Loading video...

Video Failed to Load

Go Home

Open-source software never stops. It only accelerates. Dynamo, SGLang, TensorRT LLM, and vLLM are constantly optimized by a vast ecosystem of developers building on top of the NVIDIA platform. The result: your token output keeps improving and token cost keeps decreasing on the same hardware resources while your developer...

nvidia's profile picture

NVIDIA

2,561,440 subscribers

64,473 views • 2 months ago •via X (Twitter)

News & PoliticsEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

In 2006, NVIDIA made a bold bet on a parallel computing platform that would eventually redefine the limits of science and industry. 20 years later, CUDA serves as the foundation for 6 million developers worldwide—and we are only just beginning. Join the next wave of architects and build what’s next on two decades of innovation. 🔗
0:32

In 2006, NVIDIA made a bold bet on a parallel computing platform that would eventually redefine the limits of science and industry. 20 years later, CUDA serves as the foundation for 6 million developers worldwide—and we are only just beginning. Join the next wave of architects and build what’s next on two decades of innovation. 🔗

NVIDIA

21,714 views • 2 months ago

We are innovating the full-stack AI infrastructure platform on a one-year rhythm — pushing the boundaries of inference performance across chips, systems, and software. NVIDIA Blackwell is the most advanced AI platform ever built — continuously optimized for record-breaking performance. Groundbreaking advancements include the NVIDIA-designed NVFP4 format, enabling high inference performance and accuracy. #GTCParis at #VivaTech
1:06

We are innovating the full-stack AI infrastructure platform on a one-year rhythm — pushing the boundaries of inference performance across chips, systems, and software. NVIDIA Blackwell is the most advanced AI platform ever built — continuously optimized for record-breaking performance. Groundbreaking advancements include the NVIDIA-designed NVFP4 format, enabling high inference performance and accuracy. #GTCParis at #VivaTech

NVIDIA

80,342 views • 1 year ago

“There's two reasons why we're building Nemotron. The first is because it helps us build the GPUs and systems for the future.” The second reason is because trust is the foundation of impactful AI–and it starts with understanding. That’s why Nemotron was built open source at its core—so developers, researchers, and enterprises can build together. Hear from Bryan Catanzaro, VP of Applied Deep Learning Research at NVIDIA, on why making AI open benefits everyone. 👉
1:01

“There's two reasons why we're building Nemotron. The first is because it helps us build the GPUs and systems for the future.” The second reason is because trust is the foundation of impactful AI–and it starts with understanding. That’s why Nemotron was built open source at its core—so developers, researchers, and enterprises can build together. Hear from Bryan Catanzaro, VP of Applied Deep Learning Research at NVIDIA, on why making AI open benefits everyone. 👉

NVIDIA

64,788 views • 8 months ago

Delivered performance, not peak chip specifications, drives AI factory productivity. Rigorous benchmarks are the only way to see past the noise. In MLPerf Inference v6.0, NVIDIA extreme co-design delivered the highest token output across the broadest range of models and scenarios. Maximizing token output drives down token cost and maximizes AI factory productivity. Read the blog post to dive into the details: Baseten, CoreWeave, MLCommons
0:43

Delivered performance, not peak chip specifications, drives AI factory productivity. Rigorous benchmarks are the only way to see past the noise. In MLPerf Inference v6.0, NVIDIA extreme co-design delivered the highest token output across the broadest range of models and scenarios. Maximizing token output drives down token cost and maximizes AI factory productivity. Read the blog post to dive into the details: Baseten, CoreWeave, MLCommons

NVIDIA

27,483 views • 2 months ago

📈 NVIDIA tops AI leaderboards and benchmarks with open models driven by extreme co-design across compute, networking, memory, storage, and software. This includes models for biology, AI physics, agentic AI, physical AI, robotics, and autonomous vehicles. By being vertically integrated and horizontally open, NVIDIA enables its ecosystem to scale agentic workflows at every layer of the stack with the lowest cost per token.
0:38

📈 NVIDIA tops AI leaderboards and benchmarks with open models driven by extreme co-design across compute, networking, memory, storage, and software. This includes models for biology, AI physics, agentic AI, physical AI, robotics, and autonomous vehicles. By being vertically integrated and horizontally open, NVIDIA enables its ecosystem to scale agentic workflows at every layer of the stack with the lowest cost per token.

NVIDIA

84,922 views • 1 month ago

“NVIDIA’s cost per token is the lowest in the world.” — Jensen Huang, Founder & CEO of NVIDIA Token generation cost is a direct result of architecture excellence and extreme co-design, not just compute cost. Lowest cost per token and highest performance per watt are definitive measures of AI economics and the key to unlocking maximum profitability and AI revenue. ➡️
0:49

“NVIDIA’s cost per token is the lowest in the world.” — Jensen Huang, Founder & CEO of NVIDIA Token generation cost is a direct result of architecture excellence and extreme co-design, not just compute cost. Lowest cost per token and highest performance per watt are definitive measures of AI economics and the key to unlocking maximum profitability and AI revenue. ➡️

NVIDIA

88,698 views • 2 months ago

If the engine is strong enough, you should be able to build real products on top of it. That's the whole point of LTX-2.3. Introducing LTX Desktop. A fully local, open-source video editor running directly on the LTX engine, optimized for NVIDIA GPUs and compatible hardware.
1:17

If the engine is strong enough, you should be able to build real products on top of it. That's the whole point of LTX-2.3. Introducing LTX Desktop. A fully local, open-source video editor running directly on the LTX engine, optimized for NVIDIA GPUs and compatible hardware.

LTX

953,213 views • 3 months ago

🎙️ Want a full breakdown on why cost per token is a key metric for AI infrastructure TCO? We’re operating in a power-constrained world. Demand for intelligence is scaling faster than infrastructure can keep up—so metrics like cost per GPU hour or FLOPs per dollar don’t tell the full story. When it comes to TCO, Cost per Token is the metric that captures end-to-end performance across GPUs, CPUs, networking, software, and ecosystem making it the key driver of real profitability and scalability in AI. If you’re not measuring efficiency at the token level, you’re missing what actually drives cost. Watch the deep-dive conversation with Dr. Gerro Prinsloo , Nader Khalil and Carter Abdallah, live on the NVIDIA YouTube channel.
1:05

🎙️ Want a full breakdown on why cost per token is a key metric for AI infrastructure TCO? We’re operating in a power-constrained world. Demand for intelligence is scaling faster than infrastructure can keep up—so metrics like cost per GPU hour or FLOPs per dollar don’t tell the full story. When it comes to TCO, Cost per Token is the metric that captures end-to-end performance across GPUs, CPUs, networking, software, and ecosystem making it the key driver of real profitability and scalability in AI. If you’re not measuring efficiency at the token level, you’re missing what actually drives cost. Watch the deep-dive conversation with Dr. Gerro Prinsloo , Nader Khalil and Carter Abdallah, live on the NVIDIA YouTube channel.

NVIDIA

21,970 views • 1 month ago

ICTO is a comprehensive token management and launchpad platform built on the Internet Computer (IC) blockchain. It addresses the critical need for automated token operations within the IC ecosystem.💯 Our target users are developers and project teams building on IC who require robust tools for token vesting, payroll, locking, and fundraising.📌 ICTO aims to simplify these complex processes, enabling projects to focus on their core development while ensuring transparent and secure token management.✨️
0:36

ICTO is a comprehensive token management and launchpad platform built on the Internet Computer (IC) blockchain. It addresses the critical need for automated token operations within the IC ecosystem.💯 Our target users are developers and project teams building on IC who require robust tools for token vesting, payroll, locking, and fundraising.📌 ICTO aims to simplify these complex processes, enabling projects to focus on their core development while ensuring transparent and secure token management.✨️

ICTO ∞

22,989 views • 1 year ago

Chonkie (Chonkie) is building the open source library for connecting your data to AI. Split unstructured data into optimized AI-ingestible chunks that boost your AI accuracy, improve app performance, and reduce token costs. Congrats on the launch, Shreyash Nigam and !
1:04

Chonkie (Chonkie) is building the open source library for connecting your data to AI. Split unstructured data into optimized AI-ingestible chunks that boost your AI accuracy, improve app performance, and reduce token costs. Congrats on the launch, Shreyash Nigam and !

Y Combinator

38,387 views • 1 year ago

Confident AI helps developers build the best version of their LLM application by automating evaluation, prompt iteration, and live testing. Their framework is open source and runs 700k evals every day. Congrats on the launch, Jeffrey 🐬 confident-ai.com + @KritinV78426!
2:04

Confident AI helps developers build the best version of their LLM application by automating evaluation, prompt iteration, and live testing. Their framework is open source and runs 700k evals every day. Congrats on the launch, Jeffrey 🐬 confident-ai.com + @KritinV78426!

Y Combinator

17,469 views • 1 year ago

Watch out developers, it's about to get easier to build on Supra L1 with the all-new Supra DevHub 💪 The Supra DevHub is stacked with resources designed to make building easier and faster with: 📑 Knowledgebase of Queries 🗣️ Developer Discussion Forum 🤝 Hands-on DevRel Support Supra L1 is growing, and so are our resources to help developers connect, build, and ship! Start building on Supra today! 🔗
1:57

Watch out developers, it's about to get easier to build on Supra L1 with the all-new Supra DevHub 💪 The Supra DevHub is stacked with resources designed to make building easier and faster with: 📑 Knowledgebase of Queries 🗣️ Developer Discussion Forum 🤝 Hands-on DevRel Support Supra L1 is growing, and so are our resources to help developers connect, build, and ship! Start building on Supra today! 🔗

Supra

34,237 views • 1 year ago

Developers are building the foundation of a new internet on Solana 🔥 #OnlyPossibleOnSolana Explore their stories and start building:
0:39

Developers are building the foundation of a new internet on Solana 🔥 #OnlyPossibleOnSolana Explore their stories and start building:

Solana

82,037 views • 2 years ago

Looking to build on the future of decentralized computing? Evernode is revolutionizing the space with its robust, serverless cloud platform. Whether you're a developer or a node operator, Evernode offers: • Decentralized Infrastructure • Fair EVR Token Distribution • Secure, Multi-Chain Smart Contracts • On-Demand Scalability Bridging Web2 and Web3 has never been easier. Check out how Evernode is empowering millions of developers worldwide. Evernode: The Layer-2 Execution Engine for the XRP Ecosystem
3:48

Looking to build on the future of decentralized computing? Evernode is revolutionizing the space with its robust, serverless cloud platform. Whether you're a developer or a node operator, Evernode offers: • Decentralized Infrastructure • Fair EVR Token Distribution • Secure, Multi-Chain Smart Contracts • On-Demand Scalability Bridging Web2 and Web3 has never been easier. Check out how Evernode is empowering millions of developers worldwide. Evernode: The Layer-2 Execution Engine for the XRP Ecosystem

𝗕𝗮𝗻𝗸XRP

22,115 views • 1 month ago

"The inflection point for inference has arrived." — Jensen Huang, Founder & CEO of NVIDIA We’ve officially crossed a new milestone in the inference era — where widespread adoption of AI shifts from learning to doing. The breakthrough: extreme codesign across hardware and software driving down cost per token. Lower cost → more inference More inference → more users and applications More users and applications → exponential AI revenue growth
0:41

"The inflection point for inference has arrived." — Jensen Huang, Founder & CEO of NVIDIA We’ve officially crossed a new milestone in the inference era — where widespread adoption of AI shifts from learning to doing. The breakthrough: extreme codesign across hardware and software driving down cost per token. Lower cost → more inference More inference → more users and applications More users and applications → exponential AI revenue growth

NVIDIA

81,393 views • 2 months ago

TOKENFI TOKEN LAUNCHER IS LIVE ON MAINNET IT’S OFFICIAL! TokenFi Token Launcher is live on the mainnet of five top EVM blockchains: Ethereum, BNB Chain, Base, Arbitrum, and opBNB. With TokenFi Token Launcher, ANYONE can create a fungible crypto token (ERC-20), NFT (ERC-721), or Multi-Token (ERC-1155) in just a few clicks, regardless of their crypto experience. The TokenFi platform and framework has been thoroughly audited and is being monitored in real-time by industry-leading blockchain security auditor Certik. This means that the tokens you create with TokenFi are safe and audited. TokenFi Token Launcher is powered by $TOKEN as its main utility token, and every successful transaction on the Ethereum and BNB blockchains buys and burns $TOKEN, enhancing its utility and making it perpetually deflationary as adoption of the platform grows. TokenFi Token Launcher aims to be the dominant token creation platform on EVM blockchains, and to this effect, we will be rolling out the platform on dozens of additional EVM blockchains in the coming weeks and months. You can learn more about TokenFi Token Launcher here:
0:34

TOKENFI TOKEN LAUNCHER IS LIVE ON MAINNET IT’S OFFICIAL! TokenFi Token Launcher is live on the mainnet of five top EVM blockchains: Ethereum, BNB Chain, Base, Arbitrum, and opBNB. With TokenFi Token Launcher, ANYONE can create a fungible crypto token (ERC-20), NFT (ERC-721), or Multi-Token (ERC-1155) in just a few clicks, regardless of their crypto experience. The TokenFi platform and framework has been thoroughly audited and is being monitored in real-time by industry-leading blockchain security auditor Certik. This means that the tokens you create with TokenFi are safe and audited. TokenFi Token Launcher is powered by $TOKEN as its main utility token, and every successful transaction on the Ethereum and BNB blockchains buys and burns $TOKEN, enhancing its utility and making it perpetually deflationary as adoption of the platform grows. TokenFi Token Launcher aims to be the dominant token creation platform on EVM blockchains, and to this effect, we will be rolling out the platform on dozens of additional EVM blockchains in the coming weeks and months. You can learn more about TokenFi Token Launcher here:

TokenFi

1,288,779 views • 2 years ago

Agents are becoming a new layer of enterprise software. Jensen Huang explains why companies like Cadence, CrowdStrike, Dassault Systèmes, Palantir, SAP, ServiceNow, Siemens, and Synopsys are building agents on NVIDIA, and why the opportunity for software partners is only growing.
0:29

Agents are becoming a new layer of enterprise software. Jensen Huang explains why companies like Cadence, CrowdStrike, Dassault Systèmes, Palantir, SAP, ServiceNow, Siemens, and Synopsys are building agents on NVIDIA, and why the opportunity for software partners is only growing.

NVIDIA

95,934 views • 3 days ago

Jensen spent 2 min on InferenceMAX at the GTC keynote 😎 InferenceMAX is completely open source and completely impartial, with the support of AMD, OpenAI, Nvidia, Microsoft, Oracle, Pytorch, SGLang, vLLM, Cursoe, Nebius, Tensorwave, etc
1:44

Jensen spent 2 min on InferenceMAX at the GTC keynote 😎 InferenceMAX is completely open source and completely impartial, with the support of AMD, OpenAI, Nvidia, Microsoft, Oracle, Pytorch, SGLang, vLLM, Cursoe, Nebius, Tensorwave, etc

Dylan Patel

86,497 views • 7 months ago

Reservoir has raised a $14M Series A round led by USV. We’re here to build the world’s best developer tools for token trading on every chain.
0:48

Reservoir has raised a $14M Series A round led by USV. We’re here to build the world’s best developer tools for token trading on every chain.

Reservoir

496,488 views • 1 year ago

1/ Web3 developers – join us on Base, a new, open-source Ethereum L2 with a vision for decentralization and scale. Base is built by Coinbase builders, for the world’s builders. It is designed to be an open ecosystem where anyone, anywhere can build.
0:24

1/ Web3 developers – join us on Base, a new, open-source Ethereum L2 with a vision for decentralization and scale. Base is built by Coinbase builders, for the world’s builders. It is designed to be an open ecosystem where anyone, anywhere can build.

Base

205,713 views • 3 years ago