#  @nvidiadeveloper NVIDIA Developer NVIDIA has been releasing various tools and platforms to support AI development, including the NVIDIA NIM for deploying generative AI, NVIDIA Nemo Agent for creating AI agents, and DGX Cloud for AI computing. The company has also been highlighting its Jetson series, including the AGX Orin and Nano developer kits, for building AI-powered robots and devices. Additionally, NVIDIA has been showcasing its advancements in areas like humanoid robotics, quantum computing, and accelerated data science. ### Engagements: [------] [#](/creator/youtube::UCBHcMCGaiJhv-ESTcWGJPcw/interactions)  - [--] Week [-------] -21% - [--] Month [---------] +9.60% - [--] Months [---------] -17% - [--] Year [----------] +27% ### Mentions: [--] [#](/creator/youtube::UCBHcMCGaiJhv-ESTcWGJPcw/posts_active)  - [--] Week [---] +30% - [--] Month [---] -1.20% - [--] Months [---] +22% - [--] Year [---] +231% ### Followers: [-------] [#](/creator/youtube::UCBHcMCGaiJhv-ESTcWGJPcw/followers)  - [--] Week [-------] +0.50% - [--] Month [-------] +1.50% - [--] Months [-------] +11% - [--] Year [-------] +26% ### CreatorRank: [-------] [#](/creator/youtube::UCBHcMCGaiJhv-ESTcWGJPcw/influencer_rank)  ### Social Influence **Social category influence** [stocks](/list/stocks) #2907 [technology brands](/list/technology-brands) 100% [finance](/list/finance) 2.06% [events](/list/events) 1.55% [social networks](/list/social-networks) 1.55% [travel destinations](/list/travel-destinations) 1.55% [countries](/list/countries) 1.03% [nfts](/list/nfts) 0.52% **Social topic influence** [ai](/topic/ai) #2925, [$nvda](/topic/$nvda) #56, [how to](/topic/how-to) 21.65%, [systems](/topic/systems) #1686, [agentic](/topic/agentic) #18, [llm](/topic/llm) #688, [inference](/topic/inference) #91, [gpu](/topic/gpu) #365, [nvda](/topic/nvda) #555, [build a](/topic/build-a) #1563 **Top accounts mentioned or mentioned by** [@esimstudios](/creator/undefined) [@kevinstratvert](/creator/undefined) [@huggingface](/creator/undefined) [@nvidiaomniverse](/creator/undefined) [@engineerprompt](/creator/undefined) [@marktechpost](/creator/undefined) [@kennygunderman](/creator/undefined) [@ltx_model](/creator/undefined) [@technology_now](/creator/undefined) **Top assets mentioned** [NVIDIA Corp. (NVDA)](/topic/$nvda) [Alphabet Inc Class A (GOOGL)](/topic/$googl) [Microsoft Corp. (MSFT)](/topic/microsoft) [IonQ, Inc. (IONQ)](/topic/$ionq) [FilesCoins Power Cu (FILECOIN)](/topic/files) ### Top Social Posts Top posts by engagements in the last [--] hours "DGX Spark Live: Installation & First Run Guide for Robotics Developers This is the essential live session for robotics developers ready to leverage NVIDIA Isaac Sim on the powerful DGX Spark platform. We'll guide you through the initial steps to get your high-fidelity simulation environment up and running on the aarch64 architecture. What You'll Learn & Do: Installation Walkthrough: Follow along with the official documentation process including the specific details for the DGX Spark where the ARM build is generated by default. Launch & Verification: We'll show you how to properly launch the" [YouTube Link](https://youtube.com/watch?v=34PJYWPcqK4) 2025-12-09T01:03Z 201K followers, [----] engagements "NVIDIA DGX Spark Lights up CES [----] Show Floor One year after the debut of Project Digits DGX Spark has transformed from concept to reality and is now available from NVIDIA and OEM partners. See it in action at #CES2026 where enterprise creative and agentic AI meet the edge of innovation. #SparkSomethingBig https://www.nvidia.com/en-us/events/ces/" [YouTube Link](https://youtube.com/watch?v=7Rl71SPi4lw) 2026-01-15T00:00Z 201K followers, 796.5K engagements "What's the culture like at #nvidia #ai #softwaredevelopment #coding" [YouTube Link](https://youtube.com/watch?v=8DRIzZKLlUU) 2025-08-27T21:00Z 201K followers, 33.8K engagements "Introduction to Physical AI & Robotics at NVIDIA This session will provide a high-level overview of NVIDIA's comprehensive approach to robotics emphasizing how our open models frameworks libraries and hardware are empowering developers to build intelligent and autonomous systems. Attendees will learn about the fundamental components of NVIDIA's robotics ecosystem" [YouTube Link](https://youtube.com/watch?v=p8yhD0JnScM) 2025-12-20T17:01Z 201K followers, [----] engagements "🎁 For the Innovator Who Has Everything (Except This) . an NVIDIA DGX Spark 🎁 Compact capable and efficient -- NVIDIA DGX Spark is the perfect companion for anyone ready to build prototype or refine their AI ideas. Give the gift that doesnt just keep on giving -- it keeps innovating. ✨ Shop now to #SparkSomethingBig: https://marketplace.nvidia.com/en-us/enterprise/personal-ai-supercomputers/dgx-spark/" [YouTube Link](https://youtube.com/watch?v=7hFdmt8driQ) 2025-12-09T23:44Z 201K followers, 29.7K engagements "Accelerating Applications with Parallel Algorithms CUDA C++ Class Part [--] Welcome to NVIDIAs Modern CUDA C++ Programming Class. You will learn how to program on the GPU using NVIDIAs latest programming tools. This series is for C++ developers who want to use the GPU effectivelywhether youre new to CUDA and want the fastest path from hello world to real acceleration or youre an experienced CUDA programmer ready to modernize your code with the latest best practices. If you already know C++ and want to write clean efficient idiomatic GPU code this course is for you. This video is part of a" [YouTube Link](https://youtube.com/watch?v=Sdjn9FOkhnA) 2025-11-06T22:08Z 201K followers, 34.5K engagements "AI Warehouse: AMR Visual Navigation with Isaac Sim & Isaac ROS Autonomous machines are forecasted to dramatically increase the efficiency of warehouses factories and other industrial environments. NVIDIA Isaac ROS GEMs enable novel applications by empowering robots to intelligently perceive complex 3D environments. In this video we showcase a camera-based navigation pipeline in which a robot uses NVIDIAs GPU-accelerated visual SLAM algorithm (https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_visual_odometry) to find its location in the world. GPU-accelerated real-time 3D scene reconstruction" [YouTube Link](https://youtube.com/watch?v=afNVwoX_zd0) 2022-03-22T16:59Z 201K followers, 26.8K engagements "Turn Text Into a Knowledge Graph with 70B LLM on DGX Spark Looking to run local GraphRAG or other graph analytics use cases With DGX Spark you can prepare your local text files for graph use cases at your desk. In this demo a Llama-3.1-70B model served by Ollama runs locally in DGX Sparks 128GB of unified memory. After uploading local biomedical research papers into the LLM the model extracts nodes and relationships that are embedded into a knowledge graph. By processing entire documents at once the knowledge graph retains critical long-range relationships that make GraphRAG and other graph" [YouTube Link](https://youtube.com/watch?v=8iA_f_UpzHc) 2025-10-27T15:30Z 201K followers, 37.9K engagements "Getting Started with CUDA and Parallel Programming NVIDIA GTC [----] Session Join one of CUDA's architects on a journey through the concepts of parallel programming: how it works why it works why it's not working when you think it should be working and in particular why it's different on a GPU from a CPU. We'll look at different approaches to parallel programming in CUDA and how to take advantage of the hardware it runs on. This is the next episode in what has become a series looking at the way that CUDA and the GPU work and why they work this way. This session will focus on how to think about" [YouTube Link](https://youtube.com/watch?v=GmNkYayuaA4) 2025-04-10T21:28Z 201K followers, 33.6K engagements "Interviewing a Robot at #GTC25 #nvidia #robotics #machinelearning" [YouTube Link](https://youtube.com/watch?v=JlQ7QGrjzu0) 2025-03-18T04:16Z 201K followers, 165.3K engagements "ArtisanGS: Interactive Tools for Gaussian Splat Selection with AI and Human in the Loop ArtisanGS is an interactive toolkit for 3D Gaussian Splat scenes that turns a few 2D masks into editable 3D object selections using Cutie-based multiview tracking and fast splat aggregation with rich tools for manual correction. It delivers competitive segmentation quality in about [--] seconds without perscene training and enables downstream workflows like local videodiffusion editing autoorientation and direct physics simulation on splat objects. Authors: Clement Fuji Tsang Anita Hu Or Perel Carsten Kolve" [YouTube Link](https://youtube.com/watch?v=gFOLelcdCoE) 2026-02-13T20:00Z 201K followers, [----] engagements "Getting Started with the NVIDIA Jetson AGX Thor Developer Kit for Physical AI The NVIDIA Jetson AGX Thor Developer Kit is the ultimate developer resource for building the future of humanoid robotics and next-generation physical AI applications. Powered by the advanced NVIDIA Blackwell GPU and [---] GB of memory it delivers up to [----] FP4 TFLOPS of AI performanceall within a [---] W power envelope. This video walks you through how to power on and set up the device for the first time (first boot tutorial). It also covers key features specifications and components and the latest NVIDIA workflows" [YouTube Link](https://youtube.com/watch?v=iYT2haVIgSM) 2025-08-25T15:01Z 201K followers, 65.8K engagements "DGX Spark Live: Developer Q&A Got questions about DGX Spark You're not alone With any new product launch there are always a lot of details to uncover. In this special livestream we're diving deep to answer your most pressing questions about the new DGX Spark system. We'll answer your questions to give you a complete understanding of: - Why was DGX Spark created - Who was it created for - What are ideal use cases for DGX Spark Most importantly we'll help you figure out the big question: Should you have a DGX Spark on your desk Tune in ask your questions live and get the clarity you need. Learn" [YouTube Link](https://youtube.com/watch?v=ry09P4P88r4) 2025-10-24T18:39Z 201K followers, 378.3K engagements "DGX Spark: Observing the Universe at Light Speed Tired of the perpetual 'dark sky vs. glowing screen' battle while doing visual astronomy That bright phone or tablet running SkySafari ruins your night vision and focus. We're showing off a custom AI agent running on DGX Spark that lets you have a natural voice-activated conversation with your telescope no more fumbling with apps in the dark. Join us for a deep dive and live demonstration of the full stack that allows an open-source GPT model (GPT-OSS:20b) to control a high-end mount (10micron GM2000) for astronomical objects and satellites." [YouTube Link](https://youtube.com/watch?v=uFR36XUgfCs) 2025-11-01T06:30Z 201K followers, 510.3K engagements "Intro to NVIDIA Cosmos with Ming-Yu ft. Superintelligence Cosmos Labs Join us for an exclusive deep dive into NVIDIA Cosmos with its creator Ming-Yu Vice President of Research at NVIDIA alongside your favorite technology advocate Superintelligence. In this conversation we unpack the motivation behind Cosmos the science and research powering its open models and the long-term vision shaping its evolution. Learn how Cosmos is redefining physical AI where these models are headed next and how developers and researchers can start using Cosmos today. What youll learn in this session: - Why NVIDIA" [YouTube Link](https://youtube.com/watch?v=x2Q7kkGsDOk) 2026-01-28T14:05Z 201K followers, 107K engagements "Intro to NVIDIA Cosmos with Ming-Yu ft. Superintelligence Watch an exclusive deep dive into NVIDIA Cosmos with its creator Ming-Yu Vice President of Research at NVIDIA alongside your favorite technology advocate Superintelligence. Watch the livestream 👉 https://www.youtube.com/watchv=x2Q7kkGsDOk Explore the Cosmos Cookbook 👉 https://nvda.ws/4k7EmaN Register for the hackathon 👉 https://nvda.ws/4qP4sly #NVIDIACosmos #WorldFoundationModels #CosmosCookbook #PhysicalAI" [YouTube Link](https://youtube.com/watch?v=0QEW2NfCKqY) 2026-02-12T20:10Z 201K followers, [----] engagements "DGX Spark Live: Sovereign Data Solutions With GT Edge AI Join the NVIDIA AI Developer livestream featuring an early access partner GT Edge AI for a hands-on look at why they are building hybrid edge intelligence on the DGX SPARK platform building for users that need to work with sovereign data in a secure environment. Learn why GT Edge AI is building its OS on SPARK covering agent frameworks hybrid deployment patterns and how to extend AI pipelines to the edge with both cloud hosted and local models for inference while keeping data local. GT Edge AI are building their product with the Dell" [YouTube Link](https://youtube.com/watch?v=l-wQib4k-3A) 2026-01-21T07:46Z 201K followers, [----] engagements "How to Self-Host LLMs and Multi-Modal AI Models with NVIDIA NIM in [--] Minutes -NVIDIA NIM is containerized AI inference software that makes it simple to deploy production-ready model endpoints accelerated by NVIDIA GPUs anywhere you need them. Tap into the latest AI foundation modelslike NVIDIA Nemotron Qwen DeepSeek R1 Meta Llama and more ready for secure private deployment in [--] minutes or less on NVIDIA-accelerated workstations datacenter or cloud environments. Join Neal Vaidya developer advocate at NVIDIA for a demo on how to privately deploy LLMs and multi-modal AI models with NVIDIA NIM" [YouTube Link](https://youtube.com/watch?v=087spL8hMvM) 2024-07-29T20:30Z 201K followers, 45.5K engagements "Intelligent Query Routing using vLLM Semantic Router #nvidia #machinelearning #vllm #ai" [YouTube Link](https://youtube.com/watch?v=6SL27J7EyXM) 2026-01-12T23:27Z 201K followers, [----] engagements "Build Reasoning Agents For Physical AI Cosmos Labs Learn how to apply Cosmos Cookbook recipes for physical AI reasoning using Cosmos Reason in this hands-on technical deep dive. In this session we explore how egocentric or first-person reasoning allows robots to understand social cues and physical laws leading to safer and more natural humanrobot interactions. We also show how fine-tuning Cosmos Reason with domain-specific data such as heavy traffic improves understanding in complex dynamic environments. Similar methods can be used to filter synthetic data and build visuallanguage agents for" [YouTube Link](https://youtube.com/watch?v=7O70xBA95hQ) 2026-01-28T05:48Z 201K followers, [----] engagements "How To Adapt AI for Low-Resource Languages with NVIDIA Nemotron Join NVIDIA and Dicta to explore how Sovereign AI initiatives can empower local innovation through advanced language model adaptation. This session highlights how Dicta built a Hebrew reasoning model using the Nemotron architecture and NVIDIAs NeMo frameworkshowing how open models transparent data and efficient training tools can accelerate AI development for lowresource languages. Well cover the main practices for customizing foundation models managing data quality and safety and deploying domainspecific reasoning systems. The" [YouTube Link](https://youtube.com/watch?v=8U6mqSgCs_s) 2026-01-31T21:32Z 201K followers, [----] engagements "DGX Spark Live: Powering Higher Education and Research Join NVIDIA and Stanford researchers for an exciting look at Biomni a next-generation biomedical AI agent transforming how labs explore data and design experiments. Discover how Biomni running on NVIDIA DGX Spark turns complex biomedical workloads into fast automated insights giving teams a powerful launchpad for rapid experimentation evaluation and seamless scaling" [YouTube Link](https://youtube.com/watch?v=8v_dfwpAzdY) 2026-02-11T07:39Z 201K followers, [----] engagements "Agentic AI Solutions with CrewAI and Nemotron Nemotron Labs Join this exclusive livestream for a practical deep dive with CrewAI CEO Joaoa Moura exploring real-world agentic streaming and the latest breakthroughs using Nemotron open models in production frameworks for top brands. What developers will learn: How CrewAI integrates Nemotron for rapid modular agent workflows powering everything from simple task automation to complex multi-agent orchestration. Field-tested tips and best practices on building scalable agents with insights pulled directly from CrewAIs deployments in enterprise" [YouTube Link](https://youtube.com/watch?v=9X5QtRUW0LA) 2026-01-05T20:58Z 201K followers, [----] engagements "Quantum Computing: Where We Are and Where Were Headed NVIDIA GTC [----] Fireside Chat NVIDIA founder and CEO Jensen Huang hosts industry leaders from Alice & Bob Atom Computing AWS D-Wave Infleqtion IonQ Microsoft Pasqal PsiQuantum Quantinuum Quantum Circuits QuEra Computing Rigetti and SEEQC to learn today's state of the art and what the future holds for useful quantum computing. These unprecedented fireside chats bring together the whole quantum computing community for an overview of this exciting technology. Panelists: Ben Bloom Founder and CEO Atom Computing Alan Baratz CEO D-Wave Krysta" [YouTube Link](https://youtube.com/watch?v=9XB-LsfpvCU) 2025-04-09T16:15Z 201K followers, 232.8K engagements "Getting Started with the NVIDIA DGX Spark NVIDIA DGX Spark powered by the NVIDIA GB10 Grace Blackwell Superchip delivers one petaFLOP of AI performance in a power-efficient compact form factor. With the NVIDIA AI software stack preinstalled and [---] GB of memory developers can prototype fine-tune and inference the latest generation of reasoning AI models from DeepSeek Meta NVIDIA Google Qwen and others with up to [---] billion parameters locally. This video walks you through how to power on and set up the device for the first time (first boot tutorial). Learn more: build.nvidia.com/spark" [YouTube Link](https://youtube.com/watch?v=AamP-LbGHXQ) 2025-10-14T23:23Z 201K followers, 71.8K engagements "The Breakthrough Moment for Physical AI Powered by NVIDIA Cosmos Learn how to get more out of NVIDIA Cosmos with tips straight from the authors behind our Cosmos Cookbook recipes. Watch the livestream 👉 https://www.addevent.com/calendar/ss55fmjpm04t Explore the Cosmos Cookbook 👉 https://nvda.ws/4k7EmaN Register for the hackathon 👉 https://nvda.ws/4qP4sly #NVIDIACosmos #WorldFoundationModels #CosmosCookbook #PhysicalAI" [YouTube Link](https://youtube.com/watch?v=EKE8c6RhwQo) 2026-02-09T19:01Z 201K followers, [----] engagements "How to Write a CUDA Program - Parallel Programming #gtc25 #CUDA Click to watch the full session from GTC25: "How to Write a CUDA Program - The Parallel Programming Edition" https://youtu.be/GmNkYayuaA4 Join one of CUDA's architects on a journey through the concepts of parallel programming: how it works why it works why it's not working when you think it should be working and in particular why it's different on a GPU from a CPU. We'll look at different approaches to parallel programming in CUDA and how to take advantage of the hardware it runs on. This is the next episode in what has become a" [YouTube Link](https://youtube.com/watch?v=KPeTgySUmW8) 2025-04-22T21:48Z 201K followers, 21.3K engagements "Vibe Coding Demo on DGX Spark See how we build an AI app on DGX Spark that finds uplifting news and the best pet videosbecause innovation should inspire and make you smile. Using Continue.dev we demo vibe coding with agentic workflows that spark creativity and accelerate your AI journey. Learn more: build.nvidia.com/spark" [YouTube Link](https://youtube.com/watch?v=MLu7TdwJDkw) 2025-10-07T21:16Z 201K followers, 12.6K engagements "Performance Analysis with NVIDIA Nsight Systems Timeline CUDA Developer Tools In this episode of the CUDA Developer Tools tutorial series Eyal Soha senior software engineer at NVIDIA introduces code performance analysis using the Timeline View in NVIDIA Nsight Systems. Basic knowledge of C++ CUDA programming is recommended. Highlights include: Explore the Nsight Systems timeline a powerful tool for analyzing GPU performance. Learn how the Timeline View helps you understand code processes and uncover optimization opportunities. Get an overview of the timeline interface and how to navigate the" [YouTube Link](https://youtube.com/watch?v=TGChXcFm-Yo) 2023-10-27T16:00Z 201K followers, 17K engagements "Build End-to-End Multimodal AI Agents for Document and Video Intelligence With NVIDIA Nemotron This video presents a unified approach to multimodal and document intelligence using NVIDIA Nemotron models. Implement agent-ready workflows by combining two specialized Nemotron models: [--] Nemotron Nano [--] VL for Reasoning: This 12B model provides multimodal intelligence agents need to to perform sophisticated cross-page reasoning on charts and tables grounding answers directly in the data. It also leverages a new Efficient Video Sampling (EVS) capability that generates 4x less tokens while" [YouTube Link](https://youtube.com/watch?v=bQ7prf_RDMw) 2025-10-28T17:59Z 201K followers, [----] engagements "What is CUDA Tile Join Stephen Jones CUDA Architect for a clear and insightful introduction to a paradigm-shifting technology: CUDA Tile. If you're wondering how modern GPU programming is evolving this video provides the essential foundation. We break down the core concepts of CUDA Tile explain why it's a necessary development for peak performance and discuss how it fundamentally changes the way we think about parallel computation. Speaker & Resources: 👤 Speaker: Stephen Jones CUDA Architect 📖 Official CUDA Tile Documentation: http://docs.nvidia.com/cuda/tile-ir 💡 Explore CUDA Tile:" [YouTube Link](https://youtube.com/watch?v=cHryyRX5Q2U) 2025-12-19T19:09Z 201K followers, [----] engagements "Chat with the Nemotron Team Office Hours Nemotron Labs Got questions about Nemotron Want to give direct feedback to the team behind the models Ask our Nemotron expert in this Nemotron Lab office hours about: - Our Nemotron open model family with open datasets and open techniques - How to build AI agents including report generator agent RAG agent bash computer use agent and training with synthetic data & reinforcement learning from our recent tutorial livestreams This is your chance to get hands-on support ask questions and explore the Nemotron models with the experts who built them. Whether" [YouTube Link](https://youtube.com/watch?v=d4OR-6t-FHs) 2026-01-21T22:20Z 201K followers, [---] engagements "Step-by-Step Installation of NVIDIA Virtual GPU Software on VMware vSphere Learn the entire process for getting NVIDIA Virtual GPU software running on VMware vSphere--whether youre using vSphere for Graphics/VDI workloads or AI workloads with NVIDIA AI Enterprise. NVIDIA Senior Solutions Architect Lee Bushen walks you through the following steps: - Downloading the vGPU or NVIDIA AI Enterprise software components - Server preparation for vGPU - Installing the GPU Manager on the ESXi host - Removing the GPU Manager for an vGPU software upgrade - Configuring vCenter for vGPU profiles -" [YouTube Link](https://youtube.com/watch?v=gJy2dS20so8) 2024-10-11T18:21Z 201K followers, 34.6K engagements "DGX Spark: Accelerated cuPyNumeric on your Desktop Cluster NVIDIA cuPyNumeric a multi-node multi-GPU NumPy-compatible library is ideal for domain scientists and researchers to scale their Python and NumPy program to multi-GPU multinode without having to write complex parallel computing code like MPI. Well demonstrate how to use [--] DGX Spark systems as a desktop cluster to accelerate cuPyNumeric locally. Get started with DGX Spark: https://nvda.ws/4o2rDHn" [YouTube Link](https://youtube.com/watch?v=ghysPxEUZwU) 2025-11-06T16:22Z 201K followers, [----] engagements "Under the Hood of Open Models: Building Scalable MultiAgent Architectures Nemotron Labs Join for a live walkthrough of open models datasets and tools that help developers design deploy and iterate on multiagent AI systems at scale. Learn how to use open resourcestraining recipes open datasets and reinforcement learning environmentsinto your existing stacks to speed up prototyping evaluation and production workflows. During the livestream NVIDIA experts will cover: - How to adapt open models and data for specialized agent workflows - New tools and libraries that streamline reinforcement" [YouTube Link](https://youtube.com/watch?v=3AdpDdKnH-Q) 2025-12-12T04:35Z 201K followers, [----] engagements "New Nemotron Open-Source Models and Datasets #NVIDIAGTC Develop specialized AI agents with new NVIDIA Nemotron vision RAG and guardrail models announced at GTC DC. Check out the tech blog for resources on getting started. #Nemotron #SpecializedAI #GTC" [YouTube Link](https://youtube.com/watch?v=3m_48SI18pU) 2025-10-28T18:06Z 201K followers, [----] engagements "NVIDIA Llama-3.1-Nemotron Ultra: The Best Open Model Built for Reasoning & AI Agents Discover NVIDIA's Llama-3.1-Nemotron Ultra the 253B parameter open-weight model designed specifically for advanced reasoning and enterprise AI agents. Skip the chatbots and build AI that can solve complex problems with step-by-step reasoning" [YouTube Link](https://youtube.com/watch?v=H9iNAbkQiUc) 2025-05-07T15:12Z 201K followers, [----] engagements "How to Deploy NVIDIA Nemotron Nano 4B with vLLM on Colab Reasoning & Tool Calling Demo Learn how to deploy the NVIDIA Llama Nemotron Nano 4B reasoning model on Google Colab using vLLM and an NVIDIA L40 GPU. This step-by-step demo covers system and user prompts for reasoning (on/off modes) tool calling and real-world use cases like coding scientific tasks and instruction followingideal for edge AI agents. Key features include: Leading reasoning and agentic AI accuracy for various benchmarks including GPQA-Diamond AIME [----] IFEval BFCL LiveCodeBench and MBPP 50% higher throughput compared to" [YouTube Link](https://youtube.com/watch?v=HTPiUZ3kJto) 2025-05-22T00:30Z 201K followers, [----] engagements "How to Use Nemotron [--] Nano: Connecting OpenAI API Endpoint and Build LangChain Agents Learn how to use NVIDIA Nemotron [--] Nano the advanced mixture-of-experts (MoE) model built on a hybrid Mamba-Transformer architecture. In this step-by-step tutorial we show you how to deploy and interact with Nemotron [--] Nano using OpenRouters API then build powerful LangChain agentsfrom single interactions to full multi-agent research systems. What Youll Learn: ✅ How to connect Nemotron [--] Nano through an OpenAI-compatible API ✅ The difference between thinking mode on/off and when to use them ✅ Building your" [YouTube Link](https://youtube.com/watch?v=HjhxQtZIK3s) 2025-12-15T14:00Z 201K followers, [----] engagements "Build a Custom AI Agent With NVIDIA Nemotron RAG Models This hands-on tutorial guides you through creating an Agentic Retrieval-Augmented Generation (RAG) pipeline using NVIDIA's open Nemotron models for embedding and reranking. 🔍 What You'll Learn in this RAG Tutorial: [--] NVIDIA Nemotron RAG Models: Access and use open Nemotron RAG models from Hugging Face for retrieval. [--] Custom RAG Pipeline: Build a full workflow in LangChain with data loading chunking and a Contextual Compression Retriever. [--] Agent Development: Use Nemotron Nano [--] 9B as your LLM and connect retrieval tools into an agent" [YouTube Link](https://youtube.com/watch?v=LOhIdijVno0) 2025-10-28T17:59Z 201K followers, [----] engagements "Building AI Agents at the Edge with NVIDIA Llama Nemotron Nano 4B Want to build an AI agent running on-premises This video walks you through how to code (and vibe code) a local agent running NVIDIA Llama Nemotron Nano 4B wrapped in a custom React UI built with Cursor AI and FAISS Vector Database. 00:00 Introduction 00:26 Llama Nemotron Nano 4B 06:13 UI Demo 11:23 Code 19:27 Outro #LLM #SLM #LlamaNemotron #AIagent #cursorAI #faiss Demo source code: https://github.com/NVIDIA/GenerativeAIExamples/tree/main/community/chat-llama-nemotron AI-generated summary of video concepts: ### Introduction" [YouTube Link](https://youtube.com/watch?v=LnSt5jt-DkQ) 2025-06-09T20:49Z 201K followers, [----] engagements "How to Build a Document Processing Pipeline for RAG with Nemotron Learn to build a document pipeline that turns PDFs into cited answers with NVIDIA Nemotron. Traditional Retrieval-Augmented Generation (RAG) is effective for regular text but often fails with real-world documents that include tables figures and nested tables. When these complex document structures are reduced to simple text strings it causes "linearization loss". This means the helpful structure needed to understand the documents is removed which can lead to problems like not knowing which column a row value belongs to" [YouTube Link](https://youtube.com/watch?v=RzWXAI69G90) 2026-02-04T16:49Z 201K followers, [----] engagements "Post-Training Alignment and Advanced Reasoning with Nemotron Speaker: Oleksii Kuchaiev Director of Applied Research NVIDIA Post-training is the foundation for turning a base large language model into an aligned capable assistant boosting features like reasoning tool-calling and autonomy. Every AI assistant application relies on effective post-training which is evolving as fast as new capabilities like multi-step task solving and long-horizon tasks are being developed. At this research-focused talk by Oleksii Kuchaiev from the Nemotron models post-training team youll learn whats new and whats" [YouTube Link](https://youtube.com/watch?v=YUfveVThBIU) 2025-12-12T17:38Z 201K followers, [----] engagements "Build a RAG Agent with NVIDIA Nemotron Nemotron Labs Curious about designing AI agents using RAG Join us for a developer-focused livestream that takes you from first principles to code exploring the "why" and "how" of building agentic AI using practical examples. Well cover step by step: - A live demo: building and running a simple agentic RAG pipeline in a coding window with Nemotron NVIDIAs open reasoning model - How to connect tools use memory and see agentic behavior in action - Your questions answered throughout with relatable explanations and no prior experience needed By the end you'll" [YouTube Link](https://youtube.com/watch?v=f0utW0eLueY) 2025-09-01T21:59Z 201K followers, [----] engagements "Build an AI Agent for Report Generation with NVIDIA Nemotron on OpenRouter Nemotron Labs Curious about building AI agents This livestream will introduce you to building a reporting generation agent using NVIDIA Nemotron a family of open models with open datasets and open weights through an OpenRouter endpoint. Step-by-step well cover: - Understanding of the four core considerations of any AI agent - A working document generation agent that can research and write reports - Knowledge of how to build agents using LangGraph and OpenRouter - Your own customizable agent ready to share as a NVIDIA" [YouTube Link](https://youtube.com/watch?v=jb81ugc_o6I) 2025-09-15T21:58Z 201K followers, [----] engagements "Building Faster and Smarter AI Systems with Nemotron Speaker: Bryan Catanzaro VP of Applied Deep Learning Research NVIDIA Learn how were redefining AI development with Nemotron our open platform that brings together models data libraries and research to accelerate smarter faster AI. Bryan Catanzaro walks through why were building AI how Nemotron is designed to plug into existing workflows rather than replace them and how principles like faster AI is smarter AI shape everything from model architecture and scaling laws to deployment on real-world accelerated systems. ➡ Learn more:" [YouTube Link](https://youtube.com/watch?v=tG8TCkfpJ-Y) 2025-12-11T22:09Z 201K followers, [----] engagements "Build Culturally-Aware LLM Guardrails With Nemotron Safety Guard Current safety models often miss the subtle cultural and linguistic cues needed to moderate global content effectively. A phrase that seems harmless in one language may imply harm in another especially when tone idioms or slang are involved. The Llama [---] Nemotron Safety Guard 8b v3 model tackles this challenge by introducing a multilingual moderation system trained on the culturally adapted dataset: Nemotron Safety Guard dataset v2. Supporting nine languages it uses LLM-driven techniques to detect nuanced intent and" [YouTube Link](https://youtube.com/watch?v=uuhEAZjnePk) 2025-10-28T18:01Z 201K followers, [----] engagements "Build Vision AI Pipelines Faster with NVIDIA DeepStream Inference Builder The DeepStream Inference Builder part of NVIDIA's DeepStream SDK is a toolkit for building real-time AI-powered streaming analytics pipelines using video audio or image data. Inference Builder turns AI model ideas into production-ready services with ease. Developers can now go from YAML config to deployment in minutesautomating data flow preprocessing model execution and API integration. This video walks through how to use DeepStream Inference Builder with a quick example. Learn more about DeepStream SDK" [YouTube Link](https://youtube.com/watch?v=yj11L8rFC30) 2025-09-23T16:01Z 201K followers, [----] engagements "Jensen Huang Shows Off the New #NVIDIA DGX Spark Personal AI Computer #computex2025 #dgxspark #ai" [YouTube Link](https://youtube.com/watch?v=0jjam2JDi8c) 2025-05-23T15:36Z 201K followers, 19K engagements "DIY Autonomous Car Racing with NVIDIA Jetson Interested in seeing AI races in person Visit our amAIzing race track to watch or compete as DIY autonomous cars battle it out to the finals. The DIY Robocars community will be revving up their RC-sized cars at NVIDIAs GTC [----] in San Jose. Attendees are invited to root for their favorite team and learn about the cutting-edge AI technology in action. Victors and runner-ups will be awarded prizes In this video we talked to Chris Anderson Founder of DIY RoboCars and with members of the UCSD robotics club that participated in the [----] DIYRobocars" [YouTube Link](https://youtube.com/watch?v=4B2ipB7n5Nk) 2020-01-31T18:31Z 201K followers, 306.1K engagements "DGX Spark: Powering EPRIs AI Research Join EPRI a nonprofit research organization dedicated to advancing the science that powers a reliable affordable and resilient energy future. Discover how EPRI is innovating with NVIDIA DGX Spark to run advanced openweight models such as gptoss120b and Qwen3Embedding8B to drive a secure AI-powered document research assistant. Get started with DGX Spark: https://nvda.ws/4o2rDHn" [YouTube Link](https://youtube.com/watch?v=7U-NvEfKVfc) 2025-11-14T18:09Z 201K followers, [----] engagements "NVIDIA Cosmos Cookbook: Tips for the Physical Plausibility Recipe Learn how to get more out of NVIDIA Cosmos with tips straight from the authors behind our Cosmos Cookbook recipes. Watch the livestream 👉 https://www.addevent.com/calendar/ss55fmjpm04t Explore the Cosmos Cookbook 👉 https://nvda.ws/4k7EmaN Register for the hackathon 👉 https://nvda.ws/4qP4sly #NVIDIACosmos #WorldFoundationModels #CosmosCookbook #PhysicalAI NVIDIA Cosmos World Foundation Models Cosmos Cookbook Physical AI NVIDIA Cosmos World Foundation Models Cosmos Cookbook Physical AI" [YouTube Link](https://youtube.com/watch?v=7qlBN7aAQas) 2026-02-04T19:05Z 201K followers, [----] engagements "Build a Document Intelligence Pipeline With Nemotron RAG Nemotron Labs What if you could ask questions about complex PDFsdense tables charts and scanned pagesand have an AI agent answer with precise cited snippets from the original document without hand-writing brittle parsers With Nemotron RAG you can build a multimodal intelligent document processing pipeline from scratch in under an hour using GPU-accelerated extraction and just a few hundred lines of Python to turn unstructured files into grounded queryable knowledge. Curious how it works Join us for a developer-focused livestream that" [YouTube Link](https://youtube.com/watch?v=8uNnpnzYoqw) 2026-02-07T09:56Z 201K followers, [----] engagements "Developer Insights NVIDIA DGX Spark at PyTorch Conference Hear how this developer would #SparkSomethingBig if he had one at home. We love the excitement around NVIDIA DGX Spark at #PyTorchCon and #OpenSourceAIWeek" [YouTube Link](https://youtube.com/watch?v=9eoZZ60dfuw) 2025-10-23T16:03Z 201K followers, 18.2K engagements "NVIDIA MultiTalker ASR Demo: Real-Time Multi-Speaker Transcription Made Easy See how NVIDIAs MultiTalker ASR technology delivers live automatic transcription for conversations with multiple speakerseven when people talk over each other. This advanced AI system separates identifies and captions up to four voices simultaneously requiring no registration or enrollment. Built on NVIDIAs high-precision speech models MultiTalker extends beyond single-speaker ASR to capture every voice accurately and organize each streamwithout compromising clarity or speed. Watch the demo to explore latency and" [YouTube Link](https://youtube.com/watch?v=AThOsk2qJbs) 2025-12-05T21:19Z 201K followers, [----] engagements "Inference Office Hours with SGLang: Performance Optimizations for LLM Serving Join us to find out the latest inference optimizations for leading open source models from SGLang on NVIDIA GPUs. Well dive into an in-depth overview of the engineering behind optimizing SGLang on GB200 followed by a deep dive of recent performance advancements targeting low-latency inference and throughput efficiency. General Resources: Dynamo Day on demand: Inference OSS Ecosystem featuring SGLang https://nvda.ws/3MeKMsb SGLang Adds Day-0 Support for the Highly Efficient Open Nemotron [--] Nano Hybrid MoE Model" [YouTube Link](https://youtube.com/watch?v=CLzz7ZalYD8) 2026-02-06T01:33Z 201K followers, [----] engagements "Building a Multi-Agent Chatbot Demo on DGX Spark Looking to build a smarter fully local chatbot with multiple AI models working together This demo shows how to create a local multi-agent chatbot on DGX Spark running LLMs and VLMs side by side. A gpt-oss-120b supervisor agent coordinates experts in coding retrieval-augmented generation and visual understanding unlocking the power of collaborative AI. Create this chatbot using the playbook here- https://build.nvidia.com/spark/multi-agent-chatbot Learn more: build.nvidia.com/spark" [YouTube Link](https://youtube.com/watch?v=ItHGtLqUl3M) 2025-10-10T20:06Z 201K followers, 11.5K engagements "Getting Started with NVIDIA Triton Inference Server Triton Inference Server is an open-source inference solution that standardizes model deployment and enables fast and scalable AI in production. Because of its many features a natural question to ask is where do I begin Watch the video to find out GitHub: https://github.com/triton-inference-server/server Documentation: https://github.com/triton-inference-server/server/tree/main/docs #ai #inference #nvidiatriton #AI #inference #nvidiatriton ai inference ai inference nvidia triton triton inference server #AI #inference #nvidiatriton ai" [YouTube Link](https://youtube.com/watch?v=NQDtfSi5QF4) 2022-09-07T20:28Z 201K followers, 59.7K engagements "Building Multimodal AI RAG with LlamaIndex NVIDIA NIM and Milvus LLM App Development This video explains how to create a multimodal AI retrieval-augmented generation (RAG) application including the following steps: [--]. Document processing: Convert documents into text form using vision language models specifically NeVA 22B for general image understanding and DePlot for charts and plots. [--]. Vector database: Explore the power of GPU-accelerated Milvus for efficient storage and retrieval of your embeddings. [--]. Inference with Llama 3: Leverage the NVIDIA NIM API Llama [--] model to handle user queries" [YouTube Link](https://youtube.com/watch?v=NaT5Eo97_I0) 2024-09-03T21:06Z 201K followers, 24K engagements "Unboxing the NVIDIA DRIVE AGX Thor Developer Kit The developer kit is built on the NVIDIA Blackwell architecture next-generation Arm Neoverse V3AE CPUs and the NVIDIA DriveOS [--] software stack. Its purpose-built for reasoning vision language action models and ideal for automotive development with sufficient I/O to support surround cameras radars and lidars as well as common vehicle interfaces including GbE/10GbE and PCI-Express. DRIVE AGX Thor also meets the automotive industrys stringent functional safety (ISO 26262) and cybersecurity requirements (ISO 21434). URLs mentioned in the video:" [YouTube Link](https://youtube.com/watch?v=Tjzuyh1Ra4Q) 2025-09-22T18:34Z 200K followers, [----] engagements "Introducing NVIDIA DGX Spark GTC [----] Keynote NVIDIA DGX Spark belongs to a new class computers designed to build and run AI enabling developers to prototype fine-tune and inference large #AI models locally and seamlessly deploy to the data center or cloud. Learn more: https://www.nvidia.com/en-us/products/workstations/dgx-spark/ 📣 Announced 5/19/2025: We will be launching our AI-first personal computing systems NVIDIA DGX Spark and DGX Station with global computer makers. ➡" [YouTube Link](https://youtube.com/watch?v=UaGFUtqravQ) 2025-03-19T16:29Z 201K followers, 15K engagements "CES meets DGX Spark [----] wrap-up Join the NVIDIA Developer Community Team for our CES [----] WrapUp livestream. Well look at this years biggest moments and innovations from the keynote and bustling CES show floor featuring demos in action. Well share insights and reactions from the event adding depth and perspective including updates and responses to recent announcements across the industry. Then well spotlight whats new with DGX Spark the firstoutofthegate platform powering nextgeneration AI research and development everywhere. Expect snapshots of new opensource models community contributions" [YouTube Link](https://youtube.com/watch?v=UeSGx3pB25Y) 2026-01-07T00:02Z 201K followers, [----] engagements "Getting Started with the Jetson Orin Nano Developer Kit The NVIDIA Jetson Orin Nano Developer Kit sets a new standard for creating entry-level AI-powered robots smart drones and intelligent cameras. Compact design lots of connectors and up to [--] TOPS of AI performance give you everything you need to transform your visionary concepts into reality. In this video we take you through an overview of the Jetson Orin Nano Developer Kit including its key features specifications and components along with how to power on and initiate first boot of the device. To learn more please visit our website:" [YouTube Link](https://youtube.com/watch?v=VWdJ4BCtam8) 2023-03-21T15:17Z 201K followers, 133K engagements "New Nemotron RAG Models: Multimodal Embed and Rerank VLMs Meet llama-nemotron-embed-vl-1b and llama-nemotron-rerank-vl-1bcompact 1B VLMs for high-accuracy multilingual multimodal search and visual document retrieval ready for production. Use them to search beyond plain text across PDFs scans screenshots and slide decks in a single embed + rerank pipeline. 🤗Check out our blog on @HuggingFace: https://huggingface.co/blog/nvidia/llama-nemotron-vl-1b #Nemotron #RAG #OpenModels #opensource" [YouTube Link](https://youtube.com/watch?v=VZFuph90ieM) 2026-01-09T22:58Z 201K followers, [----] engagements "Intro to NVIDIA NIM for AI Builders Discover why portable cloud-native inference microservices are ideal for powering enterprise generative AI applications. Add to your calendar: https://www.addevent.com/event/FM24088078 To further explore and get started with NIM visit these resources: NVIDIA NIM for Developers: https://nvda.ws/4frykhh Try the NVIDIA Launchable from the livestream: https://nvda.ws/3VM3IQo NIM AI foundation models discord channel (First join the developer discord before participating in this channel): https://nvda.ws/3DqvWdi Try NIM in the NVIDIA API catalog:" [YouTube Link](https://youtube.com/watch?v=X12Li9eakF8) 2024-12-04T16:26Z 200K followers, 16.1K engagements "NVIDIA Jetson AGX Xavier Developer Kit - Introduction The NVIDIA Jetson AGX Xavier Developer Kit is the latest addition to the Jetson platform. Its an AI computer for autonomous machines delivering the performance of a GPU workstation in an embedded module under 30W. Jetson AGX Xavier is designed for robots drones and other autonomous machines. Learn more: https://developer.nvidia.com/jetson-xavier NVIDIA Jetson Developer Kit Robotics AI at the edge Autonomous Machines Intelligent Machines GPU AI Deep Learning Artificial Intelligence NVIDIA Jetson AGX Xavier NVIDIA Jetson Developer Kit" [YouTube Link](https://youtube.com/watch?v=XoWW5HiGHsg) 2018-07-10T23:50Z 201K followers, 127.8K engagements "Create Infinite Medical Imaging Data with Generative AI Learn More: https://monai.io/ #MONAI #medicalimaging #medicalAI Generative AI for medical imaging can create infinite synthetic images of the human anatomy. These large synthetic datasets are used for training generalizable AI models that can learn from evolving patient data while preserving patient privacy. Learn how MONAI a framework for building and deploying medical AI and partners like Kings College London Mount Sinai and East River Imaging are using generative AI to study disease and make AI decisions and predictions more accurate" [YouTube Link](https://youtube.com/watch?v=YHTSdd8-bnc) 2023-03-21T16:41Z 201K followers, 89.8K engagements "Fine-Tuning 8B Parameter Model Locally Demo with NVIDIA DGX Spark What if you could fine-tune massive AI modelsup to [--] billion parametersright on your desktop With NVIDIA DGX Spark you can. Supercharge your AI creativity by improving the performance of pre-trained models through easy powerful fine-tuning. Build solutions tailored exactly to your needswithout waiting on massive data centers. Learn more: build.nvidia.com/spark" [YouTube Link](https://youtube.com/watch?v=_C_0LvyN7QY) 2025-08-29T17:00Z 201K followers, 17K engagements "3 Steps for Building an Intelligent Document Pipeline for RAG With Nemotron Learn how to build a high-throughput IDP pipeline that uses vision-based extraction to turn complex charts and nested tables into searchable intelligence. By preserving document structure with markdown and multimodal embeddings you can boost RAG accuracy by 40%. Check out the full Jupyter notebook and technical blog. 📝 Tech blog: https://nvda.ws/3NVXM6r 📝Notebook: https://colab.research.google.com/drive/1qQXYfzmaIXglKfnqhZ2YXXE_OmAybxSr" [YouTube Link](https://youtube.com/watch?v=_SMEr44a0GI) 2026-02-05T17:00Z 201K followers, [----] engagements "1001 Ways to Accelerate Python with CUDA Kernels NVIDIA GTC [----] Learn how to write high-performance CUDA kernels directly in Python using tools and best practices that maximize GPU acceleration. In this NVIDIA GTC [----] session well explore kernel structure memory management thread coordination and optimization strategiesmaking it easier than ever to integrate CUDA into your Python applications. Speaker: Leo Fang Python CUDA Tech Lead NVIDIA Watch more NVIDIA GTC sessions on demand: https://www.nvidia.com/en-us/on-demand/ncid=so-yout-194474-vt33 CUDA Toolkit:" [YouTube Link](https://youtube.com/watch?v=_XW6Yu6VBQE) 2025-04-16T17:00Z 200K followers, 12.5K engagements "CUDA 13.0New Features and Beyond NVIDIA GTC D.C. The NVIDIA CUDA platform is the foundation of the GPU computing ecosystem. Every application and framework that uses the GPU does so through CUDA's libraries compilers runtimes and languagewhich means CUDA is growing as fast as its ecosystem is evolving. At this engineering-focused talk by CUDA's technical product lead you'll learn what's new and what's coming next for both CUDA and GPU computing as a whole. Speakers: Rob Armstrong CUDA Technical Product Management Lead NVIDIA Watch more: https://www.nvidia.com/en-us/on-demand/" [YouTube Link](https://youtube.com/watch?v=_vL8uz7kf0M) 2025-12-02T19:00Z 201K followers, [----] engagements "Set Up Your NVIDIA RTX [----] GPU for AI Development on Linux with PyTorch This step-by-step guide walks you through setting up your Ubuntu environment for deep learning using NVIDIA RTX [----] GPU PyTorch and Hugging Face. Learn how to install NVIDIA drivers verify installation install PyTorch and Hugging Face Transformers and run a state-of-the-art large language model. More specifically youll learn how to: ✔ Install the latest NVIDIA [----] drivers on Ubuntu [-----] LTS for optimal performance. ✔ Install PyTorch Torchaudio and Torchvision nightly with NVIDIA Blackwell support and validate GPU" [YouTube Link](https://youtube.com/watch?v=af7XjGekm4g) 2025-02-10T21:33Z 201K followers, 21.9K engagements "How to Build a Voice Agent with RAG and Safety Guardrails This tutorial provides a step-by-step guide on how to build a voice agent using the latest NVIDIA Nemotron models. Youll learn how to integrate four core components: multimodal RAG to retrieve relevant text and images automatic speech recognition (ASR) to convert live audio into text a safety model to filter safe or unsafe content and long-context reasoning to generate accurate grounded responses. 📝 Tech blog: https://nvda.ws/4snwyFz ➡ Learn more: https://nvda.ws/4jjQgxL 📥 Download:" [YouTube Link](https://youtube.com/watch?v=bCDcziL9OCo) 2026-01-05T22:10Z 201K followers, [----] engagements "Deploying Generative AI in Production with NVIDIA NIM 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 platformcloud data centers or on-prem. Discover how its cloud-native architecture backed by powerful tools like NVIDIA Triton Inference Server and TensorRT-LLM simplifies the deployment and scaling of AI models ensuring efficient and cost-effective operations. Whether you're looking to" [YouTube Link](https://youtube.com/watch?v=bpOvayHifNQ) 2024-05-20T16:49Z 201K followers, 311K engagements "Intro to NVIDIA Nsight Systems CUDA Developer Tools Join NVIDIAs Sven Middelberg for an introduction to NVIDIA Nsight Systems a tool for performance tuning NVIDIA GPU-accelerated applications. Nsight Systems provides a timeline view of your system's performance helping you identify bottlenecks and optimization opportunities. 00:00 - Introduction 2:14 - How to Trace an Application 6:34 - Using the Timeline View 8:36 - Analysis Summary Tab 8:50 - Diagnostics Summary Tab 9:07 - Conclusion Highlights include: Tracing with Nsight Systems: Walk through the tracing process including project setup" [YouTube Link](https://youtube.com/watch?v=dUDGO66IadU) 2023-09-22T15:47Z 201K followers, 22.1K engagements "Build a Simple AI Agent with OpenAIs gpt-oss-20b Learn how to build a simple AI agent with OpenAI's new gpt-oss models (20b and 120b) with NVIDIA NIM. In this video we demonstrate how to access NVIDIA NIM for OpenAIs gpt-oss reasoning models through build.nvidia.com and start building immediately. Discover how to use the OpenAI Responses API set reasoning efforts for different query complexities and create a web search agent. Whether you want to use NVIDIA-hosted NIM endpoints or privately deploy and scale gpt-OSS NIM microservices on your infrastructure this tutorial is great for you Get" [YouTube Link](https://youtube.com/watch?v=e2sgwsC92Bc) 2025-08-07T21:55Z 201K followers, 21.9K engagements "Getting Started with the NVIDIA Jetson AGX Orin Developer Kit The NVIDIA Jetson AGX Orin Developer Kit makes it easy to get started with Jetson Orin. Compact size lots of connectors and up to [---] TOPS of AI performance make this developer kit perfect for prototyping advanced AI-powered robots and other autonomous machines. In this video we take you through an overview of the Jetson AGX Orin Developer Kit including its key features specifications and components along with how to power on and initiate first boot of the device. For more details please check out our Getting Stated Guide:" [YouTube Link](https://youtube.com/watch?v=eFgsOeHMAW4) 2022-04-11T19:07Z 201K followers, 85.3K engagements "Frontiers of AI and Computing: A Conversation With Yann LeCun and Bill Dally NVIDIA GTC [----] As artificial intelligence continues to reshape the world the intersection of deep learning and high performance computing becomes increasingly crucial. This talk brings together Yann LeCun a pioneer in deep learning and the chief AI scientist at Meta and Bill Dally a leading computer architect and chief scientist at NVIDIA to explore the future of AI models hardware accelerators and the evolving computational landscape. The discussion covers: The next breakthroughs in deep learning and AI" [YouTube Link](https://youtube.com/watch?v=eyrDM3A_YFc) 2025-04-10T16:00Z 201K followers, 101.2K engagements "Customizing Your Personal AI With Open Models #nvidia #ai #jensenhuang #ces2026" [YouTube Link](https://youtube.com/watch?v=hHiDgAflX9U) 2026-01-08T23:03Z 201K followers, [----] engagements "An Introduction to NVIDIA Cosmos World Foundational Models NVIDIA GTC [----] NVIDIA Cosmos is transforming how robots and autonomous vehicles learn accelerating physics-aware synthetic video generation with world foundation models. Join Ming-Yu NVIDIAs VP of Generative AI Research to see how Cosmos is democratizing physical AI developmentgiving developers open models and tools to build custom world models faster than ever. Speaker: Ming-Yu Liu VP Generative AI Research NVIDIA NVIDIA GTC [----] Session S72431. Watch more #robotics sessions from GTC on demand:" [YouTube Link](https://youtube.com/watch?v=kChwwFb5gMU) 2025-04-08T22:30Z 201K followers, 16.3K engagements "Implementing New Algorithm with CUDA Kernels CUDA C++ Class Part [--] Welcome to NVIDIAs Modern CUDA C++ Programming Class. You will learn how to implement new algorithms on the GPU using CUDA Kernels. This series is for C++ developers who want to use the GPU effectivelywhether youre new to CUDA and want the fastest path from hello world to real acceleration or youre an experienced CUDA programmer ready to modernize your code with the latest best practices. If you already know C++ and want to write clean efficient idiomatic GPU code this course is for you. This video is part of a broader" [YouTube Link](https://youtube.com/watch?v=kTWoGCSugB4) 2025-11-06T22:13Z 201K followers, [----] engagements "Building with FLUX.2: From Prototype to Real-World Application Join Black Forest Labs a member of the NVIDIA Inception Program and NVIDIA for an immersive technical exploration into FLUX.2 the state-of-the-art model redefining the boundaries of visual synthesis. Technical experts will deconstruct the FLUX.2 architecture discussing optimized deployment strategies on NVIDIA infrastructure and the diverse use casesfrom enterprise design to media productionthat this model enables. In this livestream join us for: - Live coding demonstrations of real-world examples illustrating how to move a" [YouTube Link](https://youtube.com/watch?v=lY615qJVc18) 2026-01-22T13:05Z 201K followers, [----] engagements "DGX Spark Live: Your Questions Answered Vol. [--] Got questions about DGX Spark / GB10 Whether youre exploring how DGX Spark can boost your workflows or looking to get more out of your existing setup this livestream is designed to give you real answers and practical insights. Well cover key topics to help you fully understand such as benefits use case and integration. Join us live bring your questions and get the clarity you need to make the most of your DGX Spark experience" [YouTube Link](https://youtube.com/watch?v=nRo-tQC-mEY) 2026-02-04T00:09Z 201K followers, [----] engagements "#NVIDIA DGX Spark - Your Own Personal #AI Supercomputer ✅ [--] petaFLOP ✅ 128GB of coherent unified system memory ✅ ConnectX-7 Smart NIC ✅ Up to 4TB Storage ✅ 150mm L x 150mm W x 50.5mm H Reserve yours now" [YouTube Link](https://youtube.com/watch?v=owD8jmnM_ng) 2025-07-01T17:42Z 201K followers, 104.2K engagements "DGX Spark Live: Backend Development with Local LLM Inference In this episode well explore various ways DGX Spark can help engineering teams building Generative AI applications by iterating faster and managing their own development infrastructure. Topics covered include: open source inference engineers; open source models; use cases and opportunities. Getting Started with DGX Spark: https://nvda.ws/49TaaNs Demos shown available here: https://github.com/abdelrahmanhosny/embedded-ai" [YouTube Link](https://youtube.com/watch?v=rR3TpJvM150) 2025-12-05T06:27Z 201K followers, [----] engagements "DGX Spark Live: Real-Time Worker Safety with OnSight AI Powered by DGX Spark and Smart Glasses Join our latest hackathon winners - Team Tabasco for a live demo of OnSight AI a real-time AI safety and compliance system built during the NVIDIA DGX Spark Hackathon on December 12th. Using smart glasses and a Vision-Language Model (VLM) running on DGX Spark OnSight AI continuously analyzes first-person video to detect safety violations such as protective equipment and lock-out-tag-out (LOTO) compliance and delivers instant audio feedback to workers. See how the team integrated iOS/Android smart" [YouTube Link](https://youtube.com/watch?v=t-GIii3WE9I) 2025-12-20T07:49Z 201K followers, [----] engagements "NVIDIA Jetson AGX Orin: Next-level AI Performance for Next-Gen Robotics NVIDIA Jetson AGX Orin provides upto [---] TOPS of AI performance for running next-gen robotics. Watch this video on how we built Orion robot on Jetson AGX Orin platform using different technologies provided by NVIDIA. Learn more: https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-agx-orin/" [YouTube Link](https://youtube.com/watch?v=t5YwqZqLjys) 2022-03-22T14:45Z 201K followers, 42.6K engagements "DGX Spark Live: Process Text for GraphRAG With Up to 120B LLM See NVIDIA DGX Spark in action for local GraphRAG and graph analytics. We will showcase how this demo runs entirely on DGX Sparks 128GB unified memory extracting nodes and relationships from local biomedical research papers to build a context-aware Knowledge Graph in ArangoDB. Getting Started with DGX Spark: https://nvda.ws/4o2rDHn Start building with DGX Spark: https://nvda.ws/49TaaNs" [YouTube Link](https://youtube.com/watch?v=uQtzjAvJMlE) 2025-11-19T03:31Z 201K followers, [----] engagements "First Look: NVIDIA DGX SuperPOD with DGX GB200 Systems An exclusive first look at an NVIDIA DGX SuperPOD with eight DGX GB200 systems. See everything -- from Grace Blackwell Superchips to InfiniBand and Spectrum-X networking and liquid cooling -- that makes it a record-setting system. Straight from an Equinix data center in Silicon Valley. Read the blog: https://nvda.ws/3FOL1GG" [YouTube Link](https://youtube.com/watch?v=uWECSx5CoiM) 2025-04-07T20:30Z 201K followers, 25.3K engagements "NVIDIA Cosmos Cookbook: Tips for the Egocentric Social and Physical Reasoning Recipe Learn how to get more out of NVIDIA Cosmos with tips straight from the authors behind our Cosmos Cookbook recipes. Watch the livestream 👉 https://www.addevent.com/calendar/ss55fmjpm04t Explore the Cosmos Cookbook 👉 https://nvda.ws/4k7EmaN Register for the hackathon 👉 https://nvda.ws/4qP4sly #NVIDIACosmos #WorldFoundationModels #CosmosCookbook #PhysicalAI NVIDIA Cosmos World Foundation Models Cosmos Cookbook Physical AI NVIDIA Cosmos World Foundation Models Cosmos Cookbook Physical AI" [YouTube Link](https://youtube.com/watch?v=wjWUjK0e6B8) 2026-02-03T16:55Z 201K followers, [----] engagements "Introduction to the Nsight Tools Ecosystem CUDA Developer Tools GPU acceleration enables faster and smarter applications and CUDA enables you to harness acceleration on NVIDIA GPUs. But debugging profiling and optimizing CUDA can be challengingespecially if you cant see the hardware processes interfacing with CUDA. To help you fully harness CUDA acceleration NVIDIA offers tools to make development easier and more efficient. This tutorial is an introduction to the NVIDIA Nsight Developer Tools ecosystem a suite of software libraries SDKs and IDE tools that help you use CUDA to accelerate your" [YouTube Link](https://youtube.com/watch?v=xdFQZSV5IrU) 2023-09-22T15:43Z 200K followers, 12.4K engagements "DGX Spark Live: Rapid AI Agent Development The latest generation of AI models is accelerating the deployment of AI agents helping to write code perform deep research or act as a personal assistant managing schedules booking travel and updating calendars. The ability to quickly create and deploy AI agents is becoming a business imperative. Join us to learn how Aible enables you to rapidly create AI agents within minutes using your data and easily deploy them on desktop data center or cloud. We will explore how Aible takes advantage of DGX Spark to build and deploy agents and how you can use" [YouTube Link](https://youtube.com/watch?v=yD72eaCOQjA) 2026-01-28T06:22Z 201K followers, [----] engagements "Tensor Cores in a Nutshell This video gives a brief introduction to the Tensor Core technology inside NVIDIA GPUs and how its important to maximizing deep learning performance. https://developer.nvidia.com/tensor-cores NVIDIA AI GPU Tensor Core Tensor Cores Tensorcore Tensorcores Deep Learning DL Deep Learning Training AI Training CNN DNN Mixed-Precision Training Mixed-Precision Mixed Precision Mixed Precision Training FP-16 FP-32 FP16 FP32 NVIDIA AI GPU Tensor Core Tensor Cores Tensorcore Tensorcores Deep Learning DL Deep Learning Training AI Training CNN DNN Mixed-Precision Training" [YouTube Link](https://youtube.com/watch?v=yyR0ZoCeBO8) 2019-01-30T18:26Z 201K followers, 106.4K engagements "Simplifying AI Cluster Management with NVIDIA Base Command AI clusters are difficult to manage. There are multiple hardware and software elements to coordinate and constant updates that can be extremely time consuming. DIY approaches also require diverse skills spanning networking compute and storage. NVIDIA Base Command is the operating system of the accelerated data center. It lets organizations use the full potential of their NVIDIA DGX investment with a proven platform that includes enterprise-grade orchestration and cluster management as well as libraries that accelerate compute storage" [YouTube Link](https://youtube.com/watch?v=zD0zDQ-nerQ) 2022-09-19T06:32Z 201K followers, [----] engagements "Analyzing NCCL Usage with NVIDIA Nsight Systems NVIDIA Nsight Systems now includes support for tracing NCCL (NVIDIA Collective Communications Library) usage in your CUDA application. This enables users to identify NCCL activity on the CPU timeline and correlate it to the associated GPU #CUDA kernels and #memory copies. Equipped with this information users can validate and improve NCCL usage by identifying CPU and GPU cold spots and hot spots. Nsight Systems is the go-to profiling tool for gaining a holistic view of CUDA #applications. #SC20 Learn more about Nsight Systems the family of Nsight" [YouTube Link](https://youtube.com/watch?v=bda5Er27jqo) 2020-11-09T13:31Z 199K followers, 43.3K engagements "GPU Accelerated Polars Learn how Polars Lazy Evaland NVIDIA GPU acceleration can accelerate your Data Science. These two tools create a powerful backend that builds an optimized query plan and parallelizes execution on NVIDIA GPUs. Get started in Google Colab or locally. #datascience #polars #gpu #python" [YouTube Link](https://youtube.com/watch?v=bhSYfADZDBk) 2025-04-25T19:27Z 193K followers, [----] engagements "Office Hours - Nemotron Have questions on NVIDIA's Nemotron models Want to provide your thoughts on the models directly to NVIDIA RSVP to attend office hours and drop any questions you have on our Discord channel https://discord.com/channels/1019361803752456192/1407781691698708682 or in the comments below" [YouTube Link](https://youtube.com/watch?v=c1Fbta1fSdw) 2025-09-05T00:34Z 195K followers, [----] engagements "AI Physics Deep Dive Industrial Engineering Live Stream Series Interested in AI Physics Join our "AI Physics Deep Dive" livestream to learn about the latest ML architectures for computational engineering workloads and for a hands-on tour of NVIDIA PhysicsNeMo including practical recipes of how to train and test the latest in AI Physics models. Well cover step by step: - A live demonstration of building and running NVIDIA PhysicsNeMo platform for industrial engineering problems such as CFDstructural analysis and more. - Walkthroughs of the pros and cons of using graph neural networks neural" [YouTube Link](https://youtube.com/watch?v=c4FjMkGE0eo) 2025-10-30T12:55Z 193K followers, [----] engagements "Getting Started with NGC Part 3: NGC Model Download Workflow NVIDIA NGC is a cloud platform that provides access to GPU-optimized software containers and pre-trained deep learning models making it easier for data scientists and developers to deploy and run deep learning and HPC applications on NVIDIA GPUs. In this video we demo a workflow which showcases how to use the NGC CLI to download a pretrained model. To learn more about NVIDIA AI Enterprise Administration: https://academy.nvidia.com/en/nvaie-public-training/" [YouTube Link](https://youtube.com/watch?v=cDt4GAHZNX8) 2023-05-01T11:50Z 197K followers, [----] engagements "Get Started with cuTile Python The release of NVIDIA CUDA [----] introduces tile-based programming for GPUs making it one of the most fundamental additions to GPU programming since CUDA was invented. Learn how you can write GPU tile kernels that allows you to write your algorithm at a higher level than a single instruction multiple thread (SIMT) model and the compiler and runtime handle the partitioning of work onto threads under the covers. Resources and Links: 🔗 cuTile Python GitHub Repository: https://github.com/NVIDIA/cutile-python 📖 Official cuTile Python Documentation:" [YouTube Link](https://youtube.com/watch?v=cNDbqFaoQ9k) 2025-12-04T22:23Z 196K followers, [----] engagements "NVIDIA DGX Station: Desktop Tour Watch this short video to see the highlights of the DGX OS Desktop environment. https://nvda.ws/2V7zA02" [YouTube Link](https://youtube.com/watch?v=dLK2wuIKjPw) 2019-03-28T18:59Z 193K followers, 12.3K engagements "CUDACast #10a - Your First CUDA Python Program In this CUDACast video we'll see how to write and run your first CUDA Python program using the Numba Compiler from Continuum Analytics" [YouTube Link](https://youtube.com/watch?v=dPQnFXD7DxM) 2017-07-20T23:49Z 198K followers, 155.8K engagements "Why Is NVIDIA AI-Q the Top-Rated Open Portable AI Agent for Deep Research NVIDIA AI-Q is now #1 among open and portable AI agents on the Deep Research Bench leaderboard achieving a best-in-class score of [-----]. The portability of AI-Q enables organizations to build agents that operate anywheredata center or cloud. Agents that operate locally within enterprise data centers can reduce latency and improve security. Open and built with models like NVIDIA Llama Nemotron the AI-Q blueprint is completely customizable enabling organizations to adapt the deep research for their unique use cases. AI-Q" [YouTube Link](https://youtube.com/watch?v=dd_pJchCxTg) 2025-08-04T16:59Z 195K followers, [----] engagements "Course Introduction: How to Build a RAG Agent Build smarter RAG systems that reason adapt and retrieve information autonomously. This course takes you from traditional RAG to agentic RAG AI agents that go beyond simple retrieval to actively reason through complex information tasks. Learn the architecture build the pipeline and deploy your own RAG agent using NVIDIA tools. What you'll learn in the full module: How to Build RAG Agent https://developer.nvidia.com/topics/how-to-build-agentic-ai-rag Key differences between traditional and agentic RAG systems How to architect a complete RAG" [YouTube Link](https://youtube.com/watch?v=e7Io9dr_WhI) 2025-10-27T02:53Z 193K followers, [----] engagements "NVIDIA's Dedication to Open Source NVIDIA GTC Washington D.C. [----] Keynote "The United States has to lead in open source as well. We have amazing proprietary models. We have amazing proprietary models. We need also amazing open source models. Our country depends on it. Our startups depend on it. And so NVIDIA is dedicating ourselves to go do that." -- Jensen Huang Watch the full NVIDIA GTC keynote here: https://www.youtube.com/live/lQHK61IDFH4si=_-wQFaqQNb6Y1gjR&t=4748 #nvidia #nvidiagtc #opensource" [YouTube Link](https://youtube.com/watch?v=eKwpmzvyD68) 2025-10-28T20:50Z 196K followers, [----] engagements "Train AI Agents for CLI Tasks using Synthetic Data & Reinforcement Learning Nemotron Labs What if your computer-use agent could learn a new command-line tooloperating it safely without writing files or free-typing shell commands With NVIDIA Nemotron open models you can quickly train specialized agents for any CLI using synthetic data and reinforcement learningno usage logs required. Curious how it can be adapted for your own proprietary CLI environment Join us live for a developer-focused livestream. In this interactive livestream well cover: - A live demo: Generating synthetic training data" [YouTube Link](https://youtube.com/watch?v=ekVtMFoOU-E) 2025-11-22T04:10Z 194K followers, [--] engagements "Predict LLM Performance with Dynamo AI Configurator Optimizing large language model (LLM) serving is complex. Which framework offers the best perf How do you choose between aggregated vs. disaggregated serving If disaggregated whats the best prefill/decode split What kind of parallelism should you use for each worker Exploring this space can take weeks. AI Configurator simplifies this to just minutes. Use the CLI to input your model hardware traffic characteristics and goals and the tool intelligently searches for an optimal configuration. AIC combines kernel-level benchmarks on real silicon" [YouTube Link](https://youtube.com/watch?v=en5kCYpxVjk) 2025-12-15T23:24Z 201K followers, [---] engagements "Getting started on NVIDIA-Powered Data Science Workstations Walk through getting started on NVIDIA-Powered Data Science Workstations powerful systems featuring pre-installed CUDA-X AI software libraries and NVIDIA Quadro RTX [----] GPUs. See a demo on how these systems unlock new levels of performance and productivity for data scientists. Learn more about RAPIDS: https://rapids.ai Learn more about Data Science Workstations: https://nvidia.com/data-science-workstation" [YouTube Link](https://youtube.com/watch?v=enN9F_iNVLw) 2019-07-01T22:15Z 194K followers, 10K engagements "What is Word Error Rate (WER) and how do I properly calculate it to benchmark ASR models Word Error Rateor WERmeasures how many words a speech-to-text system gets wrong compared to a human transcript. NVIDIAs open source automatic speech recognition (ASR) models Canary-Qwen-2.5B and Parakeet-TDT-0.6B-V2 which reflect the openness philosophy of Nemotron with open datasets weights and recipes hold top spots on the new ArtificialAnalysis (AA) ASR leaderboard for record WER. 🏆 Leaderboard ➡ https://artificialanalysis.ai/speech-to-text 📥 Canary Qwen 2.5B ➡" [YouTube Link](https://youtube.com/watch?v=eqK0-ywjpTw) 2025-09-25T18:13Z 190K followers, [----] engagements "Dynamo KVBM - Managing Memory at Scale Got questions about KV cache management in your LLM deployment Join us for a session on Dynamo's KV Block Manager (KVBM)- a system that decouples memory management from run-time logic to enable memory-efficient high-throughput LLM systems. Well dive into architecture integration with LLM inference runtimes integration with NIXL and our roadmap. Come ready to chat drop your questions in the comments and learn more from the engineers building KVBM. Be part of the journey and contribute on github: https://bit.ly/dynamoKVBM" [YouTube Link](https://youtube.com/watch?v=f5O3BrGwZVE) 2025-10-28T01:05Z 190K followers, [--] engagements "NVIDIA AI Tech Workshop at NeurIPS Expo [----] - Session 5: Applied Deep Learning This session from the NVIDIA AI Tech Workshop at NeurIPS Expo [----] highlighted by NVIDIA Research includes: - Building Speech Recognition with Synthetic Speech - Optimization of training neural collaborative filtering systems Presentation slides will be uploaded soon for reference" [YouTube Link](https://youtube.com/watch?v=fU_PV4HSCSQ) 2018-12-05T19:30Z 189K followers, [----] engagements "Deploy and Scale AI Workloads with NVIDIA Run:ai on Azure Kubernetes Service (AKS) NVIDIA Run:ai on Azure Kubernetes Service empowers organizations to unlock fast scalable and efficient AI infrastructure for large language models and generative AI applications. In this demo you will discover how NVIDIA Run:ai on Azure Kubernetes Service transforms deployment with its intelligent orchestration of GPU resources enabling real-time training and inference for enterprise workloads. The video highlights the seamless integration between NVIDIA Run:ai and Microsoft Azure making AI infrastructure" [YouTube Link](https://youtube.com/watch?v=fgF3c_ZY5yQ) 2025-10-30T16:27Z 190K followers, [---] engagements "Ray Tracing Essentials Part 1: Basics of Ray Tracing In Part 1: Basics of Ray Tracing NVIDIA's Eric Haines runs through the basics of ray and path tracing. To begin he defines a ray and notes how it is useful for different operations in computer graphics. Rays can be cast to test for shadows for example. In [----] Whitted introduced the idea of recursive ray casting known as ray tracing. Cook and others in [----] explored how bursts of rays could create more elaborate effects such as soft shadows and glossy reflections. Kajiya introduced the Rendering Equation in [----] showing how it could be" [YouTube Link](https://youtube.com/watch?v=gBPNO6ruevk) 2019-12-20T01:56Z 195K followers, 142K engagements "Visualizing a Twin Earth in NVIDIA Omniverse This is the Earth as we know it. Creating a Digital Twin of the Earth using technologies like the #NVIDIAOmniverse ParaView Connector allows scientists to interactively analyze weather and climate data in 3D and to combine information from multiple sources and explore what if scenarios. Read the Omniverse #ParaView Connector blog: https://nvda.ws/3xaZRhQ Learn how Omniverse is transforming #ScientificVisualization workloads: https://nvda.ws/32GP8y1" [YouTube Link](https://youtube.com/watch?v=gTiqV3akBIE) 2021-04-21T18:34Z 199K followers, 32.3K engagements "Transforming AI NVIDIA GTC [----] Panel Hosted by Jensen Huang The Transforming AI panel from GTC [----] features the authors of Attention Is All You Need" the groundbreaking paper that introduced the transformer neural network architecture. Transformers have since dominated all areas of AI revolutionizing the industry. The discussion covers the following topics: The development and impact of the Transformer model. The evolution of computing and its democratization. The future of AI technology and its potential applications. The role of accelerated computing. The potential for AI to revolutionize" [YouTube Link](https://youtube.com/watch?v=hC_qASRcBhU) 2024-04-08T23:30Z 194K followers, 117.6K engagements "NVAITC Webinar: Introduction to Convolutional Neural Networks Understand and discuss implementations of common convolutional and residual neural networks. Learn more: https://developer.nvidia.com/deep-learning-examples" [YouTube Link](https://youtube.com/watch?v=hGnpGi92J84) 2020-11-30T17:07Z 189K followers, [----] engagements "Train a Reasoning-Capable LLM in One Weekend Have you ever wanted to build your own reasoning models such as NVIDIA Nemotron but thought it was too complicated or required massive resources Think again. With NVIDIAs powerful tools and datasets you can train a small effective reasoning model in about [--] hours all on a single GPU. Explore a simple and computationally efficient recipe for training reasoning models with small amounts of training data curated from the Llama Nemotron Post-Training Dataset. Learn the strategy based on LoRA adapter training and the key considerations and" [YouTube Link](https://youtube.com/watch?v=hMGikmMFLAU) 2025-07-30T16:14Z 191K followers, 16.8K engagements "Implementing Real-time Vision AI Apps Using NVIDIA DeepStream SDK Learn how companies around the world are modernizing their existing infrastructure with IoT sensors such as cameras to extract rich insights. Whether its a patient fall detection monitoring system in a hospital understanding how traffic flows through a city or a retailer looking to understand customer purchasing sentiments and behavior real-time video analysis plays a pivotal role. Learn how various companies are building high-performance apps using DeepStream SDK for real-time video and image understanding. We'll show you the" [YouTube Link](https://youtube.com/watch?v=hSegX0P170s) 2021-01-16T16:30Z 190K followers, 30.4K engagements "Optimize AI Agents with Continuous Model Distillation and Evaluation Using a Data Flywheel Learn how to optimize AI agents in production using the NVIDIA Data Flywheel Blueprinta continuous loop of distillation fine-tuning and evaluation powered by NeMo and NIM microservices. See how to replace a Llama 70B model with a smaller faster one using LoRA ICL and LLM-as-a-judge scoringall driven by real-world agent traffic. This demo: Breaks down the architecture and building blocks of the blueprint Walks through how to replace a production-grade Llama 70B model with a smaller faster alternative for" [YouTube Link](https://youtube.com/watch?v=hTYrjYbFHyU) 2025-06-11T09:01Z 198K followers, [----] engagements "NVIDIA Jetson Partner Stories: Jibo Makes Its Robot More Social with the Jetson Platform The Jetson TK1 has been an accelerant to the design and development process of the Jibo the world's first consumer social robot for the home. The increased processing power of the Jetson TX1 will help the creators of Jibo to do some very special things with vision processing beyond simple facial recognition such as the ability to leverage more sophisticated object detection leading to a faster and more responsive robot for consumers" [YouTube Link](https://youtube.com/watch?v=i9rrVFd5zGM) 2015-11-11T17:03Z 189K followers, 15.1K engagements "Quansight and RAPIDS Push Data Science Performance Travis Oliphant CEO of Quansight and early contributor to RAPIDS explains the work being done to integrate GPUs with data" [YouTube Link](https://youtube.com/watch?v=iHM4RyjeV-U) 2018-11-07T23:03Z 188K followers, [----] engagements "Run NVIDIA GPU Cloud Containers in Singularity This video covers (1) Installing and configuring Singularity (2) Pulling and saving NGC containers and (3) Running NGC containers in an HPC environment. Learn more: https://nvda.ws/2QXzzKm" [YouTube Link](https://youtube.com/watch?v=iOLVqqHQsBU) 2018-10-18T17:15Z 191K followers, [----] engagements "CUDACast #7 - CUDA [---] nvidia-smi Accounting To learn more or comment on this video visit the blog post at http://bit.ly/cudacast-7 Learn about the new accounting features part of the nvidia-smi tool in CUDA [---] CUDA-5.5 CUDACasts nvidia-smi GNU/Linux (Operating System) CUDA-5.5 CUDACasts nvidia-smi GNU/Linux (Operating System)" [YouTube Link](https://youtube.com/watch?v=iXuRjAlPy6Q) 2013-08-22T19:08Z 200K followers, [----] engagements "GTC Silicon Valley Preview: Media & Entertainment NVIDIAs GPU Technology Conference (GTC) is the premier AI and deep learning conference providing training insights and direct access to media and entertainment experts. Here's a preview of the some of the Media & Entertainment sessions you can attend. https://nvda.ws/2CWq34u" [YouTube Link](https://youtube.com/watch?v=iYKoDVyOrEE) 2019-01-30T21:56Z 188K followers, [----] engagements "Introduction to NVIDIA DOCA Module #1: DOCA Demystified Learn the basic concepts of NVIDIA DOCA as a platform for accelerated data center application development for the NVIDIA BlueField DPU. Upon completion participants will be equipped with a set of introductory knowledge that will enable them to begin using DOCA and DPUs to develop applications that accelerate their data centers services. Complete all [--] modules of this free self-paced course on the NVIDIA Deep Learning Institute: https://nvda.ws/3nLw78v Get early access to the DOCA SDK: https://nvda.ws/3InM3ph Learn more about BlueField" [YouTube Link](https://youtube.com/watch?v=iaFN0F53L6w) 2022-01-21T19:23Z 198K followers, 18.4K engagements "Build an AI Agent for Report Generation with NVIDIA Nemotron on OpenRouter Learn how to build a powerful AI report generation agent from scratch In this workshop we'll walk you through the core concepts of AI agent design and give you hands-on experience with NVIDIA Nemotron and OpenRouter. You'll set up your development environment build the agent's tools implement research and authoring functionalities and orchestrate the entire workflow. By the end you'll have your very own report-writing agent in a turn-key portable development environment. #AIAgent #OpenRouter #Nemotron #buildyourown" [YouTube Link](https://youtube.com/watch?v=idgV7DgrzLo) 2025-09-23T17:26Z 198K followers, [----] engagements "3 Ways to Accelerate pandas with NVIDIA GPUs [--] Ways to Accelerate pandas with NVIDIA GPUs. Accelerating your pandas code is now a no-code or low-code task. This video deep dives into [--] methods across multiple coding environments to help you accelerate your pandas code. 00:00 - Intro 00:30 - Method [--] - magic command 03:55 - Method [--] - cuDF module 07:27 - Method [--] - cuDF code 09:24 - Outro ➡ Join the NVIDIA Developer Program: https://nvda.ws/3OhiXfl ➡ Read and subscribe to the NVIDIA Technical Blog: https://nvda.ws/3XHae9F #pandas #python #NVIDIA #GPU #datascience #machinelearning #ML #cuDF" [YouTube Link](https://youtube.com/watch?v=jFi60VQVmF4) 2025-07-15T19:00Z 197K followers, [----] engagements "Gemma3 Running at [--] Tokens/sec on Jetson Orin Nano Live VLM Demo Watch a live demo by Asier Arranz Senior Developer Advocate at NVIDIA running Gemma3 on Jetson Orin Nano at [--] tokens/sec including both the 4B and an impressive 12B modelright from Googles Gemma3 launch event in Paris. Learn how to deploy high-performance Visual Language Models (VLMs) on compact edge devices for real-time multimodal AI. If you're exploring similar projects or have ideas you'd like to share feel free to comment or get in touch Subscribe to Google for Developers https://goo.gle/developers #Gemma" [YouTube Link](https://youtube.com/watch?v=jSKHeYVcAB8) 2025-04-03T19:44Z 199K followers, 17K engagements "From a Robot's Perspective: Teaching Robots to Grasp We are teaching our robot arm to grasp commonly used objects with diverse appearances. We trained our models purely in simulation and they now achieve 88% success rate in the real world without any extra steps. https://arxiv.org/pdf/1905.10520.pdf" [YouTube Link](https://youtube.com/watch?v=jypErPo47IA) 2019-08-28T20:23Z 162K followers, [----] engagements "Get Started with NVIDIA TAO Toolkit The #NVIDIATAO Toolkit built on TensorFlow and PyTorch is a low-code AI solution that abstracts away the AI and deep learning framework complexity. It lets you use the power of transfer learning to fine-tune NVIDIA pretrained models with your own data.This video walkthrough will show you how to install the TAO Toolkit followed by a step-by-step guide process of fine-tuning a pretrained model in a Jupyter notebook. Learn more https://nvda.ws/39h47Fd Join the NVIDIA Developer Program: https://nvda.ws/3OhiXfl Read and subscribe to the NVIDIA Technical Blog:" [YouTube Link](https://youtube.com/watch?v=kErfKDZ50To) 2023-08-11T19:44Z 199K followers, [----] engagements "How to Autoscale Efficiently with Disaggregated Serving How can you use GPUs efficiently with disaggregated serving This video explains how NVIDIA Dynamo and its open-source planner help you serve models at large scale while meeting your service level objectives (SLOs) like time to first token and inter-token latency. Learn how prefill and decode steps are split across dedicated GPUs and why scaling shouldnt be reactionary. With time series forecasting NVIDIA Dynamo automatically scales the number of prefill or decode machines based on workload demands whether youre summarizing long documents" [YouTube Link](https://youtube.com/watch?v=kPGaxHiV99U) 2025-08-12T17:01Z 192K followers, [----] engagements "Real-Time Digital Twin - Deep Dive Industrial Engineering Livestream Series 📱 Join our Real-Time Digital Twin (RTDT) Deep Dive livestream to learn about how to build RTDTs using Omniverse APIs kit-CAE extension and NVIDIA PhysicsNeMo. This session includes live walk-through of the code base and examples for automotive aerospace and data-center design. Well cover step by step: A live demonstration of building and using the NVIDIA Omniverse kit-CAE extension for industrial engineering problems integrating data from CFD structural analysis and more. Walkthroughs of the different data importers" [YouTube Link](https://youtube.com/watch?v=kZG8dkG6hnI) 2025-11-19T03:48Z 194K followers, [--] engagements "XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies New #NVIDIAResearch Paper: XCube (X3): Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies by Xuanchi Ren Jiahui Huang Xiaohui Zeng Ken Museth Sanja Fidler Francis Williams Abstract: We present X3 (pronounced XCube) a novel generative model for high-resolution sparse 3D voxel grids with arbitrary attributes. Our model can generate millions of voxels with a finest effective resolution of up to [-----] in a feed-forward fashion without time-consuming test-time optimization. To achieve this we employ a" [YouTube Link](https://youtube.com/watch?v=kpmCQp9mabo) 2023-12-08T16:46Z 189K followers, [----] engagements "Simplicits: Mesh-Free Geometry-Agnostic Elastic Simulation NVIDIA Research The proliferation of 3D representations from explicit meshes to implicit neural fields and more motivates the need for simulators agnostic to representation. We present a data- mesh- and grid-free solution for elastic simulation for any object in any geometric representation undergoing large nonlinear deformations. We note that every standard geometric representation can be reduced to an occupancy function queried at any point in space and we define a simulator atop this common interface. For each object we fit a small" [YouTube Link](https://youtube.com/watch?v=kxEpXkSv2cM) 2024-07-27T17:00Z 192K followers, [----] engagements "Multi-GPU Communication Libraries for Scaling HPC and AI Workloads NVIDIA GTC [----] Want to scale beyond the limits of a single GPU Learn how to use CUDA-aware MPI NVSHMEM and NCCL to scale your applications across multiple GPUs and nodes. This GTC [----] session features a real-world example to help you choose the right communication library for your performance and workload needs. Speaker: Jiri Kraus Principal Developer Technology NVIDIA Replay of NVIDIA #GTC25 Session ID: S72578 Topic: Models / Libraries / Frameworks - Accelerated Computing Libraries NVIDIA technology: CUDA CUDA-X NCCL NVLink" [YouTube Link](https://youtube.com/watch?v=kyQtbyR536I) 2025-04-22T18:00Z 199K followers, [----] engagements "NVIDIA Jetson Partner Stories: Fellow Robots -- LoweBot NAVii Fellow Robots CTO Thavidu Ranatunga presents LoweBot a Jetson TX1-powered NAVii robot designed to guide Lowes Hardware customers to their item of choice via voice recognition or an onboard touchscreen display. LoweBot navigates the aisles autonomously and in an often Wi-Fi denied environment using cameras and odometry alone to find its destination. During off-hours LoweBot helps store employees by tracking depleted or missing inventory with a high-resolution camera and LED light source recognizing items using a Deep Learning-based" [YouTube Link](https://youtube.com/watch?v=l7NPmJP462M) 2017-03-08T02:09Z 193K followers, 35.8K engagements "Accelerated Machine Learning with XGBoost on NVIDIA GPUs Accelerated Data Science Series Learn how to get a 25x performance increase of XGBoost training inference and feature engineering with pandasall accelerated with RAPIDS running in Google Colab. In this demo GPUs are used to accelerate workflows using real-world taxi fare data build baseline models and incrementally improve model accuracy with advanced feature engineering. All of this is done directly in Google Colab where RAPIDS and XGBoost are pre-installed for seamless access. 📗 Try this yourself on Google Colab:" [YouTube Link](https://youtube.com/watch?v=lhraJRaDkOA) 2025-02-21T20:47Z 179K followers, [----] engagements "Deep Reinforcement Learning in Robotics with NVIDIA Jetson Discover the creation of autonomous reinforcement learning agents for robotics in this NVIDIA Jetson webinar. Learn about modern approaches in deep reinforcement learning for implementing flexible tasks and behaviors like pick-and-place and path planning in robots. Learn more at https://developer.nvidia.com/embedded/twodaystoademo#advanced-deep_reinforcement Buy the latest Jetson products at https://developer.nvidia.com/buy-jetson" [YouTube Link](https://youtube.com/watch?v=luzOblzznIc) 2019-06-11T17:08Z 192K followers, 21.7K engagements "Open Models Are Now Frontier Models #nvidia #ai #jensenhuang #ces2026" [YouTube Link](https://youtube.com/watch?v=mCcXwBdQpf8) 2026-01-10T22:00Z 201K followers, [----] engagements "Get Started with NVIDIA IGX Orin Developer Kit for Scalable Edge AI Solutions Learn how to quickly configure your NVIDIA IGX Orin Developer Kit an industrial-grade platform for developing and deploying real-time edge AI inference applications. Watch this video for an overview of the system and the different ways you can use it. Youll also learn how to: ⚬ Unbox and power up your system ⚬ Set up your system ⚬ Install the NVIDIA Holoscan SDK ⚬ Run your first Holoscan application Discover more about NVIDIA IGX Orin: https://www.nvidia.com/en-us/edge-computing/products/igx/ Read the NVIDIA IGX" [YouTube Link](https://youtube.com/watch?v=mKN5u_eZQII) 2023-10-30T17:39Z 194K followers, 10.1K engagements "Google's Gemma2 SLM on NVIDIA Jetson Orin Nano: The Future of Conversational Edge AI Dive into Google's Gemma2 SLM on Jetson Orin Nano with these easy beginner-friendly demoseven if you have ZERO experience with Jetson In this video Ill walk you through simple steps to bring powerful conversational AI to life on a small efficient device. From setup to real-time interaction see how easy it is to get started with advanced AI at the edge. Heres what youll learn: - Step-by-step setup for Gemma2 SLM on Jetson Orin Nano perfect for beginners. - Real-time conversational AI demos including" [YouTube Link](https://youtube.com/watch?v=mgUrthfw3ys) 2024-10-28T22:09Z 188K followers, 14.6K engagements "DGX Spark Live: Installation & First Run Guide for Robotics Developers 📱 This is the essential live session for robotics developers ready to leverage NVIDIA Isaac Sim on the powerful DGX Spark platform. We'll guide you through the initial steps to get your high-fidelity simulation environment up and running on the aarch64 architecture. What You'll Learn & Do: Installation Walkthrough: Follow along with the official documentation process including the specific details for the DGX Spark where the ARM build is generated by default. Launch & Verification: We'll show you how to properly launch" [YouTube Link](https://youtube.com/watch?v=msGWby4ZBmU) 2025-12-09T00:35Z 195K followers, [--] engagements "This is What an AI Application Looks Like in the Future #nvidia #ai #jensenhuang #ces2026" [YouTube Link](https://youtube.com/watch?v=n_vuRmwHduM) 2026-01-10T17:01Z 201K followers, [----] engagements "How to Build an AI Agent: Course Introduction Learn to build autonomous AI agents that plan reason and solve complex problems. This introduction covers Agentic AI Foundations from core concepts to building your first working agent. We'll explore what makes AI systems "agentic" real-world applications and design principles that matter. What you'll learn in the full module: https://developer.nvidia.com/topics/how-to-build-an-ai-agent What Agentic AI is and how it differs from single-shot generation How agents plan reason and tackle multi-step problems autonomously Real-world examples across" [YouTube Link](https://youtube.com/watch?v=nr-Xu_ZRNKY) 2025-10-27T07:15Z 193K followers, [----] engagements "Turn Any PC into a SMPTE ST [----] Compliant Source with NVIDIA RivermaxDisplay Simplify your transition to SMPTE ST [----] with NVIDIA RivermaxDisplay. See how this software application turns any PC into a SMPTE ST [----] compliant source with NMOS support. Try NVIDIA RivermaxDisplay Today: https://nvda.ws/4aFxAnE Join the NVIDIA Developer Program: https://nvda.ws/3OhiXfl Read and subscribe to the NVIDIA Technical Blog: https://nvda.ws/3XHae9F #NVIDIARivermaxDisplay #SMPTEST2110 #NVIDIA" [YouTube Link](https://youtube.com/watch?v=pD1d1de231o) 2024-01-03T18:18Z 194K followers, [----] engagements "Digital Humans and AI Design with NVIDIA NIM on RTX PCs Microsoft Build [----] Discover how to create powerful agentic workflows for RTX AI PCsquickly efficiently and backed by NVIDIA NIM microservices. With NVIDIA NIM and RTX PCs and Workstations you can quickly build advanced AI workflows that are fast local and leverage the AI model innovations. We'll showcase and guide developers on the use of NVIDIA NIM microservices to kickstart AI experimentation. Learn more about AI on NVIDIA RTX PCs: https://developer.nvidia.com/ai-apps-for-rtx-pcs Access AI Models for RTX AI PCs:" [YouTube Link](https://youtube.com/watch?v=pJ12IMuWlAs) 2025-06-03T17:16Z 192K followers, [----] engagements "Training and Inferencing with NVIDIA AI Enterprise on VMware vSphere NVIDIA AI Enterprise is a comprehensive suite of software that's optimized certified and supported on VMware vSphere [--] and industry-leading servers. This end-to-end platform is designed to provide the easiest solution for enterprises to enable AI in their core data center. In this demo we'll show some examples of the features and capabilities of this stack as well as some example workloads such as multi-node AI training as well as multiple inferencing workloads. Learn more about NVIDIA AI Enterprise here:" [YouTube Link](https://youtube.com/watch?v=quWGKXAO8m8) 2021-09-15T18:57Z 194K followers, [----] engagements "NVIDIA Developer How To Series: Accelerating Recommendation Systems with TensorRT NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime that delivers low latency and high-throughput for deep learning inference applications. You can import trained models from every deep learning framework into TensorRT and easily create highly efficient inference engines that can be incorporated into larger applications and services. This video demonstrates the steps for using NVIDIA TensorRT to optimize a Multilayer Perceptron based Recommender System that is trained on the" [YouTube Link](https://youtube.com/watch?v=r4KG3dehF48) 2018-08-03T22:56Z 188K followers, [----] engagements "The Wonderful Capability of Reasoning #nvidia #ai #jensenhuang #ces2026 #nemotron #chatgpt nvidia nvidia" [YouTube Link](https://youtube.com/watch?v=rFINqM9--ro) 2026-01-09T22:01Z 201K followers, [----] engagements "NVIDIA Announces Aerial A Software-defined Stack for Telco Systems At Mobile World Congress Los Angeles NVIDIA unveiled Aerial a set of SDKs that enables GPU-accelerated software defined 5G wireless radio access network (RAN). Today NVIDIA Aerial provides two critical new SDKs: CUDA Virtual Network Functions (cuVNF) and CUDA Baseband (cuBB). These SDKs simplify building highly programmable and scalable software-defined 5G RANs using commercial off-the-shelf (COTS) servers with NVIDIA GPUs. https://news.developer.nvidia.com/cubb-software-defined-stack-for-telco/" [YouTube Link](https://youtube.com/watch?v=rObTbAijx1M) 2019-10-21T23:49Z 194K followers, [----] engagements "Unified Whole-Body Control for Humanoids with MaskedMimic from NVIDIA Project GR00T MaskedMimic is part of NVIDIA Project GR00T for enabling development of generalized humanoid robots. This research work contributes to GR00T-Control a suite of advanced motion planning and control libraries models policies and reference workflows for whole-body control. MaskedMimic is a single unified controller for physically simulated humanoids. Our system is capable of generating a wide range of motions across diverse terrains from intuitive user-defined intents. In this work we show several applications" [YouTube Link](https://youtube.com/watch?v=rePVn1xDWlo) 2024-12-04T00:31Z 193K followers, [----] engagements "SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillation Physically-simulated models for human motion can generate high-quality responsive character animations often in real-time. Natural language serves as a flexible interface for controlling these models allowing expert and non-expert users to quickly create and edit their animations. Many recent physics-based animation methods including those that use text interfaces train control policies using reinforcement learning (RL). However scaling these methods beyond several hundred motions has remained" [YouTube Link](https://youtube.com/watch?v=rfOiBqnL_OQ) 2024-07-28T21:00Z 196K followers, [----] engagements "Accelerate Your End-to-End AI Data Analytics and HPC Workflows with the NVIDIA NGC Catalog The NGC catalog is a hub of GPU-optimized AI high-performance computing (HPC) and data analytics software that simplifies and accelerates end-to-end workflows. Explore NGC: https://nvda.ws/3liOEYA With enterprise-grade containers pre-trained AI models and industry-specific SDKs that can be deployed on premises in the cloud or at the edge enterprises can build best-in-class solutions and deliver business value faster than ever before. Learn More: https://nvda.ws/3dpy6JC Contact Us:" [YouTube Link](https://youtube.com/watch?v=rj7pRJ9VAO4) 2021-04-14T17:30Z 194K followers, 17.9K engagements "Set Up a Data Flywheel to Self-Optimize AI Models and Agents The NVIDIA Data Flywheel Blueprint provides a systematic automated solution to refine and redeploy optimized models that maintain accuracy targets while lowering resource demands. This blueprint establishes a self-reinforcing data flywheel using production traffic logs and institutional knowledge to continuously improve model efficiency and accuracy. 00:00 - 01:20 Introduction and System Overview 01:21 - 02:10 Architecture and Orchestrator 02:11 - 03:00 Model Evaluation and Cost Optimization 03:01 - 04:00 Deployment and Cloud Setup" [YouTube Link](https://youtube.com/watch?v=rjLUm_7CDkM) 2025-07-23T16:07Z 191K followers, [---] engagements "How to Deploy Hugging Face Models Using a Single NVIDIA NIM This video walks you through how to deploy different LLMs from Hugging Face with a single LLM-agnostic NVIDIA NIM container. NIM microservices are your go-to for deploying the latest AI models from NVIDIA and the community quickly and reliably. They leverage NVIDIA TensorRT-LLM to accelerate and optimize inference alongside popular community backends like vLLM and SGLang to seamlessly deploy a massive range of community LLMs. Get ready for high-performance inference on NVIDIA GPUs with rapid reliable deployment for a broad range of" [YouTube Link](https://youtube.com/watch?v=s-5el_YillY) 2025-07-01T18:32Z 193K followers, [----] engagements "Building AI Agents at Scale: Get Started with DataRobot If youre serious about deploying AI agents into production you know its harder than the hype makes it sound. In this session well show you the roadblocks youll hit and how to overcome them as well as practical steps to build deploy and manage agents that actually work at enterprise scale. You will learn to: - Compare multiple frameworks powered by NVIDIA Nemotron models - Build fast and flexibly: Ingest data from ERP systems forecasts and external signals with your preferred frameworks NVIDIA NIM microservices and side-by-side testing in" [YouTube Link](https://youtube.com/watch?v=s9-excfOc00) 2025-08-29T01:25Z 199K followers, [----] engagements "Quantum Computing - Where We're Headed #GTC25 Fireside Chat Click to watch NVIDIA founder and CEO Jensen Huang host industry leaders in "Quantum Computing: Where We Are and Where Were Headed" a fireside chat from #gtc25 #quantumcomputing https://youtu.be/9XB-LsfpvCU NVIDIA founder and CEO Jensen Huang hosts industry leaders from Alice & Bob Atom Computing AWS D-Wave Infleqtion IonQ Microsoft Pasqal PsiQuantum Quantinuum Quantum Circuits QuEra Computing Rigetti and SEEQC to learn today's state of the art and what the future holds for useful quantum computing. These unprecedented fireside chats" [YouTube Link](https://youtube.com/watch?v=sLqlSeXR0Pc) 2025-05-21T14:01Z 197K followers, [----] engagements "Agentic Systems Revolutionized Software Programming at #nvidia #nvidia #ai #jensenhuang #ces2026 #aiagent #cursor" [YouTube Link](https://youtube.com/watch?v=sPfwkydY9l8) 2026-01-11T17:01Z 201K followers, [----] engagements "NVIDIA GPU Cloud with TITAN V Step by Step In this video Adam Beberg of NVIDIA provides step-by-step instructions for configuring and using NVIDIA GPU Cloud (NGC) with a desktop PC with an NVIDIA TITAN V. Adam demonstrates how to use the NGC user interface getting your PC configured using Docker and running PyTorch within an NGC container. Learn more: https://www.nvidia.com/en-us/gpu-cloud/deep-learning-containers" [YouTube Link](https://youtube.com/watch?v=sU-dLSWNTMc) 2018-03-07T21:23Z 199K followers, [----] engagements "NVIDIA DGX Station: Unboxing Watch this short video to see how easy it is to unbox a NVIDIA DGX Station https://nvda.ws/2V7zA02" [YouTube Link](https://youtube.com/watch?v=sW-zs6cCHs8) 2019-03-28T18:57Z 195K followers, 11.7K engagements "NVIDIA Networking: Learn the Basics of LinkX Cables and Transceivers The NVIDIA LinkX product lineup encompasses a wide range of interconnect solutions including cables and transceivers all aimed at maximizing the efficiency of data center operations. In this video we'll take a look at the various types of LinkX solutions on offer and highlight their features and abilities. To learn more about NVIDIA Data Center Networking for Administrators: https://academy.nvidia.com/en/training-by-topic/training_by_topic=10" [YouTube Link](https://youtube.com/watch?v=si7a7BcJzOc) 2023-08-14T10:22Z 190K followers, [----] engagements "Getting Started with Edge AI on NVIDIA Jetson: LLMs VLMs and Foundation Models for Robotics As Physical AI gains momentum edge computing is becoming increasingly critical for bringing intelligence directly to robots devices and real-world applications. This livestream invites developers to explore this expanding frontier by experimenting with open-source models on NVIDIA Jetson unlocking capabilities ranging from private coding companions to autonomous robots" [YouTube Link](https://youtube.com/watch?v=t2Ecuu2FdC8) 2025-12-05T19:14Z 196K followers, [----] engagements "What Happens During Inference When You Ask an LLM a Question When you ask an LLM a question a complex process called inference begins from token prediction to prefill and decode. In this video we break down exactly how it works how its evolving and how NVIDIA Dynamo accelerates each stage. Learn how disaggregated serving splits these steps across multiple GPUs for faster more efficient AI responses. Learn More: https://github.com/ai-dynamo/dynamo #LLM #NVIDIA #AIInference #DisaggregatedServing #TokenPrediction #AIExplained" [YouTube Link](https://youtube.com/watch?v=t7zEaz1407M) 2025-08-11T17:01Z 198K followers, [----] engagements "CUDA Toolkit 12.2: New Accelerated Computing and Security Enhancements Revealed Join CUDA experts for this in-depth overview of the CUDA [----] release. This update offers multiple features to help you reduce programming time create more efficient code and accelerate your applications. New features include support for NVIDIA Hopper GPU hardware architecture confidential computing to protect sensitive data and AI workloads heterogeneous memory management (HMM) and enhancements to MPS prioritization. 00:00 Introduction 04:03 CUDA [----] New Features (read the related TechBlog:" [YouTube Link](https://youtube.com/watch?v=tVd4-xL6EBU) 2023-07-06T19:00Z 198K followers, 11K engagements "Cosmos Cookbook Recipe: Reasoning for Human-Robot Interactions New Cosmos Cookbook recipe just dropped 🍽 Intbots recipe evaluates Cosmos Reason [--] on a set of targeted egocentric video tests designed to probe robot-relevant reasoning including: 📖 Human intent directed toward the robot 📖 Object motion relative to the robot 📖 Spatial relationships among multiple people 📖 Social context awareness (when not to engage) Try it yourself in the Cosmos Cookbook 👉 https://nvda.ws/4sji9ud Download Cosmos Reason [--] 👉 https://github.com/nvidia-cosmos/cosmos-reason2 #NVIDIACosmos" [YouTube Link](https://youtube.com/watch?v=u9sI_fTM_So) 2026-01-08T17:08Z 201K followers, [----] engagements "Create a RAG Chatbot Using NVIDIA AI Workbench In this video youll learn how to create your own retrieval-augmented generation (RAG) chatbot using NVIDIA AI Workbench. With this unified easy-to-use developer toolkit you can create test and customize pretrained AI models on NVIDIA RTX-powered AI workstations. Start your AI projects locally on workstations and scale them effortlessly to any data center or cloud with just a few clicks. Start your AI projects locally on workstations and scale them effortlessly to any data center or cloud with just a few clicks. Learn more about NVIDIA AI" [YouTube Link](https://youtube.com/watch?v=usnXmiBuUjc) 2024-10-10T17:24Z 191K followers, [----] engagements "Jetson AI Fundamentals - S1E1 - First Time Setup with JetPack Learn to set up the NVIDIA Jetson Nano Developer Kit for the first time with JetPack. This enables you to load Docker container applications for projects in Jetson AI Fundamentals. 00:00:00 - Introduction - Setting up Jetpack with Jetson Nano 00:00:33 - Jetson Nano Developer Kit 00:01:56 - Step 1: Flashing OS onto an SD card with a computer 00:08:18 - Step 2: Configure OS on Jetson Nano 00:10:53 - Setting SWAP to 4GB 00:13:44 - Conclusion Getting Started with AI on Jetson Nano - https://nvidia.com/dli Jetson AI Fundamentals -" [YouTube Link](https://youtube.com/watch?v=uvU8AXY1170) 2020-10-13T20:44Z 189K followers, 266.9K engagements "Getting Started with Accelerated XGBoost Check out this walkthrough on accelerating XGBoost with NVIDIA RAPIDS. Notebook link: https://bit.ly/3ENje9m" [YouTube Link](https://youtube.com/watch?v=v0IFKPUzW_s) 2025-02-21T20:47Z 198K followers, [----] engagements "NVIDIA GPU-accelerated Path Rendering - SVG Part [--] Mark Kilgard gives a short demonstration of NVIDIA's GPU-Accelerated Path Rendering this is part three of a three part series on the different ways to render SVG samples using the new NVIDIA GPU-Accelerated Path Rendering SDK Read more at http://developer.nvidia.com/nv-path-rendering" [YouTube Link](https://youtube.com/watch?v=vE0ZzqK1_dE) 2011-08-26T04:03Z 193K followers, [----] engagements "Techniques for Efficient and Reproducible Foundation Model Pre-Training Speaker: Dan Su Senior Research Scientist NVIDIA Dan Su provides an inside look at the Nemotron pre-training workflow sharing the key techniques for efficient and reproducible foundation model pre-training. This session covers the sophisticated curation of high-quality pre-training data the strategic data mixture and ordering strategy and the architectural evolution of Nemotron models. You'll learn how Nemotron aims to advance the field by open-sourcing its data and recipes and how innovative models like Nano V3 achieve" [YouTube Link](https://youtube.com/watch?v=vHCVNr0uX_k) 2025-12-14T17:01Z 196K followers, [----] engagements "How Accelerated Compute is Driving Scientific Discovery For [--] years weve been building CUDA-X libraries to accelerate discovery across scientific disciplines. Today with more than [---] libraries and frameworks CUDA-X is the foundation for some of the worlds fastest breakthroughs. In this video we demonstrate how CUDA-X is reshaping science today and creating the innovations needed to power the latest scientific discoveries. Join us at Supercomputing [----] to explore our latest contributions to scientific discovery. Check out the links below to learn more Life Science: Driving Toward" [YouTube Link](https://youtube.com/watch?v=vNhbqYtsH18) 2025-11-10T21:56Z 195K followers, [----] engagements "Reinvent Video Conferencing Content Creation & Streaming with AI Using NVIDIA Maxine NVIDIA Maxine is a GPU-accelerated SDK with state-of-the-art AI features for developers to build virtual collaboration and content creation applications such as video conferencing and live streaming. Developers from video conferencing content creation and streaming providers such as Notch Headroom Be.Live and Touchcast are using the Maxine SDK to create real-time video-based experiences easily deployed to PCs data centers or in the cloud. Learn more about NVIDIA Maxine: https://nvda.ws/3cSIRVC" [YouTube Link](https://youtube.com/watch?v=vh-noM8p8Ss) 2021-04-14T17:29Z 195K followers, [----] engagements "NVIDIA Variable Rate Shading Demonstrated in Autodesk VRED Last year we introduced Variable Rate Shading (VRS) with the Turing architecture. This new easy to implement rendering technique allows developers to vary the amount of processing power spent across the image to spend time and increase quality in the areas where they are most needed. Since virtual reality demands both a high performance and a high image quality VRS is the perfect fit for VR experiences especially when used in conjunction with eye tracking. For more information about VRS read the related Developer Blog" [YouTube Link](https://youtube.com/watch?v=w5V7cjbMpJ0) 2019-11-26T20:46Z 197K followers, [----] engagements "Shutterstock Unveils Generative AI [---] HDRi Built Using NVIDIA Picasso Shutterstock is using NVIDIA Picasso a foundry for building generative AI visual models to develop a variety of generative AI services to accelerate 3D workflows. At SIGGRAPH Shutterstock announced the first offering of these new services - [---] HDRi - to create photorealistic HDR environment maps to relight a scene. This demo shows how services built using NVIDIA Picasso can streamline environment map generation speeding up 3D workflows. #siggraph2023" [YouTube Link](https://youtube.com/watch?v=wW0wIjgYDHo) 2023-08-08T17:00Z 198K followers, [----] engagements "How to Deploy UFM in an OpenStack-Based Cloud Environment NVIDIA United Fabric Manager (UFM) is a key component of the InfiniBand fabric and the InfiniBand cloud. It provides a rich representational state transfer (REST) API for integrations with schedulers and cloud service provider (CSP) allocation systems. It also provides an infrastructure for security tenant isolation and tenant service-level agreements (SLAs). In this video were going to demonstrate an example of an OpenStack cloud integration. Well create a tenant and isolate its resources from other tenant resources using pkey" [YouTube Link](https://youtube.com/watch?v=wecvydZo4Wk) 2022-05-30T17:15Z 197K followers, [----] engagements "DGX Spark: Powering EPRIs AI Research 📱 Join EPRI a nonprofit research organization dedicated to advancing the science that powers a reliable affordable and resilient energy future. Discover how EPRI is innovating with NVIDIA DGX Spark to run advanced openweight models such as gptoss120b and Qwen3Embedding8B to drive a secure AI-powered document research assistant. Get started with DGX Spark: https://nvda.ws/4o2rDHn" [YouTube Link](https://youtube.com/watch?v=wvVNx07fQ2U) 2025-11-11T01:46Z 192K followers, [--] engagements "From Data to Deployment: Building European AI at Scale Improved audio version available here: https://youtu.be/KwSwxb2GBOM Moderated by tech futurist and AI expert Sarah Rojewsky join us live with technical experts from DeepL and NVIDIA as we explore the journey of building sovereign AI capabilities in Europe. Get a behind-the-scenes look at the technical and operational challenges of large-scale AI training and inference and discover the steps involved in developing robust AI products from choosing the right technology to model deployment. Our moderators will be on hand to answer questions" [YouTube Link](https://youtube.com/watch?v=x2hLfuGp7Fw) 2025-10-25T01:30Z 193K followers, [----] engagements "What is the most underrated research area in AI world foundation models 🤔 Ming-Yu Liu VP of Research at NVIDIA responds with insights into how it wont be humans who will benefit most from whats coming in [----]. Watch his key takeaways from #NeurIPS2025 👀" [YouTube Link](https://youtube.com/watch?v=xECboO8BxAA) 2025-12-05T15:01Z 195K followers, [----] engagements "Cinematic Climate Visualization with NVIDIA Omniverse #Climate simulations produce large amounts of inherently 3D data and yet the analysis is often limited to 2D projections. In addition to climate #scientists climate data also needs to be accessible by laypersons. Therefore intuitive photorealistic renderings are desirable. The NVIDIA Omniverse platform enables the fusion of large-scale scientific data with cinematic #rendering capabilities allowing for interactive exploration of complex climate phenomena. In this demo we'll show the power of Omniverse to visualize high-resolution climate" [YouTube Link](https://youtube.com/watch?v=xJtKd2bDS3M) 2020-11-11T19:19Z 193K followers, 41.8K engagements "Train AI Agents for CLI Tasks using Synthetic Data & Reinforcement Learning Nemotron Labs 📱 What if your computer-use agent could learn a new command-line tooloperating it safely without writing files or free-typing shell commands With NVIDIA Nemotron open models you can quickly train specialized agents for any CLI using synthetic data and reinforcement learningno usage logs required. Curious how it can be adapted for your own proprietary CLI environment Join us live for a developer-focused livestream. In this interactive livestream well cover: - A live demo: Generating synthetic training" [YouTube Link](https://youtube.com/watch?v=xLv5Pg4DG_Q) 2025-11-22T04:10Z 194K followers, [--] engagements "Distributed Inference 101: Monitoring Data Center Performance and Metrics Learn the fundamentals of monitoring performance of your Dynamo deployment at scale using Grafana dashboard. 📥 Explore and download https://github.com/ai-dynamo/dynamo #Inference #datacenter #AI #GTC25 ➡ Join the NVIDIA Developer Program: https://nvda.ws/3OhiXfl ➡ Read and subscribe to the NVIDIA Technical Blog: https://nvda.ws/3XHae9F" [YouTube Link](https://youtube.com/watch?v=xoBl4PYFEHU) 2025-03-18T18:46Z 193K followers, [----] engagements "Optimizing AI Agents with the NVIDIA NeMo Agent Toolkit Profiler NVIDIA NeMo Agent toolkit is an open source library that provides framework-agnostic profiling and optimization for production AI agent systems. With the NeMo Agent toolkit profiler developers can identify bottlenecks and leverage features for parallel tool calling performance and more. Download ➡ https://github.com/NVIDIA/NeMo-Agent-Toolkit #GenerativeAI #AgenticAI #AIAgents #RAG #NeMoAgentToolkit Generative AI Agentic AI AI Agents RAG NeMo Agent Toolkit NeMo Agent Toolkit Profiler" [YouTube Link](https://youtube.com/watch?v=xojqN11vuOE) 2025-07-10T22:55Z 197K followers, [----] engagements "Announcing NVIDIA Agent Intelligence Open-Source Toolkit NVIDIA Agent Intelligence toolkit is an open-source library for connecting evaluating and accelerating teams of AI agents. The NVIDIA Agent Intelligence toolkit simplifies development while optimizing and increasing the accuracy of full-stack complex agentic AI systems. AI agent AI agent #AIAgent #AIAgents" [YouTube Link](https://youtube.com/watch?v=xpQ3WE6ehxY) 2025-03-18T20:00Z 199K followers, [----] engagements "Ray Tracing Essentials Part 2: Rasterization versus Ray Tracing In Part 2: Basics of Ray Tracing NVIDIA's Eric Haines runs through the basics of rasterization and ray tracing. For decades rasterization also known as the Z-buffer has been the method of choice for rendering 3D images at interactive rates. This talk contrasts and compares it with ray tracing showing how the operations have a certain symmetry. More details about this video can be found here: http://bit.ly/nvrttalk2 You can watch the all of the videos in the series on this YouTube Playlist:" [YouTube Link](https://youtube.com/watch?v=ynCxnR1i0QY) 2020-02-27T22:06Z 192K followers, 163.1K engagements "Boost your #LLM apps 💡#NVIDIA AI Blueprint for Enterprise RAG The NVIDIA AI Blueprint for Enterprise RAG pipelines delivers accurate context-aware responses. Our walk-through launchable makes deployment easy" [YouTube Link](https://youtube.com/watch?v=ysvlhXxH580) 2025-07-22T19:28Z 198K followers, [----] engagements "How to Insert HTML Documents into a Multimodal Retriever Collection Using NVIDIA NIM Simplify your multimodal retrieval systems with NVIDIA NIM. This guide walks you through building a #VLM-based system with LangGraph plus #Llama models. Fast efficient and ideal for experimental pipelines. In this video you will learn how to insert a set of HTML documents into a multimodal retriever collection. 📝 Learn more about NIM: https://nvda.ws/431sEb4 📝 Find the source code in the NVIDIA Generative AI Examples repo on GitHub: https://nvda.ws/417z067 ➡ Join the NVIDIA Developer Program:" [YouTube Link](https://youtube.com/watch?v=z4g-juAaxRY) 2025-02-25T00:01Z 161K followers, [---] engagements "AI Startup Speeds Disease Research With Lab in the Loop BrainStorm Therapeutics a San Diego-based startup is accelerating the development of cures for neurological disorders using AI-powered computational drug discovery paired with lab experiments using organoids: tiny 3D bundles of brain cells created from patient-derived stem cells. This hybrid iterative method where clinical data and AI models inform one another to accelerate drug development is known as lab in the loop" [YouTube Link](https://youtube.com/watch?v=z8YWZBiHoBM) 2025-04-22T12:55Z 194K followers, [----] engagements "7 Questions with Jeremy Howard (Answer.ai fast.ai) on Open Source AI and Agents Jeremy Howard the founder of fast.ai and co-founder of Answer.ai shares his thoughts on the future of open source AI the rise of AI agents and why humans should stay at the center of innovation. Interview took place after his keynote at the PyTorch Conference [----] in San Francisco CA" [YouTube Link](https://youtube.com/watch?v=zDkHJDgefyk) 2025-10-24T21:23Z 190K followers, [---] engagements "Universal Scene Description (OpenUSD): Composition and Layering Developers are using Universal Scene Description (OpenUSD) to push the boundaries of 3D workflows. In the second installment of this series on the superpowers of OpenUSD that developers can harness learn how the OpenUSD composition engine enables sparse non-destructive assembly of data from multiple sources so you can create complex scenes with ease. For an introduction to OpenUSD watch the first video in the series: https://www.youtube.com/watchv=1RnTSZK9SwM Learn about the latest USD advancements: usd.nvidia.com Learn about the" [YouTube Link](https://youtube.com/watch?v=zRyKI55qEZY) 2023-06-29T17:35Z 197K followers, 362.7K engagements "Cosmos Cookbook Recipe: Sports Video Generation with LoRA Post Training This NVIDIA Cosmos Cookbook serves as a practical guide to the Cosmos open models offering step-by-step workflows technical recipes and concrete examples for building adapting and deploying WFMs. Todays recipe shows you how to generate and build realistic physically accurate and rule-aware sports videos with smooth player motions using LoRA post-trained on Cosmos Predict [---]. Read the full recipe 📖 https://nvidia-cosmos.github.io/cosmos-cookbook/recipes/post_training/predict2_5/sports/post_training.html Download Cosmos" [YouTube Link](https://youtube.com/watch?v=zTWjI7Z7-Q4) 2025-12-03T21:01Z 195K followers, [----] engagements "Introduction of disaggregated serving in TensorRT-LLM Learn from our experts about disaggregated serving in TRT-LLM. You will learn about the potential benefits of disaggregated serving about how to run disaggregated serving with TensorRT-LLM and about current performance for popular models" [YouTube Link](https://youtube.com/watch?v=zUb_VmKwIFA) 2025-09-18T00:11Z 190K followers, [----] engagements "Top 5: GPU-Accelerated Supercomputers & More In this weeks edition of the Developer Top [--] we revisit the top developer stories of the week. From a new GPU-accelerated supercomputer in France new AI NGC containers to cutting edge medical research. https://nvda.ws/2RRvmfS" [YouTube Link](https://youtube.com/watch?v=zYVoD2P8ZUA) 2019-01-26T00:54Z 194K followers, [----] engagements "Enhance Your AI Agent with Data Flywheels Using NVIDIA NeMo Microservices NVIDIA NeMo microservices provide an end-to-end platform for building data flywheels enabling enterprises to continuously optimize their AI agents with the latest information. AI agent AI agents NVIDIA NeMo Data flywheels agentic ai data flywheel #AIAgent #AIAgents #NVIDIANeMo #AgenticAI" [YouTube Link](https://youtube.com/watch?v=zguiPdN1u_s) 2025-04-23T16:41Z 198K followers, [----] engagements "Jetson AI Fundamentals - S1E2 - Hello Camera Get started with the camera widgets in the free DLI course "Getting Started with AI on Jetson Nano". You'll learn to securely log in to your NVIDIA Jetson Nano and launch the course from a Docker container. 00:00:00 - Introduction - Setting up Docker container and webcam for DLI course 00:00:28 - DLI course overview 00:01:04 - Getting Started with AI on Jetson Nano 00:02:55 - Headless device mode 00:08:26 - Inside the container 00:09:30 - Inside Jupyter lab environment 00:14:28 - Conclusion Getting Started with AI on Jetson Nano -" [YouTube Link](https://youtube.com/watch?v=zsjcSapzUfU) 2020-10-07T02:32Z 189K followers, 154.6K engagements Limited data mode. Full metrics available with subscription: lunarcrush.com/pricing
@nvidiadeveloper NVIDIA Developer
NVIDIA has been releasing various tools and platforms to support AI development, including the NVIDIA NIM for deploying generative AI, NVIDIA Nemo Agent for creating AI agents, and DGX Cloud for AI computing. The company has also been highlighting its Jetson series, including the AGX Orin and Nano developer kits, for building AI-powered robots and devices. Additionally, NVIDIA has been showcasing its advancements in areas like humanoid robotics, quantum computing, and accelerated data science.
Engagements: [------] #
- [--] Week [-------] -21%
- [--] Month [---------] +9.60%
- [--] Months [---------] -17%
- [--] Year [----------] +27%
Mentions: [--] #
- [--] Week [---] +30%
- [--] Month [---] -1.20%
- [--] Months [---] +22%
- [--] Year [---] +231%
Followers: [-------] #
- [--] Week [-------] +0.50%
- [--] Month [-------] +1.50%
- [--] Months [-------] +11%
- [--] Year [-------] +26%
CreatorRank: [-------] #
Social Influence
Social category influence stocks #2907 technology brands 100% finance 2.06% events 1.55% social networks 1.55% travel destinations 1.55% countries 1.03% nfts 0.52%
Social topic influence ai #2925, $nvda #56, how to 21.65%, systems #1686, agentic #18, llm #688, inference #91, gpu #365, nvda #555, build a #1563
Top accounts mentioned or mentioned by @esimstudios @kevinstratvert @huggingface @nvidiaomniverse @engineerprompt @marktechpost @kennygunderman @ltx_model @technology_now
Top assets mentioned NVIDIA Corp. (NVDA) Alphabet Inc Class A (GOOGL) Microsoft Corp. (MSFT) IonQ, Inc. (IONQ) FilesCoins Power Cu (FILECOIN)
Top Social Posts
Top posts by engagements in the last [--] hours
"DGX Spark Live: Installation & First Run Guide for Robotics Developers This is the essential live session for robotics developers ready to leverage NVIDIA Isaac Sim on the powerful DGX Spark platform. We'll guide you through the initial steps to get your high-fidelity simulation environment up and running on the aarch64 architecture. What You'll Learn & Do: Installation Walkthrough: Follow along with the official documentation process including the specific details for the DGX Spark where the ARM build is generated by default. Launch & Verification: We'll show you how to properly launch the"
YouTube Link 2025-12-09T01:03Z 201K followers, [----] engagements
"NVIDIA DGX Spark Lights up CES [----] Show Floor One year after the debut of Project Digits DGX Spark has transformed from concept to reality and is now available from NVIDIA and OEM partners. See it in action at #CES2026 where enterprise creative and agentic AI meet the edge of innovation. #SparkSomethingBig https://www.nvidia.com/en-us/events/ces/"
YouTube Link 2026-01-15T00:00Z 201K followers, 796.5K engagements
"What's the culture like at #nvidia #ai #softwaredevelopment #coding"
YouTube Link 2025-08-27T21:00Z 201K followers, 33.8K engagements
"Introduction to Physical AI & Robotics at NVIDIA This session will provide a high-level overview of NVIDIA's comprehensive approach to robotics emphasizing how our open models frameworks libraries and hardware are empowering developers to build intelligent and autonomous systems. Attendees will learn about the fundamental components of NVIDIA's robotics ecosystem"
YouTube Link 2025-12-20T17:01Z 201K followers, [----] engagements
"🎁 For the Innovator Who Has Everything (Except This) . an NVIDIA DGX Spark 🎁 Compact capable and efficient -- NVIDIA DGX Spark is the perfect companion for anyone ready to build prototype or refine their AI ideas. Give the gift that doesnt just keep on giving -- it keeps innovating. ✨ Shop now to #SparkSomethingBig: https://marketplace.nvidia.com/en-us/enterprise/personal-ai-supercomputers/dgx-spark/"
YouTube Link 2025-12-09T23:44Z 201K followers, 29.7K engagements
"Accelerating Applications with Parallel Algorithms CUDA C++ Class Part [--] Welcome to NVIDIAs Modern CUDA C++ Programming Class. You will learn how to program on the GPU using NVIDIAs latest programming tools. This series is for C++ developers who want to use the GPU effectivelywhether youre new to CUDA and want the fastest path from hello world to real acceleration or youre an experienced CUDA programmer ready to modernize your code with the latest best practices. If you already know C++ and want to write clean efficient idiomatic GPU code this course is for you. This video is part of a"
YouTube Link 2025-11-06T22:08Z 201K followers, 34.5K engagements
"AI Warehouse: AMR Visual Navigation with Isaac Sim & Isaac ROS Autonomous machines are forecasted to dramatically increase the efficiency of warehouses factories and other industrial environments. NVIDIA Isaac ROS GEMs enable novel applications by empowering robots to intelligently perceive complex 3D environments. In this video we showcase a camera-based navigation pipeline in which a robot uses NVIDIAs GPU-accelerated visual SLAM algorithm (https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_visual_odometry) to find its location in the world. GPU-accelerated real-time 3D scene reconstruction"
YouTube Link 2022-03-22T16:59Z 201K followers, 26.8K engagements
"Turn Text Into a Knowledge Graph with 70B LLM on DGX Spark Looking to run local GraphRAG or other graph analytics use cases With DGX Spark you can prepare your local text files for graph use cases at your desk. In this demo a Llama-3.1-70B model served by Ollama runs locally in DGX Sparks 128GB of unified memory. After uploading local biomedical research papers into the LLM the model extracts nodes and relationships that are embedded into a knowledge graph. By processing entire documents at once the knowledge graph retains critical long-range relationships that make GraphRAG and other graph"
YouTube Link 2025-10-27T15:30Z 201K followers, 37.9K engagements
"Getting Started with CUDA and Parallel Programming NVIDIA GTC [----] Session Join one of CUDA's architects on a journey through the concepts of parallel programming: how it works why it works why it's not working when you think it should be working and in particular why it's different on a GPU from a CPU. We'll look at different approaches to parallel programming in CUDA and how to take advantage of the hardware it runs on. This is the next episode in what has become a series looking at the way that CUDA and the GPU work and why they work this way. This session will focus on how to think about"
YouTube Link 2025-04-10T21:28Z 201K followers, 33.6K engagements
"Interviewing a Robot at #GTC25 #nvidia #robotics #machinelearning"
YouTube Link 2025-03-18T04:16Z 201K followers, 165.3K engagements
"ArtisanGS: Interactive Tools for Gaussian Splat Selection with AI and Human in the Loop ArtisanGS is an interactive toolkit for 3D Gaussian Splat scenes that turns a few 2D masks into editable 3D object selections using Cutie-based multiview tracking and fast splat aggregation with rich tools for manual correction. It delivers competitive segmentation quality in about [--] seconds without perscene training and enables downstream workflows like local videodiffusion editing autoorientation and direct physics simulation on splat objects. Authors: Clement Fuji Tsang Anita Hu Or Perel Carsten Kolve"
YouTube Link 2026-02-13T20:00Z 201K followers, [----] engagements
"Getting Started with the NVIDIA Jetson AGX Thor Developer Kit for Physical AI The NVIDIA Jetson AGX Thor Developer Kit is the ultimate developer resource for building the future of humanoid robotics and next-generation physical AI applications. Powered by the advanced NVIDIA Blackwell GPU and [---] GB of memory it delivers up to [----] FP4 TFLOPS of AI performanceall within a [---] W power envelope. This video walks you through how to power on and set up the device for the first time (first boot tutorial). It also covers key features specifications and components and the latest NVIDIA workflows"
YouTube Link 2025-08-25T15:01Z 201K followers, 65.8K engagements
"DGX Spark Live: Developer Q&A Got questions about DGX Spark You're not alone With any new product launch there are always a lot of details to uncover. In this special livestream we're diving deep to answer your most pressing questions about the new DGX Spark system. We'll answer your questions to give you a complete understanding of: - Why was DGX Spark created - Who was it created for - What are ideal use cases for DGX Spark Most importantly we'll help you figure out the big question: Should you have a DGX Spark on your desk Tune in ask your questions live and get the clarity you need. Learn"
YouTube Link 2025-10-24T18:39Z 201K followers, 378.3K engagements
"DGX Spark: Observing the Universe at Light Speed Tired of the perpetual 'dark sky vs. glowing screen' battle while doing visual astronomy That bright phone or tablet running SkySafari ruins your night vision and focus. We're showing off a custom AI agent running on DGX Spark that lets you have a natural voice-activated conversation with your telescope no more fumbling with apps in the dark. Join us for a deep dive and live demonstration of the full stack that allows an open-source GPT model (GPT-OSS:20b) to control a high-end mount (10micron GM2000) for astronomical objects and satellites."
YouTube Link 2025-11-01T06:30Z 201K followers, 510.3K engagements
"Intro to NVIDIA Cosmos with Ming-Yu ft. Superintelligence Cosmos Labs Join us for an exclusive deep dive into NVIDIA Cosmos with its creator Ming-Yu Vice President of Research at NVIDIA alongside your favorite technology advocate Superintelligence. In this conversation we unpack the motivation behind Cosmos the science and research powering its open models and the long-term vision shaping its evolution. Learn how Cosmos is redefining physical AI where these models are headed next and how developers and researchers can start using Cosmos today. What youll learn in this session: - Why NVIDIA"
YouTube Link 2026-01-28T14:05Z 201K followers, 107K engagements
"Intro to NVIDIA Cosmos with Ming-Yu ft. Superintelligence Watch an exclusive deep dive into NVIDIA Cosmos with its creator Ming-Yu Vice President of Research at NVIDIA alongside your favorite technology advocate Superintelligence. Watch the livestream 👉 https://www.youtube.com/watchv=x2Q7kkGsDOk Explore the Cosmos Cookbook 👉 https://nvda.ws/4k7EmaN Register for the hackathon 👉 https://nvda.ws/4qP4sly #NVIDIACosmos #WorldFoundationModels #CosmosCookbook #PhysicalAI"
YouTube Link 2026-02-12T20:10Z 201K followers, [----] engagements
"DGX Spark Live: Sovereign Data Solutions With GT Edge AI Join the NVIDIA AI Developer livestream featuring an early access partner GT Edge AI for a hands-on look at why they are building hybrid edge intelligence on the DGX SPARK platform building for users that need to work with sovereign data in a secure environment. Learn why GT Edge AI is building its OS on SPARK covering agent frameworks hybrid deployment patterns and how to extend AI pipelines to the edge with both cloud hosted and local models for inference while keeping data local. GT Edge AI are building their product with the Dell"
YouTube Link 2026-01-21T07:46Z 201K followers, [----] engagements
"How to Self-Host LLMs and Multi-Modal AI Models with NVIDIA NIM in [--] Minutes -NVIDIA NIM is containerized AI inference software that makes it simple to deploy production-ready model endpoints accelerated by NVIDIA GPUs anywhere you need them. Tap into the latest AI foundation modelslike NVIDIA Nemotron Qwen DeepSeek R1 Meta Llama and more ready for secure private deployment in [--] minutes or less on NVIDIA-accelerated workstations datacenter or cloud environments. Join Neal Vaidya developer advocate at NVIDIA for a demo on how to privately deploy LLMs and multi-modal AI models with NVIDIA NIM"
YouTube Link 2024-07-29T20:30Z 201K followers, 45.5K engagements
"Intelligent Query Routing using vLLM Semantic Router #nvidia #machinelearning #vllm #ai"
YouTube Link 2026-01-12T23:27Z 201K followers, [----] engagements
"Build Reasoning Agents For Physical AI Cosmos Labs Learn how to apply Cosmos Cookbook recipes for physical AI reasoning using Cosmos Reason in this hands-on technical deep dive. In this session we explore how egocentric or first-person reasoning allows robots to understand social cues and physical laws leading to safer and more natural humanrobot interactions. We also show how fine-tuning Cosmos Reason with domain-specific data such as heavy traffic improves understanding in complex dynamic environments. Similar methods can be used to filter synthetic data and build visuallanguage agents for"
YouTube Link 2026-01-28T05:48Z 201K followers, [----] engagements
"How To Adapt AI for Low-Resource Languages with NVIDIA Nemotron Join NVIDIA and Dicta to explore how Sovereign AI initiatives can empower local innovation through advanced language model adaptation. This session highlights how Dicta built a Hebrew reasoning model using the Nemotron architecture and NVIDIAs NeMo frameworkshowing how open models transparent data and efficient training tools can accelerate AI development for lowresource languages. Well cover the main practices for customizing foundation models managing data quality and safety and deploying domainspecific reasoning systems. The"
YouTube Link 2026-01-31T21:32Z 201K followers, [----] engagements
"DGX Spark Live: Powering Higher Education and Research Join NVIDIA and Stanford researchers for an exciting look at Biomni a next-generation biomedical AI agent transforming how labs explore data and design experiments. Discover how Biomni running on NVIDIA DGX Spark turns complex biomedical workloads into fast automated insights giving teams a powerful launchpad for rapid experimentation evaluation and seamless scaling"
YouTube Link 2026-02-11T07:39Z 201K followers, [----] engagements
"Agentic AI Solutions with CrewAI and Nemotron Nemotron Labs Join this exclusive livestream for a practical deep dive with CrewAI CEO Joaoa Moura exploring real-world agentic streaming and the latest breakthroughs using Nemotron open models in production frameworks for top brands. What developers will learn: How CrewAI integrates Nemotron for rapid modular agent workflows powering everything from simple task automation to complex multi-agent orchestration. Field-tested tips and best practices on building scalable agents with insights pulled directly from CrewAIs deployments in enterprise"
YouTube Link 2026-01-05T20:58Z 201K followers, [----] engagements
"Quantum Computing: Where We Are and Where Were Headed NVIDIA GTC [----] Fireside Chat NVIDIA founder and CEO Jensen Huang hosts industry leaders from Alice & Bob Atom Computing AWS D-Wave Infleqtion IonQ Microsoft Pasqal PsiQuantum Quantinuum Quantum Circuits QuEra Computing Rigetti and SEEQC to learn today's state of the art and what the future holds for useful quantum computing. These unprecedented fireside chats bring together the whole quantum computing community for an overview of this exciting technology. Panelists: Ben Bloom Founder and CEO Atom Computing Alan Baratz CEO D-Wave Krysta"
YouTube Link 2025-04-09T16:15Z 201K followers, 232.8K engagements
"Getting Started with the NVIDIA DGX Spark NVIDIA DGX Spark powered by the NVIDIA GB10 Grace Blackwell Superchip delivers one petaFLOP of AI performance in a power-efficient compact form factor. With the NVIDIA AI software stack preinstalled and [---] GB of memory developers can prototype fine-tune and inference the latest generation of reasoning AI models from DeepSeek Meta NVIDIA Google Qwen and others with up to [---] billion parameters locally. This video walks you through how to power on and set up the device for the first time (first boot tutorial). Learn more: build.nvidia.com/spark"
YouTube Link 2025-10-14T23:23Z 201K followers, 71.8K engagements
"The Breakthrough Moment for Physical AI Powered by NVIDIA Cosmos Learn how to get more out of NVIDIA Cosmos with tips straight from the authors behind our Cosmos Cookbook recipes. Watch the livestream 👉 https://www.addevent.com/calendar/ss55fmjpm04t Explore the Cosmos Cookbook 👉 https://nvda.ws/4k7EmaN Register for the hackathon 👉 https://nvda.ws/4qP4sly #NVIDIACosmos #WorldFoundationModels #CosmosCookbook #PhysicalAI"
YouTube Link 2026-02-09T19:01Z 201K followers, [----] engagements
"How to Write a CUDA Program - Parallel Programming #gtc25 #CUDA Click to watch the full session from GTC25: "How to Write a CUDA Program - The Parallel Programming Edition" https://youtu.be/GmNkYayuaA4 Join one of CUDA's architects on a journey through the concepts of parallel programming: how it works why it works why it's not working when you think it should be working and in particular why it's different on a GPU from a CPU. We'll look at different approaches to parallel programming in CUDA and how to take advantage of the hardware it runs on. This is the next episode in what has become a"
YouTube Link 2025-04-22T21:48Z 201K followers, 21.3K engagements
"Vibe Coding Demo on DGX Spark See how we build an AI app on DGX Spark that finds uplifting news and the best pet videosbecause innovation should inspire and make you smile. Using Continue.dev we demo vibe coding with agentic workflows that spark creativity and accelerate your AI journey. Learn more: build.nvidia.com/spark"
YouTube Link 2025-10-07T21:16Z 201K followers, 12.6K engagements
"Performance Analysis with NVIDIA Nsight Systems Timeline CUDA Developer Tools In this episode of the CUDA Developer Tools tutorial series Eyal Soha senior software engineer at NVIDIA introduces code performance analysis using the Timeline View in NVIDIA Nsight Systems. Basic knowledge of C++ CUDA programming is recommended. Highlights include: Explore the Nsight Systems timeline a powerful tool for analyzing GPU performance. Learn how the Timeline View helps you understand code processes and uncover optimization opportunities. Get an overview of the timeline interface and how to navigate the"
YouTube Link 2023-10-27T16:00Z 201K followers, 17K engagements
"Build End-to-End Multimodal AI Agents for Document and Video Intelligence With NVIDIA Nemotron This video presents a unified approach to multimodal and document intelligence using NVIDIA Nemotron models. Implement agent-ready workflows by combining two specialized Nemotron models: [--] Nemotron Nano [--] VL for Reasoning: This 12B model provides multimodal intelligence agents need to to perform sophisticated cross-page reasoning on charts and tables grounding answers directly in the data. It also leverages a new Efficient Video Sampling (EVS) capability that generates 4x less tokens while"
YouTube Link 2025-10-28T17:59Z 201K followers, [----] engagements
"What is CUDA Tile Join Stephen Jones CUDA Architect for a clear and insightful introduction to a paradigm-shifting technology: CUDA Tile. If you're wondering how modern GPU programming is evolving this video provides the essential foundation. We break down the core concepts of CUDA Tile explain why it's a necessary development for peak performance and discuss how it fundamentally changes the way we think about parallel computation. Speaker & Resources: 👤 Speaker: Stephen Jones CUDA Architect 📖 Official CUDA Tile Documentation: http://docs.nvidia.com/cuda/tile-ir 💡 Explore CUDA Tile:"
YouTube Link 2025-12-19T19:09Z 201K followers, [----] engagements
"Chat with the Nemotron Team Office Hours Nemotron Labs Got questions about Nemotron Want to give direct feedback to the team behind the models Ask our Nemotron expert in this Nemotron Lab office hours about: - Our Nemotron open model family with open datasets and open techniques - How to build AI agents including report generator agent RAG agent bash computer use agent and training with synthetic data & reinforcement learning from our recent tutorial livestreams This is your chance to get hands-on support ask questions and explore the Nemotron models with the experts who built them. Whether"
YouTube Link 2026-01-21T22:20Z 201K followers, [---] engagements
"Step-by-Step Installation of NVIDIA Virtual GPU Software on VMware vSphere Learn the entire process for getting NVIDIA Virtual GPU software running on VMware vSphere--whether youre using vSphere for Graphics/VDI workloads or AI workloads with NVIDIA AI Enterprise. NVIDIA Senior Solutions Architect Lee Bushen walks you through the following steps: - Downloading the vGPU or NVIDIA AI Enterprise software components - Server preparation for vGPU - Installing the GPU Manager on the ESXi host - Removing the GPU Manager for an vGPU software upgrade - Configuring vCenter for vGPU profiles -"
YouTube Link 2024-10-11T18:21Z 201K followers, 34.6K engagements
"DGX Spark: Accelerated cuPyNumeric on your Desktop Cluster NVIDIA cuPyNumeric a multi-node multi-GPU NumPy-compatible library is ideal for domain scientists and researchers to scale their Python and NumPy program to multi-GPU multinode without having to write complex parallel computing code like MPI. Well demonstrate how to use [--] DGX Spark systems as a desktop cluster to accelerate cuPyNumeric locally. Get started with DGX Spark: https://nvda.ws/4o2rDHn"
YouTube Link 2025-11-06T16:22Z 201K followers, [----] engagements
"Under the Hood of Open Models: Building Scalable MultiAgent Architectures Nemotron Labs Join for a live walkthrough of open models datasets and tools that help developers design deploy and iterate on multiagent AI systems at scale. Learn how to use open resourcestraining recipes open datasets and reinforcement learning environmentsinto your existing stacks to speed up prototyping evaluation and production workflows. During the livestream NVIDIA experts will cover: - How to adapt open models and data for specialized agent workflows - New tools and libraries that streamline reinforcement"
YouTube Link 2025-12-12T04:35Z 201K followers, [----] engagements
"New Nemotron Open-Source Models and Datasets #NVIDIAGTC Develop specialized AI agents with new NVIDIA Nemotron vision RAG and guardrail models announced at GTC DC. Check out the tech blog for resources on getting started. #Nemotron #SpecializedAI #GTC"
YouTube Link 2025-10-28T18:06Z 201K followers, [----] engagements
"NVIDIA Llama-3.1-Nemotron Ultra: The Best Open Model Built for Reasoning & AI Agents Discover NVIDIA's Llama-3.1-Nemotron Ultra the 253B parameter open-weight model designed specifically for advanced reasoning and enterprise AI agents. Skip the chatbots and build AI that can solve complex problems with step-by-step reasoning"
YouTube Link 2025-05-07T15:12Z 201K followers, [----] engagements
"How to Deploy NVIDIA Nemotron Nano 4B with vLLM on Colab Reasoning & Tool Calling Demo Learn how to deploy the NVIDIA Llama Nemotron Nano 4B reasoning model on Google Colab using vLLM and an NVIDIA L40 GPU. This step-by-step demo covers system and user prompts for reasoning (on/off modes) tool calling and real-world use cases like coding scientific tasks and instruction followingideal for edge AI agents. Key features include: Leading reasoning and agentic AI accuracy for various benchmarks including GPQA-Diamond AIME [----] IFEval BFCL LiveCodeBench and MBPP 50% higher throughput compared to"
YouTube Link 2025-05-22T00:30Z 201K followers, [----] engagements
"How to Use Nemotron [--] Nano: Connecting OpenAI API Endpoint and Build LangChain Agents Learn how to use NVIDIA Nemotron [--] Nano the advanced mixture-of-experts (MoE) model built on a hybrid Mamba-Transformer architecture. In this step-by-step tutorial we show you how to deploy and interact with Nemotron [--] Nano using OpenRouters API then build powerful LangChain agentsfrom single interactions to full multi-agent research systems. What Youll Learn: ✅ How to connect Nemotron [--] Nano through an OpenAI-compatible API ✅ The difference between thinking mode on/off and when to use them ✅ Building your"
YouTube Link 2025-12-15T14:00Z 201K followers, [----] engagements
"Build a Custom AI Agent With NVIDIA Nemotron RAG Models This hands-on tutorial guides you through creating an Agentic Retrieval-Augmented Generation (RAG) pipeline using NVIDIA's open Nemotron models for embedding and reranking. 🔍 What You'll Learn in this RAG Tutorial: [--] NVIDIA Nemotron RAG Models: Access and use open Nemotron RAG models from Hugging Face for retrieval. [--] Custom RAG Pipeline: Build a full workflow in LangChain with data loading chunking and a Contextual Compression Retriever. [--] Agent Development: Use Nemotron Nano [--] 9B as your LLM and connect retrieval tools into an agent"
YouTube Link 2025-10-28T17:59Z 201K followers, [----] engagements
"Building AI Agents at the Edge with NVIDIA Llama Nemotron Nano 4B Want to build an AI agent running on-premises This video walks you through how to code (and vibe code) a local agent running NVIDIA Llama Nemotron Nano 4B wrapped in a custom React UI built with Cursor AI and FAISS Vector Database. 00:00 Introduction 00:26 Llama Nemotron Nano 4B 06:13 UI Demo 11:23 Code 19:27 Outro #LLM #SLM #LlamaNemotron #AIagent #cursorAI #faiss Demo source code: https://github.com/NVIDIA/GenerativeAIExamples/tree/main/community/chat-llama-nemotron AI-generated summary of video concepts: ### Introduction"
YouTube Link 2025-06-09T20:49Z 201K followers, [----] engagements
"How to Build a Document Processing Pipeline for RAG with Nemotron Learn to build a document pipeline that turns PDFs into cited answers with NVIDIA Nemotron. Traditional Retrieval-Augmented Generation (RAG) is effective for regular text but often fails with real-world documents that include tables figures and nested tables. When these complex document structures are reduced to simple text strings it causes "linearization loss". This means the helpful structure needed to understand the documents is removed which can lead to problems like not knowing which column a row value belongs to"
YouTube Link 2026-02-04T16:49Z 201K followers, [----] engagements
"Post-Training Alignment and Advanced Reasoning with Nemotron Speaker: Oleksii Kuchaiev Director of Applied Research NVIDIA Post-training is the foundation for turning a base large language model into an aligned capable assistant boosting features like reasoning tool-calling and autonomy. Every AI assistant application relies on effective post-training which is evolving as fast as new capabilities like multi-step task solving and long-horizon tasks are being developed. At this research-focused talk by Oleksii Kuchaiev from the Nemotron models post-training team youll learn whats new and whats"
YouTube Link 2025-12-12T17:38Z 201K followers, [----] engagements
"Build a RAG Agent with NVIDIA Nemotron Nemotron Labs Curious about designing AI agents using RAG Join us for a developer-focused livestream that takes you from first principles to code exploring the "why" and "how" of building agentic AI using practical examples. Well cover step by step: - A live demo: building and running a simple agentic RAG pipeline in a coding window with Nemotron NVIDIAs open reasoning model - How to connect tools use memory and see agentic behavior in action - Your questions answered throughout with relatable explanations and no prior experience needed By the end you'll"
YouTube Link 2025-09-01T21:59Z 201K followers, [----] engagements
"Build an AI Agent for Report Generation with NVIDIA Nemotron on OpenRouter Nemotron Labs Curious about building AI agents This livestream will introduce you to building a reporting generation agent using NVIDIA Nemotron a family of open models with open datasets and open weights through an OpenRouter endpoint. Step-by-step well cover: - Understanding of the four core considerations of any AI agent - A working document generation agent that can research and write reports - Knowledge of how to build agents using LangGraph and OpenRouter - Your own customizable agent ready to share as a NVIDIA"
YouTube Link 2025-09-15T21:58Z 201K followers, [----] engagements
"Building Faster and Smarter AI Systems with Nemotron Speaker: Bryan Catanzaro VP of Applied Deep Learning Research NVIDIA Learn how were redefining AI development with Nemotron our open platform that brings together models data libraries and research to accelerate smarter faster AI. Bryan Catanzaro walks through why were building AI how Nemotron is designed to plug into existing workflows rather than replace them and how principles like faster AI is smarter AI shape everything from model architecture and scaling laws to deployment on real-world accelerated systems. ➡ Learn more:"
YouTube Link 2025-12-11T22:09Z 201K followers, [----] engagements
"Build Culturally-Aware LLM Guardrails With Nemotron Safety Guard Current safety models often miss the subtle cultural and linguistic cues needed to moderate global content effectively. A phrase that seems harmless in one language may imply harm in another especially when tone idioms or slang are involved. The Llama [---] Nemotron Safety Guard 8b v3 model tackles this challenge by introducing a multilingual moderation system trained on the culturally adapted dataset: Nemotron Safety Guard dataset v2. Supporting nine languages it uses LLM-driven techniques to detect nuanced intent and"
YouTube Link 2025-10-28T18:01Z 201K followers, [----] engagements
"Build Vision AI Pipelines Faster with NVIDIA DeepStream Inference Builder The DeepStream Inference Builder part of NVIDIA's DeepStream SDK is a toolkit for building real-time AI-powered streaming analytics pipelines using video audio or image data. Inference Builder turns AI model ideas into production-ready services with ease. Developers can now go from YAML config to deployment in minutesautomating data flow preprocessing model execution and API integration. This video walks through how to use DeepStream Inference Builder with a quick example. Learn more about DeepStream SDK"
YouTube Link 2025-09-23T16:01Z 201K followers, [----] engagements
"Jensen Huang Shows Off the New #NVIDIA DGX Spark Personal AI Computer #computex2025 #dgxspark #ai"
YouTube Link 2025-05-23T15:36Z 201K followers, 19K engagements
"DIY Autonomous Car Racing with NVIDIA Jetson Interested in seeing AI races in person Visit our amAIzing race track to watch or compete as DIY autonomous cars battle it out to the finals. The DIY Robocars community will be revving up their RC-sized cars at NVIDIAs GTC [----] in San Jose. Attendees are invited to root for their favorite team and learn about the cutting-edge AI technology in action. Victors and runner-ups will be awarded prizes In this video we talked to Chris Anderson Founder of DIY RoboCars and with members of the UCSD robotics club that participated in the [----] DIYRobocars"
YouTube Link 2020-01-31T18:31Z 201K followers, 306.1K engagements
"DGX Spark: Powering EPRIs AI Research Join EPRI a nonprofit research organization dedicated to advancing the science that powers a reliable affordable and resilient energy future. Discover how EPRI is innovating with NVIDIA DGX Spark to run advanced openweight models such as gptoss120b and Qwen3Embedding8B to drive a secure AI-powered document research assistant. Get started with DGX Spark: https://nvda.ws/4o2rDHn"
YouTube Link 2025-11-14T18:09Z 201K followers, [----] engagements
"NVIDIA Cosmos Cookbook: Tips for the Physical Plausibility Recipe Learn how to get more out of NVIDIA Cosmos with tips straight from the authors behind our Cosmos Cookbook recipes. Watch the livestream 👉 https://www.addevent.com/calendar/ss55fmjpm04t Explore the Cosmos Cookbook 👉 https://nvda.ws/4k7EmaN Register for the hackathon 👉 https://nvda.ws/4qP4sly #NVIDIACosmos #WorldFoundationModels #CosmosCookbook #PhysicalAI NVIDIA Cosmos World Foundation Models Cosmos Cookbook Physical AI NVIDIA Cosmos World Foundation Models Cosmos Cookbook Physical AI"
YouTube Link 2026-02-04T19:05Z 201K followers, [----] engagements
"Build a Document Intelligence Pipeline With Nemotron RAG Nemotron Labs What if you could ask questions about complex PDFsdense tables charts and scanned pagesand have an AI agent answer with precise cited snippets from the original document without hand-writing brittle parsers With Nemotron RAG you can build a multimodal intelligent document processing pipeline from scratch in under an hour using GPU-accelerated extraction and just a few hundred lines of Python to turn unstructured files into grounded queryable knowledge. Curious how it works Join us for a developer-focused livestream that"
YouTube Link 2026-02-07T09:56Z 201K followers, [----] engagements
"Developer Insights NVIDIA DGX Spark at PyTorch Conference Hear how this developer would #SparkSomethingBig if he had one at home. We love the excitement around NVIDIA DGX Spark at #PyTorchCon and #OpenSourceAIWeek"
YouTube Link 2025-10-23T16:03Z 201K followers, 18.2K engagements
"NVIDIA MultiTalker ASR Demo: Real-Time Multi-Speaker Transcription Made Easy See how NVIDIAs MultiTalker ASR technology delivers live automatic transcription for conversations with multiple speakerseven when people talk over each other. This advanced AI system separates identifies and captions up to four voices simultaneously requiring no registration or enrollment. Built on NVIDIAs high-precision speech models MultiTalker extends beyond single-speaker ASR to capture every voice accurately and organize each streamwithout compromising clarity or speed. Watch the demo to explore latency and"
YouTube Link 2025-12-05T21:19Z 201K followers, [----] engagements
"Inference Office Hours with SGLang: Performance Optimizations for LLM Serving Join us to find out the latest inference optimizations for leading open source models from SGLang on NVIDIA GPUs. Well dive into an in-depth overview of the engineering behind optimizing SGLang on GB200 followed by a deep dive of recent performance advancements targeting low-latency inference and throughput efficiency. General Resources: Dynamo Day on demand: Inference OSS Ecosystem featuring SGLang https://nvda.ws/3MeKMsb SGLang Adds Day-0 Support for the Highly Efficient Open Nemotron [--] Nano Hybrid MoE Model"
YouTube Link 2026-02-06T01:33Z 201K followers, [----] engagements
"Building a Multi-Agent Chatbot Demo on DGX Spark Looking to build a smarter fully local chatbot with multiple AI models working together This demo shows how to create a local multi-agent chatbot on DGX Spark running LLMs and VLMs side by side. A gpt-oss-120b supervisor agent coordinates experts in coding retrieval-augmented generation and visual understanding unlocking the power of collaborative AI. Create this chatbot using the playbook here- https://build.nvidia.com/spark/multi-agent-chatbot Learn more: build.nvidia.com/spark"
YouTube Link 2025-10-10T20:06Z 201K followers, 11.5K engagements
"Getting Started with NVIDIA Triton Inference Server Triton Inference Server is an open-source inference solution that standardizes model deployment and enables fast and scalable AI in production. Because of its many features a natural question to ask is where do I begin Watch the video to find out GitHub: https://github.com/triton-inference-server/server Documentation: https://github.com/triton-inference-server/server/tree/main/docs #ai #inference #nvidiatriton #AI #inference #nvidiatriton ai inference ai inference nvidia triton triton inference server #AI #inference #nvidiatriton ai"
YouTube Link 2022-09-07T20:28Z 201K followers, 59.7K engagements
"Building Multimodal AI RAG with LlamaIndex NVIDIA NIM and Milvus LLM App Development This video explains how to create a multimodal AI retrieval-augmented generation (RAG) application including the following steps: [--]. Document processing: Convert documents into text form using vision language models specifically NeVA 22B for general image understanding and DePlot for charts and plots. [--]. Vector database: Explore the power of GPU-accelerated Milvus for efficient storage and retrieval of your embeddings. [--]. Inference with Llama 3: Leverage the NVIDIA NIM API Llama [--] model to handle user queries"
YouTube Link 2024-09-03T21:06Z 201K followers, 24K engagements
"Unboxing the NVIDIA DRIVE AGX Thor Developer Kit The developer kit is built on the NVIDIA Blackwell architecture next-generation Arm Neoverse V3AE CPUs and the NVIDIA DriveOS [--] software stack. Its purpose-built for reasoning vision language action models and ideal for automotive development with sufficient I/O to support surround cameras radars and lidars as well as common vehicle interfaces including GbE/10GbE and PCI-Express. DRIVE AGX Thor also meets the automotive industrys stringent functional safety (ISO 26262) and cybersecurity requirements (ISO 21434). URLs mentioned in the video:"
YouTube Link 2025-09-22T18:34Z 200K followers, [----] engagements
"Introducing NVIDIA DGX Spark GTC [----] Keynote NVIDIA DGX Spark belongs to a new class computers designed to build and run AI enabling developers to prototype fine-tune and inference large #AI models locally and seamlessly deploy to the data center or cloud. Learn more: https://www.nvidia.com/en-us/products/workstations/dgx-spark/ 📣 Announced 5/19/2025: We will be launching our AI-first personal computing systems NVIDIA DGX Spark and DGX Station with global computer makers. ➡"
YouTube Link 2025-03-19T16:29Z 201K followers, 15K engagements
"CES meets DGX Spark [----] wrap-up Join the NVIDIA Developer Community Team for our CES [----] WrapUp livestream. Well look at this years biggest moments and innovations from the keynote and bustling CES show floor featuring demos in action. Well share insights and reactions from the event adding depth and perspective including updates and responses to recent announcements across the industry. Then well spotlight whats new with DGX Spark the firstoutofthegate platform powering nextgeneration AI research and development everywhere. Expect snapshots of new opensource models community contributions"
YouTube Link 2026-01-07T00:02Z 201K followers, [----] engagements
"Getting Started with the Jetson Orin Nano Developer Kit The NVIDIA Jetson Orin Nano Developer Kit sets a new standard for creating entry-level AI-powered robots smart drones and intelligent cameras. Compact design lots of connectors and up to [--] TOPS of AI performance give you everything you need to transform your visionary concepts into reality. In this video we take you through an overview of the Jetson Orin Nano Developer Kit including its key features specifications and components along with how to power on and initiate first boot of the device. To learn more please visit our website:"
YouTube Link 2023-03-21T15:17Z 201K followers, 133K engagements
"New Nemotron RAG Models: Multimodal Embed and Rerank VLMs Meet llama-nemotron-embed-vl-1b and llama-nemotron-rerank-vl-1bcompact 1B VLMs for high-accuracy multilingual multimodal search and visual document retrieval ready for production. Use them to search beyond plain text across PDFs scans screenshots and slide decks in a single embed + rerank pipeline. 🤗Check out our blog on @HuggingFace: https://huggingface.co/blog/nvidia/llama-nemotron-vl-1b #Nemotron #RAG #OpenModels #opensource"
YouTube Link 2026-01-09T22:58Z 201K followers, [----] engagements
"Intro to NVIDIA NIM for AI Builders Discover why portable cloud-native inference microservices are ideal for powering enterprise generative AI applications. Add to your calendar: https://www.addevent.com/event/FM24088078 To further explore and get started with NIM visit these resources: NVIDIA NIM for Developers: https://nvda.ws/4frykhh Try the NVIDIA Launchable from the livestream: https://nvda.ws/3VM3IQo NIM AI foundation models discord channel (First join the developer discord before participating in this channel): https://nvda.ws/3DqvWdi Try NIM in the NVIDIA API catalog:"
YouTube Link 2024-12-04T16:26Z 200K followers, 16.1K engagements
"NVIDIA Jetson AGX Xavier Developer Kit - Introduction The NVIDIA Jetson AGX Xavier Developer Kit is the latest addition to the Jetson platform. Its an AI computer for autonomous machines delivering the performance of a GPU workstation in an embedded module under 30W. Jetson AGX Xavier is designed for robots drones and other autonomous machines. Learn more: https://developer.nvidia.com/jetson-xavier NVIDIA Jetson Developer Kit Robotics AI at the edge Autonomous Machines Intelligent Machines GPU AI Deep Learning Artificial Intelligence NVIDIA Jetson AGX Xavier NVIDIA Jetson Developer Kit"
YouTube Link 2018-07-10T23:50Z 201K followers, 127.8K engagements
"Create Infinite Medical Imaging Data with Generative AI Learn More: https://monai.io/ #MONAI #medicalimaging #medicalAI Generative AI for medical imaging can create infinite synthetic images of the human anatomy. These large synthetic datasets are used for training generalizable AI models that can learn from evolving patient data while preserving patient privacy. Learn how MONAI a framework for building and deploying medical AI and partners like Kings College London Mount Sinai and East River Imaging are using generative AI to study disease and make AI decisions and predictions more accurate"
YouTube Link 2023-03-21T16:41Z 201K followers, 89.8K engagements
"Fine-Tuning 8B Parameter Model Locally Demo with NVIDIA DGX Spark What if you could fine-tune massive AI modelsup to [--] billion parametersright on your desktop With NVIDIA DGX Spark you can. Supercharge your AI creativity by improving the performance of pre-trained models through easy powerful fine-tuning. Build solutions tailored exactly to your needswithout waiting on massive data centers. Learn more: build.nvidia.com/spark"
YouTube Link 2025-08-29T17:00Z 201K followers, 17K engagements
"3 Steps for Building an Intelligent Document Pipeline for RAG With Nemotron Learn how to build a high-throughput IDP pipeline that uses vision-based extraction to turn complex charts and nested tables into searchable intelligence. By preserving document structure with markdown and multimodal embeddings you can boost RAG accuracy by 40%. Check out the full Jupyter notebook and technical blog. 📝 Tech blog: https://nvda.ws/3NVXM6r 📝Notebook: https://colab.research.google.com/drive/1qQXYfzmaIXglKfnqhZ2YXXE_OmAybxSr"
YouTube Link 2026-02-05T17:00Z 201K followers, [----] engagements
"1001 Ways to Accelerate Python with CUDA Kernels NVIDIA GTC [----] Learn how to write high-performance CUDA kernels directly in Python using tools and best practices that maximize GPU acceleration. In this NVIDIA GTC [----] session well explore kernel structure memory management thread coordination and optimization strategiesmaking it easier than ever to integrate CUDA into your Python applications. Speaker: Leo Fang Python CUDA Tech Lead NVIDIA Watch more NVIDIA GTC sessions on demand: https://www.nvidia.com/en-us/on-demand/ncid=so-yout-194474-vt33 CUDA Toolkit:"
YouTube Link 2025-04-16T17:00Z 200K followers, 12.5K engagements
"CUDA 13.0New Features and Beyond NVIDIA GTC D.C. The NVIDIA CUDA platform is the foundation of the GPU computing ecosystem. Every application and framework that uses the GPU does so through CUDA's libraries compilers runtimes and languagewhich means CUDA is growing as fast as its ecosystem is evolving. At this engineering-focused talk by CUDA's technical product lead you'll learn what's new and what's coming next for both CUDA and GPU computing as a whole. Speakers: Rob Armstrong CUDA Technical Product Management Lead NVIDIA Watch more: https://www.nvidia.com/en-us/on-demand/"
YouTube Link 2025-12-02T19:00Z 201K followers, [----] engagements
"Set Up Your NVIDIA RTX [----] GPU for AI Development on Linux with PyTorch This step-by-step guide walks you through setting up your Ubuntu environment for deep learning using NVIDIA RTX [----] GPU PyTorch and Hugging Face. Learn how to install NVIDIA drivers verify installation install PyTorch and Hugging Face Transformers and run a state-of-the-art large language model. More specifically youll learn how to: ✔ Install the latest NVIDIA [----] drivers on Ubuntu [-----] LTS for optimal performance. ✔ Install PyTorch Torchaudio and Torchvision nightly with NVIDIA Blackwell support and validate GPU"
YouTube Link 2025-02-10T21:33Z 201K followers, 21.9K engagements
"How to Build a Voice Agent with RAG and Safety Guardrails This tutorial provides a step-by-step guide on how to build a voice agent using the latest NVIDIA Nemotron models. Youll learn how to integrate four core components: multimodal RAG to retrieve relevant text and images automatic speech recognition (ASR) to convert live audio into text a safety model to filter safe or unsafe content and long-context reasoning to generate accurate grounded responses. 📝 Tech blog: https://nvda.ws/4snwyFz ➡ Learn more: https://nvda.ws/4jjQgxL 📥 Download:"
YouTube Link 2026-01-05T22:10Z 201K followers, [----] engagements
"Deploying Generative AI in Production with NVIDIA NIM 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 platformcloud data centers or on-prem. Discover how its cloud-native architecture backed by powerful tools like NVIDIA Triton Inference Server and TensorRT-LLM simplifies the deployment and scaling of AI models ensuring efficient and cost-effective operations. Whether you're looking to"
YouTube Link 2024-05-20T16:49Z 201K followers, 311K engagements
"Intro to NVIDIA Nsight Systems CUDA Developer Tools Join NVIDIAs Sven Middelberg for an introduction to NVIDIA Nsight Systems a tool for performance tuning NVIDIA GPU-accelerated applications. Nsight Systems provides a timeline view of your system's performance helping you identify bottlenecks and optimization opportunities. 00:00 - Introduction 2:14 - How to Trace an Application 6:34 - Using the Timeline View 8:36 - Analysis Summary Tab 8:50 - Diagnostics Summary Tab 9:07 - Conclusion Highlights include: Tracing with Nsight Systems: Walk through the tracing process including project setup"
YouTube Link 2023-09-22T15:47Z 201K followers, 22.1K engagements
"Build a Simple AI Agent with OpenAIs gpt-oss-20b Learn how to build a simple AI agent with OpenAI's new gpt-oss models (20b and 120b) with NVIDIA NIM. In this video we demonstrate how to access NVIDIA NIM for OpenAIs gpt-oss reasoning models through build.nvidia.com and start building immediately. Discover how to use the OpenAI Responses API set reasoning efforts for different query complexities and create a web search agent. Whether you want to use NVIDIA-hosted NIM endpoints or privately deploy and scale gpt-OSS NIM microservices on your infrastructure this tutorial is great for you Get"
YouTube Link 2025-08-07T21:55Z 201K followers, 21.9K engagements
"Getting Started with the NVIDIA Jetson AGX Orin Developer Kit The NVIDIA Jetson AGX Orin Developer Kit makes it easy to get started with Jetson Orin. Compact size lots of connectors and up to [---] TOPS of AI performance make this developer kit perfect for prototyping advanced AI-powered robots and other autonomous machines. In this video we take you through an overview of the Jetson AGX Orin Developer Kit including its key features specifications and components along with how to power on and initiate first boot of the device. For more details please check out our Getting Stated Guide:"
YouTube Link 2022-04-11T19:07Z 201K followers, 85.3K engagements
"Frontiers of AI and Computing: A Conversation With Yann LeCun and Bill Dally NVIDIA GTC [----] As artificial intelligence continues to reshape the world the intersection of deep learning and high performance computing becomes increasingly crucial. This talk brings together Yann LeCun a pioneer in deep learning and the chief AI scientist at Meta and Bill Dally a leading computer architect and chief scientist at NVIDIA to explore the future of AI models hardware accelerators and the evolving computational landscape. The discussion covers: The next breakthroughs in deep learning and AI"
YouTube Link 2025-04-10T16:00Z 201K followers, 101.2K engagements
"Customizing Your Personal AI With Open Models #nvidia #ai #jensenhuang #ces2026"
YouTube Link 2026-01-08T23:03Z 201K followers, [----] engagements
"An Introduction to NVIDIA Cosmos World Foundational Models NVIDIA GTC [----] NVIDIA Cosmos is transforming how robots and autonomous vehicles learn accelerating physics-aware synthetic video generation with world foundation models. Join Ming-Yu NVIDIAs VP of Generative AI Research to see how Cosmos is democratizing physical AI developmentgiving developers open models and tools to build custom world models faster than ever. Speaker: Ming-Yu Liu VP Generative AI Research NVIDIA NVIDIA GTC [----] Session S72431. Watch more #robotics sessions from GTC on demand:"
YouTube Link 2025-04-08T22:30Z 201K followers, 16.3K engagements
"Implementing New Algorithm with CUDA Kernels CUDA C++ Class Part [--] Welcome to NVIDIAs Modern CUDA C++ Programming Class. You will learn how to implement new algorithms on the GPU using CUDA Kernels. This series is for C++ developers who want to use the GPU effectivelywhether youre new to CUDA and want the fastest path from hello world to real acceleration or youre an experienced CUDA programmer ready to modernize your code with the latest best practices. If you already know C++ and want to write clean efficient idiomatic GPU code this course is for you. This video is part of a broader"
YouTube Link 2025-11-06T22:13Z 201K followers, [----] engagements
"Building with FLUX.2: From Prototype to Real-World Application Join Black Forest Labs a member of the NVIDIA Inception Program and NVIDIA for an immersive technical exploration into FLUX.2 the state-of-the-art model redefining the boundaries of visual synthesis. Technical experts will deconstruct the FLUX.2 architecture discussing optimized deployment strategies on NVIDIA infrastructure and the diverse use casesfrom enterprise design to media productionthat this model enables. In this livestream join us for: - Live coding demonstrations of real-world examples illustrating how to move a"
YouTube Link 2026-01-22T13:05Z 201K followers, [----] engagements
"DGX Spark Live: Your Questions Answered Vol. [--] Got questions about DGX Spark / GB10 Whether youre exploring how DGX Spark can boost your workflows or looking to get more out of your existing setup this livestream is designed to give you real answers and practical insights. Well cover key topics to help you fully understand such as benefits use case and integration. Join us live bring your questions and get the clarity you need to make the most of your DGX Spark experience"
YouTube Link 2026-02-04T00:09Z 201K followers, [----] engagements
"#NVIDIA DGX Spark - Your Own Personal #AI Supercomputer ✅ [--] petaFLOP ✅ 128GB of coherent unified system memory ✅ ConnectX-7 Smart NIC ✅ Up to 4TB Storage ✅ 150mm L x 150mm W x 50.5mm H Reserve yours now"
YouTube Link 2025-07-01T17:42Z 201K followers, 104.2K engagements
"DGX Spark Live: Backend Development with Local LLM Inference In this episode well explore various ways DGX Spark can help engineering teams building Generative AI applications by iterating faster and managing their own development infrastructure. Topics covered include: open source inference engineers; open source models; use cases and opportunities. Getting Started with DGX Spark: https://nvda.ws/49TaaNs Demos shown available here: https://github.com/abdelrahmanhosny/embedded-ai"
YouTube Link 2025-12-05T06:27Z 201K followers, [----] engagements
"DGX Spark Live: Real-Time Worker Safety with OnSight AI Powered by DGX Spark and Smart Glasses Join our latest hackathon winners - Team Tabasco for a live demo of OnSight AI a real-time AI safety and compliance system built during the NVIDIA DGX Spark Hackathon on December 12th. Using smart glasses and a Vision-Language Model (VLM) running on DGX Spark OnSight AI continuously analyzes first-person video to detect safety violations such as protective equipment and lock-out-tag-out (LOTO) compliance and delivers instant audio feedback to workers. See how the team integrated iOS/Android smart"
YouTube Link 2025-12-20T07:49Z 201K followers, [----] engagements
"NVIDIA Jetson AGX Orin: Next-level AI Performance for Next-Gen Robotics NVIDIA Jetson AGX Orin provides upto [---] TOPS of AI performance for running next-gen robotics. Watch this video on how we built Orion robot on Jetson AGX Orin platform using different technologies provided by NVIDIA. Learn more: https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-agx-orin/"
YouTube Link 2022-03-22T14:45Z 201K followers, 42.6K engagements
"DGX Spark Live: Process Text for GraphRAG With Up to 120B LLM See NVIDIA DGX Spark in action for local GraphRAG and graph analytics. We will showcase how this demo runs entirely on DGX Sparks 128GB unified memory extracting nodes and relationships from local biomedical research papers to build a context-aware Knowledge Graph in ArangoDB. Getting Started with DGX Spark: https://nvda.ws/4o2rDHn Start building with DGX Spark: https://nvda.ws/49TaaNs"
YouTube Link 2025-11-19T03:31Z 201K followers, [----] engagements
"First Look: NVIDIA DGX SuperPOD with DGX GB200 Systems An exclusive first look at an NVIDIA DGX SuperPOD with eight DGX GB200 systems. See everything -- from Grace Blackwell Superchips to InfiniBand and Spectrum-X networking and liquid cooling -- that makes it a record-setting system. Straight from an Equinix data center in Silicon Valley. Read the blog: https://nvda.ws/3FOL1GG"
YouTube Link 2025-04-07T20:30Z 201K followers, 25.3K engagements
"NVIDIA Cosmos Cookbook: Tips for the Egocentric Social and Physical Reasoning Recipe Learn how to get more out of NVIDIA Cosmos with tips straight from the authors behind our Cosmos Cookbook recipes. Watch the livestream 👉 https://www.addevent.com/calendar/ss55fmjpm04t Explore the Cosmos Cookbook 👉 https://nvda.ws/4k7EmaN Register for the hackathon 👉 https://nvda.ws/4qP4sly #NVIDIACosmos #WorldFoundationModels #CosmosCookbook #PhysicalAI NVIDIA Cosmos World Foundation Models Cosmos Cookbook Physical AI NVIDIA Cosmos World Foundation Models Cosmos Cookbook Physical AI"
YouTube Link 2026-02-03T16:55Z 201K followers, [----] engagements
"Introduction to the Nsight Tools Ecosystem CUDA Developer Tools GPU acceleration enables faster and smarter applications and CUDA enables you to harness acceleration on NVIDIA GPUs. But debugging profiling and optimizing CUDA can be challengingespecially if you cant see the hardware processes interfacing with CUDA. To help you fully harness CUDA acceleration NVIDIA offers tools to make development easier and more efficient. This tutorial is an introduction to the NVIDIA Nsight Developer Tools ecosystem a suite of software libraries SDKs and IDE tools that help you use CUDA to accelerate your"
YouTube Link 2023-09-22T15:43Z 200K followers, 12.4K engagements
"DGX Spark Live: Rapid AI Agent Development The latest generation of AI models is accelerating the deployment of AI agents helping to write code perform deep research or act as a personal assistant managing schedules booking travel and updating calendars. The ability to quickly create and deploy AI agents is becoming a business imperative. Join us to learn how Aible enables you to rapidly create AI agents within minutes using your data and easily deploy them on desktop data center or cloud. We will explore how Aible takes advantage of DGX Spark to build and deploy agents and how you can use"
YouTube Link 2026-01-28T06:22Z 201K followers, [----] engagements
"Tensor Cores in a Nutshell This video gives a brief introduction to the Tensor Core technology inside NVIDIA GPUs and how its important to maximizing deep learning performance. https://developer.nvidia.com/tensor-cores NVIDIA AI GPU Tensor Core Tensor Cores Tensorcore Tensorcores Deep Learning DL Deep Learning Training AI Training CNN DNN Mixed-Precision Training Mixed-Precision Mixed Precision Mixed Precision Training FP-16 FP-32 FP16 FP32 NVIDIA AI GPU Tensor Core Tensor Cores Tensorcore Tensorcores Deep Learning DL Deep Learning Training AI Training CNN DNN Mixed-Precision Training"
YouTube Link 2019-01-30T18:26Z 201K followers, 106.4K engagements
"Simplifying AI Cluster Management with NVIDIA Base Command AI clusters are difficult to manage. There are multiple hardware and software elements to coordinate and constant updates that can be extremely time consuming. DIY approaches also require diverse skills spanning networking compute and storage. NVIDIA Base Command is the operating system of the accelerated data center. It lets organizations use the full potential of their NVIDIA DGX investment with a proven platform that includes enterprise-grade orchestration and cluster management as well as libraries that accelerate compute storage"
YouTube Link 2022-09-19T06:32Z 201K followers, [----] engagements
"Analyzing NCCL Usage with NVIDIA Nsight Systems NVIDIA Nsight Systems now includes support for tracing NCCL (NVIDIA Collective Communications Library) usage in your CUDA application. This enables users to identify NCCL activity on the CPU timeline and correlate it to the associated GPU #CUDA kernels and #memory copies. Equipped with this information users can validate and improve NCCL usage by identifying CPU and GPU cold spots and hot spots. Nsight Systems is the go-to profiling tool for gaining a holistic view of CUDA #applications. #SC20 Learn more about Nsight Systems the family of Nsight"
YouTube Link 2020-11-09T13:31Z 199K followers, 43.3K engagements
"GPU Accelerated Polars Learn how Polars Lazy Evaland NVIDIA GPU acceleration can accelerate your Data Science. These two tools create a powerful backend that builds an optimized query plan and parallelizes execution on NVIDIA GPUs. Get started in Google Colab or locally. #datascience #polars #gpu #python"
YouTube Link 2025-04-25T19:27Z 193K followers, [----] engagements
"Office Hours - Nemotron Have questions on NVIDIA's Nemotron models Want to provide your thoughts on the models directly to NVIDIA RSVP to attend office hours and drop any questions you have on our Discord channel https://discord.com/channels/1019361803752456192/1407781691698708682 or in the comments below"
YouTube Link 2025-09-05T00:34Z 195K followers, [----] engagements
"AI Physics Deep Dive Industrial Engineering Live Stream Series Interested in AI Physics Join our "AI Physics Deep Dive" livestream to learn about the latest ML architectures for computational engineering workloads and for a hands-on tour of NVIDIA PhysicsNeMo including practical recipes of how to train and test the latest in AI Physics models. Well cover step by step: - A live demonstration of building and running NVIDIA PhysicsNeMo platform for industrial engineering problems such as CFDstructural analysis and more. - Walkthroughs of the pros and cons of using graph neural networks neural"
YouTube Link 2025-10-30T12:55Z 193K followers, [----] engagements
"Getting Started with NGC Part 3: NGC Model Download Workflow NVIDIA NGC is a cloud platform that provides access to GPU-optimized software containers and pre-trained deep learning models making it easier for data scientists and developers to deploy and run deep learning and HPC applications on NVIDIA GPUs. In this video we demo a workflow which showcases how to use the NGC CLI to download a pretrained model. To learn more about NVIDIA AI Enterprise Administration: https://academy.nvidia.com/en/nvaie-public-training/"
YouTube Link 2023-05-01T11:50Z 197K followers, [----] engagements
"Get Started with cuTile Python The release of NVIDIA CUDA [----] introduces tile-based programming for GPUs making it one of the most fundamental additions to GPU programming since CUDA was invented. Learn how you can write GPU tile kernels that allows you to write your algorithm at a higher level than a single instruction multiple thread (SIMT) model and the compiler and runtime handle the partitioning of work onto threads under the covers. Resources and Links: 🔗 cuTile Python GitHub Repository: https://github.com/NVIDIA/cutile-python 📖 Official cuTile Python Documentation:"
YouTube Link 2025-12-04T22:23Z 196K followers, [----] engagements
"NVIDIA DGX Station: Desktop Tour Watch this short video to see the highlights of the DGX OS Desktop environment. https://nvda.ws/2V7zA02"
YouTube Link 2019-03-28T18:59Z 193K followers, 12.3K engagements
"CUDACast #10a - Your First CUDA Python Program In this CUDACast video we'll see how to write and run your first CUDA Python program using the Numba Compiler from Continuum Analytics"
YouTube Link 2017-07-20T23:49Z 198K followers, 155.8K engagements
"Why Is NVIDIA AI-Q the Top-Rated Open Portable AI Agent for Deep Research NVIDIA AI-Q is now #1 among open and portable AI agents on the Deep Research Bench leaderboard achieving a best-in-class score of [-----]. The portability of AI-Q enables organizations to build agents that operate anywheredata center or cloud. Agents that operate locally within enterprise data centers can reduce latency and improve security. Open and built with models like NVIDIA Llama Nemotron the AI-Q blueprint is completely customizable enabling organizations to adapt the deep research for their unique use cases. AI-Q"
YouTube Link 2025-08-04T16:59Z 195K followers, [----] engagements
"Course Introduction: How to Build a RAG Agent Build smarter RAG systems that reason adapt and retrieve information autonomously. This course takes you from traditional RAG to agentic RAG AI agents that go beyond simple retrieval to actively reason through complex information tasks. Learn the architecture build the pipeline and deploy your own RAG agent using NVIDIA tools. What you'll learn in the full module: How to Build RAG Agent https://developer.nvidia.com/topics/how-to-build-agentic-ai-rag Key differences between traditional and agentic RAG systems How to architect a complete RAG"
YouTube Link 2025-10-27T02:53Z 193K followers, [----] engagements
"NVIDIA's Dedication to Open Source NVIDIA GTC Washington D.C. [----] Keynote "The United States has to lead in open source as well. We have amazing proprietary models. We have amazing proprietary models. We need also amazing open source models. Our country depends on it. Our startups depend on it. And so NVIDIA is dedicating ourselves to go do that." -- Jensen Huang Watch the full NVIDIA GTC keynote here: https://www.youtube.com/live/lQHK61IDFH4si=_-wQFaqQNb6Y1gjR&t=4748 #nvidia #nvidiagtc #opensource"
YouTube Link 2025-10-28T20:50Z 196K followers, [----] engagements
"Train AI Agents for CLI Tasks using Synthetic Data & Reinforcement Learning Nemotron Labs What if your computer-use agent could learn a new command-line tooloperating it safely without writing files or free-typing shell commands With NVIDIA Nemotron open models you can quickly train specialized agents for any CLI using synthetic data and reinforcement learningno usage logs required. Curious how it can be adapted for your own proprietary CLI environment Join us live for a developer-focused livestream. In this interactive livestream well cover: - A live demo: Generating synthetic training data"
YouTube Link 2025-11-22T04:10Z 194K followers, [--] engagements
"Predict LLM Performance with Dynamo AI Configurator Optimizing large language model (LLM) serving is complex. Which framework offers the best perf How do you choose between aggregated vs. disaggregated serving If disaggregated whats the best prefill/decode split What kind of parallelism should you use for each worker Exploring this space can take weeks. AI Configurator simplifies this to just minutes. Use the CLI to input your model hardware traffic characteristics and goals and the tool intelligently searches for an optimal configuration. AIC combines kernel-level benchmarks on real silicon"
YouTube Link 2025-12-15T23:24Z 201K followers, [---] engagements
"Getting started on NVIDIA-Powered Data Science Workstations Walk through getting started on NVIDIA-Powered Data Science Workstations powerful systems featuring pre-installed CUDA-X AI software libraries and NVIDIA Quadro RTX [----] GPUs. See a demo on how these systems unlock new levels of performance and productivity for data scientists. Learn more about RAPIDS: https://rapids.ai Learn more about Data Science Workstations: https://nvidia.com/data-science-workstation"
YouTube Link 2019-07-01T22:15Z 194K followers, 10K engagements
"What is Word Error Rate (WER) and how do I properly calculate it to benchmark ASR models Word Error Rateor WERmeasures how many words a speech-to-text system gets wrong compared to a human transcript. NVIDIAs open source automatic speech recognition (ASR) models Canary-Qwen-2.5B and Parakeet-TDT-0.6B-V2 which reflect the openness philosophy of Nemotron with open datasets weights and recipes hold top spots on the new ArtificialAnalysis (AA) ASR leaderboard for record WER. 🏆 Leaderboard ➡ https://artificialanalysis.ai/speech-to-text 📥 Canary Qwen 2.5B ➡"
YouTube Link 2025-09-25T18:13Z 190K followers, [----] engagements
"Dynamo KVBM - Managing Memory at Scale Got questions about KV cache management in your LLM deployment Join us for a session on Dynamo's KV Block Manager (KVBM)- a system that decouples memory management from run-time logic to enable memory-efficient high-throughput LLM systems. Well dive into architecture integration with LLM inference runtimes integration with NIXL and our roadmap. Come ready to chat drop your questions in the comments and learn more from the engineers building KVBM. Be part of the journey and contribute on github: https://bit.ly/dynamoKVBM"
YouTube Link 2025-10-28T01:05Z 190K followers, [--] engagements
"NVIDIA AI Tech Workshop at NeurIPS Expo [----] - Session 5: Applied Deep Learning This session from the NVIDIA AI Tech Workshop at NeurIPS Expo [----] highlighted by NVIDIA Research includes: - Building Speech Recognition with Synthetic Speech - Optimization of training neural collaborative filtering systems Presentation slides will be uploaded soon for reference"
YouTube Link 2018-12-05T19:30Z 189K followers, [----] engagements
"Deploy and Scale AI Workloads with NVIDIA Run:ai on Azure Kubernetes Service (AKS) NVIDIA Run:ai on Azure Kubernetes Service empowers organizations to unlock fast scalable and efficient AI infrastructure for large language models and generative AI applications. In this demo you will discover how NVIDIA Run:ai on Azure Kubernetes Service transforms deployment with its intelligent orchestration of GPU resources enabling real-time training and inference for enterprise workloads. The video highlights the seamless integration between NVIDIA Run:ai and Microsoft Azure making AI infrastructure"
YouTube Link 2025-10-30T16:27Z 190K followers, [---] engagements
"Ray Tracing Essentials Part 1: Basics of Ray Tracing In Part 1: Basics of Ray Tracing NVIDIA's Eric Haines runs through the basics of ray and path tracing. To begin he defines a ray and notes how it is useful for different operations in computer graphics. Rays can be cast to test for shadows for example. In [----] Whitted introduced the idea of recursive ray casting known as ray tracing. Cook and others in [----] explored how bursts of rays could create more elaborate effects such as soft shadows and glossy reflections. Kajiya introduced the Rendering Equation in [----] showing how it could be"
YouTube Link 2019-12-20T01:56Z 195K followers, 142K engagements
"Visualizing a Twin Earth in NVIDIA Omniverse This is the Earth as we know it. Creating a Digital Twin of the Earth using technologies like the #NVIDIAOmniverse ParaView Connector allows scientists to interactively analyze weather and climate data in 3D and to combine information from multiple sources and explore what if scenarios. Read the Omniverse #ParaView Connector blog: https://nvda.ws/3xaZRhQ Learn how Omniverse is transforming #ScientificVisualization workloads: https://nvda.ws/32GP8y1"
YouTube Link 2021-04-21T18:34Z 199K followers, 32.3K engagements
"Transforming AI NVIDIA GTC [----] Panel Hosted by Jensen Huang The Transforming AI panel from GTC [----] features the authors of Attention Is All You Need" the groundbreaking paper that introduced the transformer neural network architecture. Transformers have since dominated all areas of AI revolutionizing the industry. The discussion covers the following topics: The development and impact of the Transformer model. The evolution of computing and its democratization. The future of AI technology and its potential applications. The role of accelerated computing. The potential for AI to revolutionize"
YouTube Link 2024-04-08T23:30Z 194K followers, 117.6K engagements
"NVAITC Webinar: Introduction to Convolutional Neural Networks Understand and discuss implementations of common convolutional and residual neural networks. Learn more: https://developer.nvidia.com/deep-learning-examples"
YouTube Link 2020-11-30T17:07Z 189K followers, [----] engagements
"Train a Reasoning-Capable LLM in One Weekend Have you ever wanted to build your own reasoning models such as NVIDIA Nemotron but thought it was too complicated or required massive resources Think again. With NVIDIAs powerful tools and datasets you can train a small effective reasoning model in about [--] hours all on a single GPU. Explore a simple and computationally efficient recipe for training reasoning models with small amounts of training data curated from the Llama Nemotron Post-Training Dataset. Learn the strategy based on LoRA adapter training and the key considerations and"
YouTube Link 2025-07-30T16:14Z 191K followers, 16.8K engagements
"Implementing Real-time Vision AI Apps Using NVIDIA DeepStream SDK Learn how companies around the world are modernizing their existing infrastructure with IoT sensors such as cameras to extract rich insights. Whether its a patient fall detection monitoring system in a hospital understanding how traffic flows through a city or a retailer looking to understand customer purchasing sentiments and behavior real-time video analysis plays a pivotal role. Learn how various companies are building high-performance apps using DeepStream SDK for real-time video and image understanding. We'll show you the"
YouTube Link 2021-01-16T16:30Z 190K followers, 30.4K engagements
"Optimize AI Agents with Continuous Model Distillation and Evaluation Using a Data Flywheel Learn how to optimize AI agents in production using the NVIDIA Data Flywheel Blueprinta continuous loop of distillation fine-tuning and evaluation powered by NeMo and NIM microservices. See how to replace a Llama 70B model with a smaller faster one using LoRA ICL and LLM-as-a-judge scoringall driven by real-world agent traffic. This demo: Breaks down the architecture and building blocks of the blueprint Walks through how to replace a production-grade Llama 70B model with a smaller faster alternative for"
YouTube Link 2025-06-11T09:01Z 198K followers, [----] engagements
"NVIDIA Jetson Partner Stories: Jibo Makes Its Robot More Social with the Jetson Platform The Jetson TK1 has been an accelerant to the design and development process of the Jibo the world's first consumer social robot for the home. The increased processing power of the Jetson TX1 will help the creators of Jibo to do some very special things with vision processing beyond simple facial recognition such as the ability to leverage more sophisticated object detection leading to a faster and more responsive robot for consumers"
YouTube Link 2015-11-11T17:03Z 189K followers, 15.1K engagements
"Quansight and RAPIDS Push Data Science Performance Travis Oliphant CEO of Quansight and early contributor to RAPIDS explains the work being done to integrate GPUs with data"
YouTube Link 2018-11-07T23:03Z 188K followers, [----] engagements
"Run NVIDIA GPU Cloud Containers in Singularity This video covers (1) Installing and configuring Singularity (2) Pulling and saving NGC containers and (3) Running NGC containers in an HPC environment. Learn more: https://nvda.ws/2QXzzKm"
YouTube Link 2018-10-18T17:15Z 191K followers, [----] engagements
"CUDACast #7 - CUDA [---] nvidia-smi Accounting To learn more or comment on this video visit the blog post at http://bit.ly/cudacast-7 Learn about the new accounting features part of the nvidia-smi tool in CUDA [---] CUDA-5.5 CUDACasts nvidia-smi GNU/Linux (Operating System) CUDA-5.5 CUDACasts nvidia-smi GNU/Linux (Operating System)"
YouTube Link 2013-08-22T19:08Z 200K followers, [----] engagements
"GTC Silicon Valley Preview: Media & Entertainment NVIDIAs GPU Technology Conference (GTC) is the premier AI and deep learning conference providing training insights and direct access to media and entertainment experts. Here's a preview of the some of the Media & Entertainment sessions you can attend. https://nvda.ws/2CWq34u"
YouTube Link 2019-01-30T21:56Z 188K followers, [----] engagements
"Introduction to NVIDIA DOCA Module #1: DOCA Demystified Learn the basic concepts of NVIDIA DOCA as a platform for accelerated data center application development for the NVIDIA BlueField DPU. Upon completion participants will be equipped with a set of introductory knowledge that will enable them to begin using DOCA and DPUs to develop applications that accelerate their data centers services. Complete all [--] modules of this free self-paced course on the NVIDIA Deep Learning Institute: https://nvda.ws/3nLw78v Get early access to the DOCA SDK: https://nvda.ws/3InM3ph Learn more about BlueField"
YouTube Link 2022-01-21T19:23Z 198K followers, 18.4K engagements
"Build an AI Agent for Report Generation with NVIDIA Nemotron on OpenRouter Learn how to build a powerful AI report generation agent from scratch In this workshop we'll walk you through the core concepts of AI agent design and give you hands-on experience with NVIDIA Nemotron and OpenRouter. You'll set up your development environment build the agent's tools implement research and authoring functionalities and orchestrate the entire workflow. By the end you'll have your very own report-writing agent in a turn-key portable development environment. #AIAgent #OpenRouter #Nemotron #buildyourown"
YouTube Link 2025-09-23T17:26Z 198K followers, [----] engagements
"3 Ways to Accelerate pandas with NVIDIA GPUs [--] Ways to Accelerate pandas with NVIDIA GPUs. Accelerating your pandas code is now a no-code or low-code task. This video deep dives into [--] methods across multiple coding environments to help you accelerate your pandas code. 00:00 - Intro 00:30 - Method [--] - magic command 03:55 - Method [--] - cuDF module 07:27 - Method [--] - cuDF code 09:24 - Outro ➡ Join the NVIDIA Developer Program: https://nvda.ws/3OhiXfl ➡ Read and subscribe to the NVIDIA Technical Blog: https://nvda.ws/3XHae9F #pandas #python #NVIDIA #GPU #datascience #machinelearning #ML #cuDF"
YouTube Link 2025-07-15T19:00Z 197K followers, [----] engagements
"Gemma3 Running at [--] Tokens/sec on Jetson Orin Nano Live VLM Demo Watch a live demo by Asier Arranz Senior Developer Advocate at NVIDIA running Gemma3 on Jetson Orin Nano at [--] tokens/sec including both the 4B and an impressive 12B modelright from Googles Gemma3 launch event in Paris. Learn how to deploy high-performance Visual Language Models (VLMs) on compact edge devices for real-time multimodal AI. If you're exploring similar projects or have ideas you'd like to share feel free to comment or get in touch Subscribe to Google for Developers https://goo.gle/developers #Gemma"
YouTube Link 2025-04-03T19:44Z 199K followers, 17K engagements
"From a Robot's Perspective: Teaching Robots to Grasp We are teaching our robot arm to grasp commonly used objects with diverse appearances. We trained our models purely in simulation and they now achieve 88% success rate in the real world without any extra steps. https://arxiv.org/pdf/1905.10520.pdf"
YouTube Link 2019-08-28T20:23Z 162K followers, [----] engagements
"Get Started with NVIDIA TAO Toolkit The #NVIDIATAO Toolkit built on TensorFlow and PyTorch is a low-code AI solution that abstracts away the AI and deep learning framework complexity. It lets you use the power of transfer learning to fine-tune NVIDIA pretrained models with your own data.This video walkthrough will show you how to install the TAO Toolkit followed by a step-by-step guide process of fine-tuning a pretrained model in a Jupyter notebook. Learn more https://nvda.ws/39h47Fd Join the NVIDIA Developer Program: https://nvda.ws/3OhiXfl Read and subscribe to the NVIDIA Technical Blog:"
YouTube Link 2023-08-11T19:44Z 199K followers, [----] engagements
"How to Autoscale Efficiently with Disaggregated Serving How can you use GPUs efficiently with disaggregated serving This video explains how NVIDIA Dynamo and its open-source planner help you serve models at large scale while meeting your service level objectives (SLOs) like time to first token and inter-token latency. Learn how prefill and decode steps are split across dedicated GPUs and why scaling shouldnt be reactionary. With time series forecasting NVIDIA Dynamo automatically scales the number of prefill or decode machines based on workload demands whether youre summarizing long documents"
YouTube Link 2025-08-12T17:01Z 192K followers, [----] engagements
"Real-Time Digital Twin - Deep Dive Industrial Engineering Livestream Series 📱 Join our Real-Time Digital Twin (RTDT) Deep Dive livestream to learn about how to build RTDTs using Omniverse APIs kit-CAE extension and NVIDIA PhysicsNeMo. This session includes live walk-through of the code base and examples for automotive aerospace and data-center design. Well cover step by step: A live demonstration of building and using the NVIDIA Omniverse kit-CAE extension for industrial engineering problems integrating data from CFD structural analysis and more. Walkthroughs of the different data importers"
YouTube Link 2025-11-19T03:48Z 194K followers, [--] engagements
"XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies New #NVIDIAResearch Paper: XCube (X3): Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies by Xuanchi Ren Jiahui Huang Xiaohui Zeng Ken Museth Sanja Fidler Francis Williams Abstract: We present X3 (pronounced XCube) a novel generative model for high-resolution sparse 3D voxel grids with arbitrary attributes. Our model can generate millions of voxels with a finest effective resolution of up to [-----] in a feed-forward fashion without time-consuming test-time optimization. To achieve this we employ a"
YouTube Link 2023-12-08T16:46Z 189K followers, [----] engagements
"Simplicits: Mesh-Free Geometry-Agnostic Elastic Simulation NVIDIA Research The proliferation of 3D representations from explicit meshes to implicit neural fields and more motivates the need for simulators agnostic to representation. We present a data- mesh- and grid-free solution for elastic simulation for any object in any geometric representation undergoing large nonlinear deformations. We note that every standard geometric representation can be reduced to an occupancy function queried at any point in space and we define a simulator atop this common interface. For each object we fit a small"
YouTube Link 2024-07-27T17:00Z 192K followers, [----] engagements
"Multi-GPU Communication Libraries for Scaling HPC and AI Workloads NVIDIA GTC [----] Want to scale beyond the limits of a single GPU Learn how to use CUDA-aware MPI NVSHMEM and NCCL to scale your applications across multiple GPUs and nodes. This GTC [----] session features a real-world example to help you choose the right communication library for your performance and workload needs. Speaker: Jiri Kraus Principal Developer Technology NVIDIA Replay of NVIDIA #GTC25 Session ID: S72578 Topic: Models / Libraries / Frameworks - Accelerated Computing Libraries NVIDIA technology: CUDA CUDA-X NCCL NVLink"
YouTube Link 2025-04-22T18:00Z 199K followers, [----] engagements
"NVIDIA Jetson Partner Stories: Fellow Robots -- LoweBot NAVii Fellow Robots CTO Thavidu Ranatunga presents LoweBot a Jetson TX1-powered NAVii robot designed to guide Lowes Hardware customers to their item of choice via voice recognition or an onboard touchscreen display. LoweBot navigates the aisles autonomously and in an often Wi-Fi denied environment using cameras and odometry alone to find its destination. During off-hours LoweBot helps store employees by tracking depleted or missing inventory with a high-resolution camera and LED light source recognizing items using a Deep Learning-based"
YouTube Link 2017-03-08T02:09Z 193K followers, 35.8K engagements
"Accelerated Machine Learning with XGBoost on NVIDIA GPUs Accelerated Data Science Series Learn how to get a 25x performance increase of XGBoost training inference and feature engineering with pandasall accelerated with RAPIDS running in Google Colab. In this demo GPUs are used to accelerate workflows using real-world taxi fare data build baseline models and incrementally improve model accuracy with advanced feature engineering. All of this is done directly in Google Colab where RAPIDS and XGBoost are pre-installed for seamless access. 📗 Try this yourself on Google Colab:"
YouTube Link 2025-02-21T20:47Z 179K followers, [----] engagements
"Deep Reinforcement Learning in Robotics with NVIDIA Jetson Discover the creation of autonomous reinforcement learning agents for robotics in this NVIDIA Jetson webinar. Learn about modern approaches in deep reinforcement learning for implementing flexible tasks and behaviors like pick-and-place and path planning in robots. Learn more at https://developer.nvidia.com/embedded/twodaystoademo#advanced-deep_reinforcement Buy the latest Jetson products at https://developer.nvidia.com/buy-jetson"
YouTube Link 2019-06-11T17:08Z 192K followers, 21.7K engagements
"Open Models Are Now Frontier Models #nvidia #ai #jensenhuang #ces2026"
YouTube Link 2026-01-10T22:00Z 201K followers, [----] engagements
"Get Started with NVIDIA IGX Orin Developer Kit for Scalable Edge AI Solutions Learn how to quickly configure your NVIDIA IGX Orin Developer Kit an industrial-grade platform for developing and deploying real-time edge AI inference applications. Watch this video for an overview of the system and the different ways you can use it. Youll also learn how to: ⚬ Unbox and power up your system ⚬ Set up your system ⚬ Install the NVIDIA Holoscan SDK ⚬ Run your first Holoscan application Discover more about NVIDIA IGX Orin: https://www.nvidia.com/en-us/edge-computing/products/igx/ Read the NVIDIA IGX"
YouTube Link 2023-10-30T17:39Z 194K followers, 10.1K engagements
"Google's Gemma2 SLM on NVIDIA Jetson Orin Nano: The Future of Conversational Edge AI Dive into Google's Gemma2 SLM on Jetson Orin Nano with these easy beginner-friendly demoseven if you have ZERO experience with Jetson In this video Ill walk you through simple steps to bring powerful conversational AI to life on a small efficient device. From setup to real-time interaction see how easy it is to get started with advanced AI at the edge. Heres what youll learn: - Step-by-step setup for Gemma2 SLM on Jetson Orin Nano perfect for beginners. - Real-time conversational AI demos including"
YouTube Link 2024-10-28T22:09Z 188K followers, 14.6K engagements
"DGX Spark Live: Installation & First Run Guide for Robotics Developers 📱 This is the essential live session for robotics developers ready to leverage NVIDIA Isaac Sim on the powerful DGX Spark platform. We'll guide you through the initial steps to get your high-fidelity simulation environment up and running on the aarch64 architecture. What You'll Learn & Do: Installation Walkthrough: Follow along with the official documentation process including the specific details for the DGX Spark where the ARM build is generated by default. Launch & Verification: We'll show you how to properly launch"
YouTube Link 2025-12-09T00:35Z 195K followers, [--] engagements
"This is What an AI Application Looks Like in the Future #nvidia #ai #jensenhuang #ces2026"
YouTube Link 2026-01-10T17:01Z 201K followers, [----] engagements
"How to Build an AI Agent: Course Introduction Learn to build autonomous AI agents that plan reason and solve complex problems. This introduction covers Agentic AI Foundations from core concepts to building your first working agent. We'll explore what makes AI systems "agentic" real-world applications and design principles that matter. What you'll learn in the full module: https://developer.nvidia.com/topics/how-to-build-an-ai-agent What Agentic AI is and how it differs from single-shot generation How agents plan reason and tackle multi-step problems autonomously Real-world examples across"
YouTube Link 2025-10-27T07:15Z 193K followers, [----] engagements
"Turn Any PC into a SMPTE ST [----] Compliant Source with NVIDIA RivermaxDisplay Simplify your transition to SMPTE ST [----] with NVIDIA RivermaxDisplay. See how this software application turns any PC into a SMPTE ST [----] compliant source with NMOS support. Try NVIDIA RivermaxDisplay Today: https://nvda.ws/4aFxAnE Join the NVIDIA Developer Program: https://nvda.ws/3OhiXfl Read and subscribe to the NVIDIA Technical Blog: https://nvda.ws/3XHae9F #NVIDIARivermaxDisplay #SMPTEST2110 #NVIDIA"
YouTube Link 2024-01-03T18:18Z 194K followers, [----] engagements
"Digital Humans and AI Design with NVIDIA NIM on RTX PCs Microsoft Build [----] Discover how to create powerful agentic workflows for RTX AI PCsquickly efficiently and backed by NVIDIA NIM microservices. With NVIDIA NIM and RTX PCs and Workstations you can quickly build advanced AI workflows that are fast local and leverage the AI model innovations. We'll showcase and guide developers on the use of NVIDIA NIM microservices to kickstart AI experimentation. Learn more about AI on NVIDIA RTX PCs: https://developer.nvidia.com/ai-apps-for-rtx-pcs Access AI Models for RTX AI PCs:"
YouTube Link 2025-06-03T17:16Z 192K followers, [----] engagements
"Training and Inferencing with NVIDIA AI Enterprise on VMware vSphere NVIDIA AI Enterprise is a comprehensive suite of software that's optimized certified and supported on VMware vSphere [--] and industry-leading servers. This end-to-end platform is designed to provide the easiest solution for enterprises to enable AI in their core data center. In this demo we'll show some examples of the features and capabilities of this stack as well as some example workloads such as multi-node AI training as well as multiple inferencing workloads. Learn more about NVIDIA AI Enterprise here:"
YouTube Link 2021-09-15T18:57Z 194K followers, [----] engagements
"NVIDIA Developer How To Series: Accelerating Recommendation Systems with TensorRT NVIDIA TensorRT is a high-performance deep learning inference optimizer and runtime that delivers low latency and high-throughput for deep learning inference applications. You can import trained models from every deep learning framework into TensorRT and easily create highly efficient inference engines that can be incorporated into larger applications and services. This video demonstrates the steps for using NVIDIA TensorRT to optimize a Multilayer Perceptron based Recommender System that is trained on the"
YouTube Link 2018-08-03T22:56Z 188K followers, [----] engagements
"The Wonderful Capability of Reasoning #nvidia #ai #jensenhuang #ces2026 #nemotron #chatgpt nvidia nvidia"
YouTube Link 2026-01-09T22:01Z 201K followers, [----] engagements
"NVIDIA Announces Aerial A Software-defined Stack for Telco Systems At Mobile World Congress Los Angeles NVIDIA unveiled Aerial a set of SDKs that enables GPU-accelerated software defined 5G wireless radio access network (RAN). Today NVIDIA Aerial provides two critical new SDKs: CUDA Virtual Network Functions (cuVNF) and CUDA Baseband (cuBB). These SDKs simplify building highly programmable and scalable software-defined 5G RANs using commercial off-the-shelf (COTS) servers with NVIDIA GPUs. https://news.developer.nvidia.com/cubb-software-defined-stack-for-telco/"
YouTube Link 2019-10-21T23:49Z 194K followers, [----] engagements
"Unified Whole-Body Control for Humanoids with MaskedMimic from NVIDIA Project GR00T MaskedMimic is part of NVIDIA Project GR00T for enabling development of generalized humanoid robots. This research work contributes to GR00T-Control a suite of advanced motion planning and control libraries models policies and reference workflows for whole-body control. MaskedMimic is a single unified controller for physically simulated humanoids. Our system is capable of generating a wide range of motions across diverse terrains from intuitive user-defined intents. In this work we show several applications"
YouTube Link 2024-12-04T00:31Z 193K followers, [----] engagements
"SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillation Physically-simulated models for human motion can generate high-quality responsive character animations often in real-time. Natural language serves as a flexible interface for controlling these models allowing expert and non-expert users to quickly create and edit their animations. Many recent physics-based animation methods including those that use text interfaces train control policies using reinforcement learning (RL). However scaling these methods beyond several hundred motions has remained"
YouTube Link 2024-07-28T21:00Z 196K followers, [----] engagements
"Accelerate Your End-to-End AI Data Analytics and HPC Workflows with the NVIDIA NGC Catalog The NGC catalog is a hub of GPU-optimized AI high-performance computing (HPC) and data analytics software that simplifies and accelerates end-to-end workflows. Explore NGC: https://nvda.ws/3liOEYA With enterprise-grade containers pre-trained AI models and industry-specific SDKs that can be deployed on premises in the cloud or at the edge enterprises can build best-in-class solutions and deliver business value faster than ever before. Learn More: https://nvda.ws/3dpy6JC Contact Us:"
YouTube Link 2021-04-14T17:30Z 194K followers, 17.9K engagements
"Set Up a Data Flywheel to Self-Optimize AI Models and Agents The NVIDIA Data Flywheel Blueprint provides a systematic automated solution to refine and redeploy optimized models that maintain accuracy targets while lowering resource demands. This blueprint establishes a self-reinforcing data flywheel using production traffic logs and institutional knowledge to continuously improve model efficiency and accuracy. 00:00 - 01:20 Introduction and System Overview 01:21 - 02:10 Architecture and Orchestrator 02:11 - 03:00 Model Evaluation and Cost Optimization 03:01 - 04:00 Deployment and Cloud Setup"
YouTube Link 2025-07-23T16:07Z 191K followers, [---] engagements
"How to Deploy Hugging Face Models Using a Single NVIDIA NIM This video walks you through how to deploy different LLMs from Hugging Face with a single LLM-agnostic NVIDIA NIM container. NIM microservices are your go-to for deploying the latest AI models from NVIDIA and the community quickly and reliably. They leverage NVIDIA TensorRT-LLM to accelerate and optimize inference alongside popular community backends like vLLM and SGLang to seamlessly deploy a massive range of community LLMs. Get ready for high-performance inference on NVIDIA GPUs with rapid reliable deployment for a broad range of"
YouTube Link 2025-07-01T18:32Z 193K followers, [----] engagements
"Building AI Agents at Scale: Get Started with DataRobot If youre serious about deploying AI agents into production you know its harder than the hype makes it sound. In this session well show you the roadblocks youll hit and how to overcome them as well as practical steps to build deploy and manage agents that actually work at enterprise scale. You will learn to: - Compare multiple frameworks powered by NVIDIA Nemotron models - Build fast and flexibly: Ingest data from ERP systems forecasts and external signals with your preferred frameworks NVIDIA NIM microservices and side-by-side testing in"
YouTube Link 2025-08-29T01:25Z 199K followers, [----] engagements
"Quantum Computing - Where We're Headed #GTC25 Fireside Chat Click to watch NVIDIA founder and CEO Jensen Huang host industry leaders in "Quantum Computing: Where We Are and Where Were Headed" a fireside chat from #gtc25 #quantumcomputing https://youtu.be/9XB-LsfpvCU NVIDIA founder and CEO Jensen Huang hosts industry leaders from Alice & Bob Atom Computing AWS D-Wave Infleqtion IonQ Microsoft Pasqal PsiQuantum Quantinuum Quantum Circuits QuEra Computing Rigetti and SEEQC to learn today's state of the art and what the future holds for useful quantum computing. These unprecedented fireside chats"
YouTube Link 2025-05-21T14:01Z 197K followers, [----] engagements
"Agentic Systems Revolutionized Software Programming at #nvidia #nvidia #ai #jensenhuang #ces2026 #aiagent #cursor"
YouTube Link 2026-01-11T17:01Z 201K followers, [----] engagements
"NVIDIA GPU Cloud with TITAN V Step by Step In this video Adam Beberg of NVIDIA provides step-by-step instructions for configuring and using NVIDIA GPU Cloud (NGC) with a desktop PC with an NVIDIA TITAN V. Adam demonstrates how to use the NGC user interface getting your PC configured using Docker and running PyTorch within an NGC container. Learn more: https://www.nvidia.com/en-us/gpu-cloud/deep-learning-containers"
YouTube Link 2018-03-07T21:23Z 199K followers, [----] engagements
"NVIDIA DGX Station: Unboxing Watch this short video to see how easy it is to unbox a NVIDIA DGX Station https://nvda.ws/2V7zA02"
YouTube Link 2019-03-28T18:57Z 195K followers, 11.7K engagements
"NVIDIA Networking: Learn the Basics of LinkX Cables and Transceivers The NVIDIA LinkX product lineup encompasses a wide range of interconnect solutions including cables and transceivers all aimed at maximizing the efficiency of data center operations. In this video we'll take a look at the various types of LinkX solutions on offer and highlight their features and abilities. To learn more about NVIDIA Data Center Networking for Administrators: https://academy.nvidia.com/en/training-by-topic/training_by_topic=10"
YouTube Link 2023-08-14T10:22Z 190K followers, [----] engagements
"Getting Started with Edge AI on NVIDIA Jetson: LLMs VLMs and Foundation Models for Robotics As Physical AI gains momentum edge computing is becoming increasingly critical for bringing intelligence directly to robots devices and real-world applications. This livestream invites developers to explore this expanding frontier by experimenting with open-source models on NVIDIA Jetson unlocking capabilities ranging from private coding companions to autonomous robots"
YouTube Link 2025-12-05T19:14Z 196K followers, [----] engagements
"What Happens During Inference When You Ask an LLM a Question When you ask an LLM a question a complex process called inference begins from token prediction to prefill and decode. In this video we break down exactly how it works how its evolving and how NVIDIA Dynamo accelerates each stage. Learn how disaggregated serving splits these steps across multiple GPUs for faster more efficient AI responses. Learn More: https://github.com/ai-dynamo/dynamo #LLM #NVIDIA #AIInference #DisaggregatedServing #TokenPrediction #AIExplained"
YouTube Link 2025-08-11T17:01Z 198K followers, [----] engagements
"CUDA Toolkit 12.2: New Accelerated Computing and Security Enhancements Revealed Join CUDA experts for this in-depth overview of the CUDA [----] release. This update offers multiple features to help you reduce programming time create more efficient code and accelerate your applications. New features include support for NVIDIA Hopper GPU hardware architecture confidential computing to protect sensitive data and AI workloads heterogeneous memory management (HMM) and enhancements to MPS prioritization. 00:00 Introduction 04:03 CUDA [----] New Features (read the related TechBlog:"
YouTube Link 2023-07-06T19:00Z 198K followers, 11K engagements
"Cosmos Cookbook Recipe: Reasoning for Human-Robot Interactions New Cosmos Cookbook recipe just dropped 🍽 Intbots recipe evaluates Cosmos Reason [--] on a set of targeted egocentric video tests designed to probe robot-relevant reasoning including: 📖 Human intent directed toward the robot 📖 Object motion relative to the robot 📖 Spatial relationships among multiple people 📖 Social context awareness (when not to engage) Try it yourself in the Cosmos Cookbook 👉 https://nvda.ws/4sji9ud Download Cosmos Reason [--] 👉 https://github.com/nvidia-cosmos/cosmos-reason2 #NVIDIACosmos"
YouTube Link 2026-01-08T17:08Z 201K followers, [----] engagements
"Create a RAG Chatbot Using NVIDIA AI Workbench In this video youll learn how to create your own retrieval-augmented generation (RAG) chatbot using NVIDIA AI Workbench. With this unified easy-to-use developer toolkit you can create test and customize pretrained AI models on NVIDIA RTX-powered AI workstations. Start your AI projects locally on workstations and scale them effortlessly to any data center or cloud with just a few clicks. Start your AI projects locally on workstations and scale them effortlessly to any data center or cloud with just a few clicks. Learn more about NVIDIA AI"
YouTube Link 2024-10-10T17:24Z 191K followers, [----] engagements
"Jetson AI Fundamentals - S1E1 - First Time Setup with JetPack Learn to set up the NVIDIA Jetson Nano Developer Kit for the first time with JetPack. This enables you to load Docker container applications for projects in Jetson AI Fundamentals. 00:00:00 - Introduction - Setting up Jetpack with Jetson Nano 00:00:33 - Jetson Nano Developer Kit 00:01:56 - Step 1: Flashing OS onto an SD card with a computer 00:08:18 - Step 2: Configure OS on Jetson Nano 00:10:53 - Setting SWAP to 4GB 00:13:44 - Conclusion Getting Started with AI on Jetson Nano - https://nvidia.com/dli Jetson AI Fundamentals -"
YouTube Link 2020-10-13T20:44Z 189K followers, 266.9K engagements
"Getting Started with Accelerated XGBoost Check out this walkthrough on accelerating XGBoost with NVIDIA RAPIDS. Notebook link: https://bit.ly/3ENje9m"
YouTube Link 2025-02-21T20:47Z 198K followers, [----] engagements
"NVIDIA GPU-accelerated Path Rendering - SVG Part [--] Mark Kilgard gives a short demonstration of NVIDIA's GPU-Accelerated Path Rendering this is part three of a three part series on the different ways to render SVG samples using the new NVIDIA GPU-Accelerated Path Rendering SDK Read more at http://developer.nvidia.com/nv-path-rendering"
YouTube Link 2011-08-26T04:03Z 193K followers, [----] engagements
"Techniques for Efficient and Reproducible Foundation Model Pre-Training Speaker: Dan Su Senior Research Scientist NVIDIA Dan Su provides an inside look at the Nemotron pre-training workflow sharing the key techniques for efficient and reproducible foundation model pre-training. This session covers the sophisticated curation of high-quality pre-training data the strategic data mixture and ordering strategy and the architectural evolution of Nemotron models. You'll learn how Nemotron aims to advance the field by open-sourcing its data and recipes and how innovative models like Nano V3 achieve"
YouTube Link 2025-12-14T17:01Z 196K followers, [----] engagements
"How Accelerated Compute is Driving Scientific Discovery For [--] years weve been building CUDA-X libraries to accelerate discovery across scientific disciplines. Today with more than [---] libraries and frameworks CUDA-X is the foundation for some of the worlds fastest breakthroughs. In this video we demonstrate how CUDA-X is reshaping science today and creating the innovations needed to power the latest scientific discoveries. Join us at Supercomputing [----] to explore our latest contributions to scientific discovery. Check out the links below to learn more Life Science: Driving Toward"
YouTube Link 2025-11-10T21:56Z 195K followers, [----] engagements
"Reinvent Video Conferencing Content Creation & Streaming with AI Using NVIDIA Maxine NVIDIA Maxine is a GPU-accelerated SDK with state-of-the-art AI features for developers to build virtual collaboration and content creation applications such as video conferencing and live streaming. Developers from video conferencing content creation and streaming providers such as Notch Headroom Be.Live and Touchcast are using the Maxine SDK to create real-time video-based experiences easily deployed to PCs data centers or in the cloud. Learn more about NVIDIA Maxine: https://nvda.ws/3cSIRVC"
YouTube Link 2021-04-14T17:29Z 195K followers, [----] engagements
"NVIDIA Variable Rate Shading Demonstrated in Autodesk VRED Last year we introduced Variable Rate Shading (VRS) with the Turing architecture. This new easy to implement rendering technique allows developers to vary the amount of processing power spent across the image to spend time and increase quality in the areas where they are most needed. Since virtual reality demands both a high performance and a high image quality VRS is the perfect fit for VR experiences especially when used in conjunction with eye tracking. For more information about VRS read the related Developer Blog"
YouTube Link 2019-11-26T20:46Z 197K followers, [----] engagements
"Shutterstock Unveils Generative AI [---] HDRi Built Using NVIDIA Picasso Shutterstock is using NVIDIA Picasso a foundry for building generative AI visual models to develop a variety of generative AI services to accelerate 3D workflows. At SIGGRAPH Shutterstock announced the first offering of these new services - [---] HDRi - to create photorealistic HDR environment maps to relight a scene. This demo shows how services built using NVIDIA Picasso can streamline environment map generation speeding up 3D workflows. #siggraph2023"
YouTube Link 2023-08-08T17:00Z 198K followers, [----] engagements
"How to Deploy UFM in an OpenStack-Based Cloud Environment NVIDIA United Fabric Manager (UFM) is a key component of the InfiniBand fabric and the InfiniBand cloud. It provides a rich representational state transfer (REST) API for integrations with schedulers and cloud service provider (CSP) allocation systems. It also provides an infrastructure for security tenant isolation and tenant service-level agreements (SLAs). In this video were going to demonstrate an example of an OpenStack cloud integration. Well create a tenant and isolate its resources from other tenant resources using pkey"
YouTube Link 2022-05-30T17:15Z 197K followers, [----] engagements
"DGX Spark: Powering EPRIs AI Research 📱 Join EPRI a nonprofit research organization dedicated to advancing the science that powers a reliable affordable and resilient energy future. Discover how EPRI is innovating with NVIDIA DGX Spark to run advanced openweight models such as gptoss120b and Qwen3Embedding8B to drive a secure AI-powered document research assistant. Get started with DGX Spark: https://nvda.ws/4o2rDHn"
YouTube Link 2025-11-11T01:46Z 192K followers, [--] engagements
"From Data to Deployment: Building European AI at Scale Improved audio version available here: https://youtu.be/KwSwxb2GBOM Moderated by tech futurist and AI expert Sarah Rojewsky join us live with technical experts from DeepL and NVIDIA as we explore the journey of building sovereign AI capabilities in Europe. Get a behind-the-scenes look at the technical and operational challenges of large-scale AI training and inference and discover the steps involved in developing robust AI products from choosing the right technology to model deployment. Our moderators will be on hand to answer questions"
YouTube Link 2025-10-25T01:30Z 193K followers, [----] engagements
"What is the most underrated research area in AI world foundation models 🤔 Ming-Yu Liu VP of Research at NVIDIA responds with insights into how it wont be humans who will benefit most from whats coming in [----]. Watch his key takeaways from #NeurIPS2025 👀"
YouTube Link 2025-12-05T15:01Z 195K followers, [----] engagements
"Cinematic Climate Visualization with NVIDIA Omniverse #Climate simulations produce large amounts of inherently 3D data and yet the analysis is often limited to 2D projections. In addition to climate #scientists climate data also needs to be accessible by laypersons. Therefore intuitive photorealistic renderings are desirable. The NVIDIA Omniverse platform enables the fusion of large-scale scientific data with cinematic #rendering capabilities allowing for interactive exploration of complex climate phenomena. In this demo we'll show the power of Omniverse to visualize high-resolution climate"
YouTube Link 2020-11-11T19:19Z 193K followers, 41.8K engagements
"Train AI Agents for CLI Tasks using Synthetic Data & Reinforcement Learning Nemotron Labs 📱 What if your computer-use agent could learn a new command-line tooloperating it safely without writing files or free-typing shell commands With NVIDIA Nemotron open models you can quickly train specialized agents for any CLI using synthetic data and reinforcement learningno usage logs required. Curious how it can be adapted for your own proprietary CLI environment Join us live for a developer-focused livestream. In this interactive livestream well cover: - A live demo: Generating synthetic training"
YouTube Link 2025-11-22T04:10Z 194K followers, [--] engagements
"Distributed Inference 101: Monitoring Data Center Performance and Metrics Learn the fundamentals of monitoring performance of your Dynamo deployment at scale using Grafana dashboard. 📥 Explore and download https://github.com/ai-dynamo/dynamo #Inference #datacenter #AI #GTC25 ➡ Join the NVIDIA Developer Program: https://nvda.ws/3OhiXfl ➡ Read and subscribe to the NVIDIA Technical Blog: https://nvda.ws/3XHae9F"
YouTube Link 2025-03-18T18:46Z 193K followers, [----] engagements
"Optimizing AI Agents with the NVIDIA NeMo Agent Toolkit Profiler NVIDIA NeMo Agent toolkit is an open source library that provides framework-agnostic profiling and optimization for production AI agent systems. With the NeMo Agent toolkit profiler developers can identify bottlenecks and leverage features for parallel tool calling performance and more. Download ➡ https://github.com/NVIDIA/NeMo-Agent-Toolkit #GenerativeAI #AgenticAI #AIAgents #RAG #NeMoAgentToolkit Generative AI Agentic AI AI Agents RAG NeMo Agent Toolkit NeMo Agent Toolkit Profiler"
YouTube Link 2025-07-10T22:55Z 197K followers, [----] engagements
"Announcing NVIDIA Agent Intelligence Open-Source Toolkit NVIDIA Agent Intelligence toolkit is an open-source library for connecting evaluating and accelerating teams of AI agents. The NVIDIA Agent Intelligence toolkit simplifies development while optimizing and increasing the accuracy of full-stack complex agentic AI systems. AI agent AI agent #AIAgent #AIAgents"
YouTube Link 2025-03-18T20:00Z 199K followers, [----] engagements
"Ray Tracing Essentials Part 2: Rasterization versus Ray Tracing In Part 2: Basics of Ray Tracing NVIDIA's Eric Haines runs through the basics of rasterization and ray tracing. For decades rasterization also known as the Z-buffer has been the method of choice for rendering 3D images at interactive rates. This talk contrasts and compares it with ray tracing showing how the operations have a certain symmetry. More details about this video can be found here: http://bit.ly/nvrttalk2 You can watch the all of the videos in the series on this YouTube Playlist:"
YouTube Link 2020-02-27T22:06Z 192K followers, 163.1K engagements
"Boost your #LLM apps 💡#NVIDIA AI Blueprint for Enterprise RAG The NVIDIA AI Blueprint for Enterprise RAG pipelines delivers accurate context-aware responses. Our walk-through launchable makes deployment easy"
YouTube Link 2025-07-22T19:28Z 198K followers, [----] engagements
"How to Insert HTML Documents into a Multimodal Retriever Collection Using NVIDIA NIM Simplify your multimodal retrieval systems with NVIDIA NIM. This guide walks you through building a #VLM-based system with LangGraph plus #Llama models. Fast efficient and ideal for experimental pipelines. In this video you will learn how to insert a set of HTML documents into a multimodal retriever collection. 📝 Learn more about NIM: https://nvda.ws/431sEb4 📝 Find the source code in the NVIDIA Generative AI Examples repo on GitHub: https://nvda.ws/417z067 ➡ Join the NVIDIA Developer Program:"
YouTube Link 2025-02-25T00:01Z 161K followers, [---] engagements
"AI Startup Speeds Disease Research With Lab in the Loop BrainStorm Therapeutics a San Diego-based startup is accelerating the development of cures for neurological disorders using AI-powered computational drug discovery paired with lab experiments using organoids: tiny 3D bundles of brain cells created from patient-derived stem cells. This hybrid iterative method where clinical data and AI models inform one another to accelerate drug development is known as lab in the loop"
YouTube Link 2025-04-22T12:55Z 194K followers, [----] engagements
"7 Questions with Jeremy Howard (Answer.ai fast.ai) on Open Source AI and Agents Jeremy Howard the founder of fast.ai and co-founder of Answer.ai shares his thoughts on the future of open source AI the rise of AI agents and why humans should stay at the center of innovation. Interview took place after his keynote at the PyTorch Conference [----] in San Francisco CA"
YouTube Link 2025-10-24T21:23Z 190K followers, [---] engagements
"Universal Scene Description (OpenUSD): Composition and Layering Developers are using Universal Scene Description (OpenUSD) to push the boundaries of 3D workflows. In the second installment of this series on the superpowers of OpenUSD that developers can harness learn how the OpenUSD composition engine enables sparse non-destructive assembly of data from multiple sources so you can create complex scenes with ease. For an introduction to OpenUSD watch the first video in the series: https://www.youtube.com/watchv=1RnTSZK9SwM Learn about the latest USD advancements: usd.nvidia.com Learn about the"
YouTube Link 2023-06-29T17:35Z 197K followers, 362.7K engagements
"Cosmos Cookbook Recipe: Sports Video Generation with LoRA Post Training This NVIDIA Cosmos Cookbook serves as a practical guide to the Cosmos open models offering step-by-step workflows technical recipes and concrete examples for building adapting and deploying WFMs. Todays recipe shows you how to generate and build realistic physically accurate and rule-aware sports videos with smooth player motions using LoRA post-trained on Cosmos Predict [---]. Read the full recipe 📖 https://nvidia-cosmos.github.io/cosmos-cookbook/recipes/post_training/predict2_5/sports/post_training.html Download Cosmos"
YouTube Link 2025-12-03T21:01Z 195K followers, [----] engagements
"Introduction of disaggregated serving in TensorRT-LLM Learn from our experts about disaggregated serving in TRT-LLM. You will learn about the potential benefits of disaggregated serving about how to run disaggregated serving with TensorRT-LLM and about current performance for popular models"
YouTube Link 2025-09-18T00:11Z 190K followers, [----] engagements
"Top 5: GPU-Accelerated Supercomputers & More In this weeks edition of the Developer Top [--] we revisit the top developer stories of the week. From a new GPU-accelerated supercomputer in France new AI NGC containers to cutting edge medical research. https://nvda.ws/2RRvmfS"
YouTube Link 2019-01-26T00:54Z 194K followers, [----] engagements
"Enhance Your AI Agent with Data Flywheels Using NVIDIA NeMo Microservices NVIDIA NeMo microservices provide an end-to-end platform for building data flywheels enabling enterprises to continuously optimize their AI agents with the latest information. AI agent AI agents NVIDIA NeMo Data flywheels agentic ai data flywheel #AIAgent #AIAgents #NVIDIANeMo #AgenticAI"
YouTube Link 2025-04-23T16:41Z 198K followers, [----] engagements
"Jetson AI Fundamentals - S1E2 - Hello Camera Get started with the camera widgets in the free DLI course "Getting Started with AI on Jetson Nano". You'll learn to securely log in to your NVIDIA Jetson Nano and launch the course from a Docker container. 00:00:00 - Introduction - Setting up Docker container and webcam for DLI course 00:00:28 - DLI course overview 00:01:04 - Getting Started with AI on Jetson Nano 00:02:55 - Headless device mode 00:08:26 - Inside the container 00:09:30 - Inside Jupyter lab environment 00:14:28 - Conclusion Getting Started with AI on Jetson Nano -"
YouTube Link 2020-10-07T02:32Z 189K followers, 154.6K engagements
Limited data mode. Full metrics available with subscription: lunarcrush.com/pricing