. Optimize and solve complex problems with routing, supply chain, and more. 00:00 - Part 1: Introduc...
NVIDIA RTX Video SDK
Просмотров 2,3 тыс.21 день назад
Add AI-enhanced super resolution and HDR tone mapping to watch or create sharper, more vibrant 4K HDR video. Enhance edges, restore details, remove artifacts, and much more with NVIDIA RTX Video SDK. To learn more, visit our RTX Video SDK page: nvda.ws/3RbPkib, and read the Technical Blog: developer.nvidia.com/blog/enhancing-low-resolution-sdr-video-with-the-nvidia-rtx-video-sdk/ Join the NVIDI...
Overview of NVIDIA RTX AI Toolkit
Просмотров 3,6 тыс.21 день назад
Watch here for an end-to-end developer walkthrough of the NVIDIA RTX AI Toolkit, from model development to application deployment. This workflow showcases the model development workflow with AI Workbench and LlamaFactory-from customizing a Llama 3-7B model with the QLoRA technique to quantizing the model checkpoint with TensorRT Model Optimizer. The application deployment phase utilizes the NVI...
Generate Images Faster with Stable Diffusion and RTX
Просмотров 4 тыс.21 день назад
ComfyUI offers a streamlined interface for Stable Diffusion, accelerated on NVIDIA RTX GPUs with NVIDIA TensorRT. Fast image generation combined with one-step RTX-enhanced ControlNets unlocks unprecedented workflow control. ✨ #TensorRT and GeForce #RTX unlock ComfyUI SD superhero powers 🦸⚡ 📗 DIY notebook: nvda.ws/3Kv1G1d ✨ RTX GPUs not only speed up image generation but offer access to the newe...
JETSON AI LAB | Research Group Meeting (5/29/2024)
Просмотров 4,6 тыс.Месяц назад
Topics Covered: * OpenAI-style Tools with NousResearch/Hermes-2-Pro-Llama-3-8B * Jetson Copilot with jetrag (Chitoku Yato) * whisper_trt for Orin Nano * Open Q&A
Understanding AI Workflows: From Concept to Production
Просмотров 1,9 тыс.Месяц назад
In this segment from the NVIDIA AI Infrastructure and Operations Fundamentals course you will learn the phases of a typical AI workflow, used by AI practitioners to develop, train, and deploy an AI model, with the key tasks and typical tools used in each phase. Artifical Intelligence(AI), is a broad area of knowledge with important foundational concepts such as Machine Learning(ML), Deep Learni...
Getting Started with ChatRTX in Three Steps
Просмотров 649Месяц назад
Get started with Chat RTX today. This step-by-step tutorial walks you through downloading, installing, launching, and using ChatRTX. Create a personalized chatbot with the Chat with RTX tech demo. Accelerated by TensorRT-LLM and Tensor Cores, you can quickly get tailored info from your files and content. Try it now. Appendix A - Short Story: drive.google.com/file/d/1NZQ3D37nM1FN794Die6xjaKeJp5h...
Deploying Generative AI in Production with NVIDIA NIM
Просмотров 15 тыс.Месяц назад
Unlock the potential of generative AI with NVIDIA NIM. This video dives into how NVIDIA NIM microservices can transform your AI deployment into a production-ready powerhouse. Learn how NIM delivers flexible, scalable, and secure AI applications across any platform-cloud, data centers, or on-prem. Discover how its cloud-native architecture, backed by powerful tools like NVIDIA Triton Inference S...
JETSON AI LAB | Research Group Meeting (5/15/2024)
Просмотров 710Месяц назад
www.jetson-ai-lab.com/research.html Topics Covered: * JetPack 6.0 GA / L4T R36.3 * VILA-1.5 on Video Sequences * Voicecraft (Martin Cerven) * JetBot / Nanosaur Updates (Chitoku Yato / Raffaello Bonghi) * Controller LLM & Advanced Function Calling * RAG Samples with LlamaIndex (Chitoku Yato)
Python Profiling: NVIDIA Nsight Tools Feature Spotlight
Просмотров 2 тыс.Месяц назад
Profile Python for AI and deep learning applications with NVIDIA's suite of Nsight Developer Tools. This video explores Python profiling features that will help you optimize GPU-accelerated Python code and ensure your applications are fully saturating available resources. 00:00 - Introduction 0:31 - Nsight Tools JupyterLab Extension 1:22 - Nsight Systems Python Profiling 2:03 - Nsight Compute P...
JETSON AI LAB | Realtime Video Vision/Language Model with VILA1.5-3b and Jetson Orin
Просмотров 3,5 тыс.Месяц назад
JETSON AI LAB | Realtime Video Vision/Language Model with VILA1.5-3b and Jetson Orin
Geometric Fabrics: Generalizing Classical Mechanics to Capture the Physics of Behavior
Просмотров 1,5 тыс.Месяц назад
Geometric Fabrics: Generalizing Classical Mechanics to Capture the Physics of Behavior
JETSON AI LAB | Research Group Meeting (5/1/2024)
Просмотров 873Месяц назад
JETSON AI LAB | Research Group Meeting (5/1/2024)
JETSON AI LAB | Research Group Meeting (4/17/2024)
Просмотров 485Месяц назад
JETSON AI LAB | Research Group Meeting (4/17/2024)
JETSON AI LAB | Research Group Meeting (4/3/24)
Просмотров 1,1 тыс.Месяц назад
JETSON AI LAB | Research Group Meeting (4/3/24)
ChatRTX Update: New Models & Features (Voice & Image Data Support)
Просмотров 3,1 тыс.Месяц назад
ChatRTX Update: New Models & Features (Voice & Image Data Support)
JETSON AI LAB | Self-Learning Llama-3 Voice Agent with Function Calling and Automatic RAG
Просмотров 4,5 тыс.2 месяца назад
JETSON AI LAB | Self-Learning Llama-3 Voice Agent with Function Calling and Automatic RAG
Advancing HPC and AI Energy Efficiency with AWS and NVIDIA
Просмотров 1,1 тыс.2 месяца назад
Advancing HPC and AI Energy Efficiency with AWS and NVIDIA
Design and Test 5G and 6G Networks Using NVIDIA Aerial Omniverse Digital Twin
Просмотров 2,9 тыс.2 месяца назад
Design and Test 5G and 6G Networks Using NVIDIA Aerial Omniverse Digital Twin
Deploying AI in Real-World Robots | Aaron Saunders, Boston Dynamics CTO | NVIDIA GTC 2024
Просмотров 15 тыс.2 месяца назад
Deploying AI in Real-World Robots | Aaron Saunders, Boston Dynamics CTO | NVIDIA GTC 2024
The Future of AI and the Path to AGI - David Luan & Bryan Catanzaro | NVIDIA GTC 2024
Просмотров 11 тыс.2 месяца назад
The Future of AI and the Path to AGI - David Luan & Bryan Catanzaro | NVIDIA GTC 2024
Accelerating Simulations of Multiscale Chemical Reactors Using NVIDIA Modulus | NVIDIA GTC 2024
Просмотров 1,1 тыс.2 месяца назад
Accelerating Simulations of Multiscale Chemical Reactors Using NVIDIA Modulus | NVIDIA GTC 2024
Enabling Digital Twins for Science: A Perspective from CERN openlab | NVIDIA GTC 2024
Просмотров 1,9 тыс.2 месяца назад
Enabling Digital Twins for Science: A Perspective from CERN openlab | NVIDIA GTC 2024
Beyond the Output: Navigating the Ethical Challenges of Generative AI | NVIDIA GTC 2024
Просмотров 9082 месяца назад
Beyond the Output: Navigating the Ethical Challenges of Generative AI | NVIDIA GTC 2024
Generally Capable Agents in Open-Ended Worlds, Jim Fan, NVIDIA Lead of Embodied AI | NVIDIA GTC 2024
Просмотров 10 тыс.2 месяца назад
Generally Capable Agents in Open-Ended Worlds, Jim Fan, NVIDIA Lead of Embodied AI | NVIDIA GTC 2024

Комментарии

  • @sarpsomer
    @sarpsomer День назад

    Perfect

  • @neuralDEEPnet
    @neuralDEEPnet День назад

    ❤🎉🎉🎉 great progress

  • @rohanr3736
    @rohanr3736 День назад

    Super cool! Would love to try it out 🙂

  • @MOSSAI362
    @MOSSAI362 День назад

    Never mind just saw the zero shot model ha! Love it

  • @MOSSAI362
    @MOSSAI362 День назад

    Can bounding boxes or any segmentation be displayed on overlay for rtmp video feed for objects of interest?

  • @OZtwo
    @OZtwo День назад

    Been waiting so long and have to ask with all that has been going on in the last few years: WHEN WILL you be updating JetBot to version 2.0?

    • @dusty-nv
      @dusty-nv 17 часов назад

      We recently added update for it for Orin Nano and will be rolling out more of this stuff to it! There is also Nanosaur and Create3, we support those too and add local genAI to ROS2. It's a whole thing 🤣

  • @armisis
    @armisis День назад

    I've been wanting to work this into Fabric and link it to homeassistant so it can control my house based on its vision.

  • @armisis
    @armisis День назад

    I got two old Jetson Nano can I use these for this??

    • @MOSSAI362
      @MOSSAI362 День назад

      What you got Armis.

    • @harrivayrynen
      @harrivayrynen День назад

      There is a list of supported models at video description (link to the page)

    • @dusty-nv
      @dusty-nv День назад

      I believe I heard Ollama / llama.cpp can run on the OG Nano...I would try SLMs like ShearedLlama, StableLM, or Phi.

  • @MOSSAI362
    @MOSSAI362 День назад

    This is exactly what I’ve been researching absolutely amazing brilliant wow. Thank you Founder Moss Ai Analytics preparing Xavier now. Very interesting

    • @dusty-nv
      @dusty-nv День назад

      Awesome @MOSSAI362 - the most recent builds for this are on JetPack 6, but I should be able to backport it to JetPack 5 again.

    • @MOSSAI362
      @MOSSAI362 День назад

      Would be extremely grateful!

  • @user-ik4qt6jc5n
    @user-ik4qt6jc5n 2 дня назад

    세로운 영감을경혐해보고 시행함

  • @bryanKisner-xc6wx
    @bryanKisner-xc6wx 2 дня назад

    miscliked

  • @12pinpon
    @12pinpon 5 дней назад

    Nice video, excellent work! Thank's!!!

  • @Caligrapher1
    @Caligrapher1 6 дней назад

    the installation takes decades for gods sakes

  • @weagonfto
    @weagonfto 6 дней назад

    How do I install Nvidia broadcast on the Quadro P1000? If not, are there alternatives?

  • @KristalKlearGlasz
    @KristalKlearGlasz 6 дней назад

    Not interested bud

  • @e101sg
    @e101sg 6 дней назад

    yes. Great! useful. want try llamspeak Thanks for sharing !! :)

  • @pandamonium7996
    @pandamonium7996 7 дней назад

    I, for one, welcome our new hyperdexterous overlords. And now I'm going to go look how many other people left the exact same obvious comment😂

  • @microsoftflightsimulator476
    @microsoftflightsimulator476 8 дней назад

    I think this technology will limit for RTX5000

  • @DarkionAvey
    @DarkionAvey 8 дней назад

    is there a way to run rapids from VS windows but let it read the wsl data? i want a gui editor to interact with rapids and i dont want jnotebook

  • @mattwesney
    @mattwesney 9 дней назад

    So cooooool

  • @mrxx506
    @mrxx506 9 дней назад

    Where do you take the client software from?

  • @maksymkyiv1111
    @maksymkyiv1111 10 дней назад

    Ніколи такого не було. З цього переліку продукції багато чого потрібно. Врешті, спочатку потрібна відеокарта та устаткування для розробки.

  • @maksymkyiv1111
    @maksymkyiv1111 10 дней назад

    Ніколи не було такої.

  • @maksymkyiv1111
    @maksymkyiv1111 10 дней назад

    Це зрозуміло.

  • @maksymkyiv1111
    @maksymkyiv1111 10 дней назад

    this is what is needed. Without it, everything else is impossible

  • @maksymkyiv1111
    @maksymkyiv1111 10 дней назад

    Orin nano developer kit

  • @CGFUN829
    @CGFUN829 10 дней назад

    man, cant believe this was 4 years ago. Now its implemented in rtx remix.

  • @shakiruluwar9818
    @shakiruluwar9818 10 дней назад

    🎉

  • @Mrchingchingdingding
    @Mrchingchingdingding 11 дней назад

    I'd love to hear some quality of life adjustments in traditional workflows of logistics specialists or proposed by panels of cross-sectional employees (i e. at different levels of the org/havin different specialties/etc.) so that people can start leveraging your tech in the public sector to engineer those projects.

  • @ericyoung3183
    @ericyoung3183 11 дней назад

    What are the benefits of unlocking the power of edge AI with MediaTek and NVIDIA TAO integration, revolutionizing industries with real-time insights?

  • @benjaminlee3669
    @benjaminlee3669 11 дней назад

    Is this the same NVIDIA TAO that is being used together with the Mediatek's NeuroPilot?

  • @lucasbrown7338
    @lucasbrown7338 12 дней назад

    I was hearing about the NVIDIA Tool Kit, seems very potential in terms of the Edge AI as there is a great integration of this tool with the MediaTek Neuropilot SDK system. Pretty impressive one!!

  • @lucasbrown7338
    @lucasbrown7338 12 дней назад

    Hearing about the TAO toolkit , that has been integrated in the MediaTek Neuropilot system, seems very interesting with the edge AI functioning.

  • @lucasbrown7338
    @lucasbrown7338 12 дней назад

    MediaTek and NVIDIA? Now that's a powerful team for AI development! The integration of this TAO toolkit with the MediaTek is very potential for the developers.

  • @lucasbrown7338
    @lucasbrown7338 12 дней назад

    Along with the NVIDIA TAO toolkit and the associated MediaTek SDK system, there is a better benefit for the edge AI process for the developers and is a great development.

  • @lucasbrown7338
    @lucasbrown7338 12 дней назад

    Hearing about the integration of TAO toolkit from NVIDIA with the MediaTek SDK, This is awesome news! Sounds like building edge AI apps just got way easier.

  • @lucasbrown7338
    @lucasbrown7338 12 дней назад

    I think the NVIDIA Tao tool kit integrates a great level of performance in terms of the development for the SDK in the case of MediaTek , thus benefitting the developer users.

  • @Mixam-256
    @Mixam-256 12 дней назад

    NVIDIA, please simplify this information!

  • @Mixam-256
    @Mixam-256 12 дней назад

    Who is the target audience for these, they're so difficult to understand.

  • @donjuan752
    @donjuan752 12 дней назад

    Ѧвѧн умнѳѫлѧсь шѧтрѧх свѳй ѳкрестнѳсть се дождьамонь сь нѫнее сѧлмскй се дождь щ от того как ѳвнѧ шѧтрѧ ѯѧтвѳрл нѧшх шѧтрѧ ѯѧтвѳрл нѧшх стрчь стѳрѳну ныне всякому росла нашлось мы вы его внуши разумею дѳля ѧмрѧфелѧ рѧѯѳйдутся соответственного убьет блгмдрсвенный сь нѫнее сѧлмскй се да не щт😅 нее нѳемѧѫенѧм скѧѫут се шрѳту скнеплѳднѧ смѳлѳю суше сѳеднлсь жвая увел вы Ꙍ дождь щ не не

  • @yunchaoyang8464
    @yunchaoyang8464 12 дней назад

    The open chat cannot launch the webui. the output for chat saying that: stat: cannot statx '/var/host-run/docker.sock': No such file or directory groupadd: invalid group ID 'docker' usermod: group 'docker' does not exist Any idea how to fix this?

    • @NVIDIADeveloper
      @NVIDIADeveloper 11 дней назад

      Hi! Let me speak to somebody and get back to you to see if it's a known issue.

    • @tylerwhitehouseus6310
      @tylerwhitehouseus6310 6 дней назад

      The Hybrid RAG Project requires Docker as the runtime. It won't work with podman. Which runtime did you select when you installed?

  • @user-xz7hx2ss2f
    @user-xz7hx2ss2f 13 дней назад

    Thanks a lot. It was very helpful!

  • @master7738
    @master7738 13 дней назад

    In 20 years there will be a so muuch better world thanks to Nvidia.

  • @JMai-ci9nl
    @JMai-ci9nl 14 дней назад

    This is so far the most complicated RAG system setup I have ever seen. Good luck to anyone who is going to actually set it up and use it.

    • @raiskazi9760
      @raiskazi9760 14 дней назад

      Its one time setup. I found this video tutorial easy to follow and it worked for me without any hassles.

  • @xl000
    @xl000 14 дней назад

    The real demo here is just one level meta up. There are no humans in this video, and there is no software. It's just the result of prompt for a video animation.....