Загрузка видео...

Не удалось загрузить видео

На главную

LiteRT is here. The universal framework for on-device AI. 📱💻 ✨ 1.4x faster GPU performance ✨ Unified NPU acceleration ✨ Seamless PyTorch and JAX support ✨ Ready for Gemma and gen AI Build faster, simpler, and everywhere. Read the blog:

googledevs's profile picture

Google for Developers

2,575,964 subscribers

194,389 просмотров • 6 месяцев назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

.Adobe Photoshop and Premiere — rebuilt from the ground up for NVIDIA RTX Spark. Up to 2x faster across AI, editing, coloring and effects. Full GPU acceleration. AI-native pipeline. Coming soon.
0:26

.Adobe Photoshop and Premiere — rebuilt from the ground up for NVIDIA RTX Spark. Up to 2x faster across AI, editing, coloring and effects. Full GPU acceleration. AI-native pipeline. Coming soon.

NVIDIA RTX Spark

75,736 просмотров • 2 месяцев назад

NEAR AI is going to create the AGI for the world ✨ ✨ ✨ and give it away
0:51

NEAR AI is going to create the AGI for the world ✨ ✨ ✨ and give it away

NEAR Protocol

166,815 просмотров • 1 год назад

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.
0:54

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.

NEXA AI

26,091 просмотров • 9 месяцев назад

Big day for Windows with Microsoft and NVIDIA announcing the next generation of Windows PCs powered by NVIDIA RTX Spark. These devices bring together performance, efficiency, graphics, and on-device AI in thin-and-light designs that make powerful experiences feel faster. RTX Spark delivers 1 petaflop of AI performance, industry-leading performance-per-watt, full stack NVIDIA AI and RTX graphics technology, and up to 128GB of unified memory. And the new Surface Laptop Ultra shows what happens when that power is thoughtfully applied. Creators and developers can move faster, push further, and build richer experiences locally on Windows, without compromise.
0:51

Big day for Windows with Microsoft and NVIDIA announcing the next generation of Windows PCs powered by NVIDIA RTX Spark. These devices bring together performance, efficiency, graphics, and on-device AI in thin-and-light designs that make powerful experiences feel faster. RTX Spark delivers 1 petaflop of AI performance, industry-leading performance-per-watt, full stack NVIDIA AI and RTX graphics technology, and up to 128GB of unified memory. And the new Surface Laptop Ultra shows what happens when that power is thoughtfully applied. Creators and developers can move faster, push further, and build richer experiences locally on Windows, without compromise.

Yusuf Mehdi

14,487 просмотров • 2 месяцев назад

Hyra AI Reborn. Stronger. Faster. Decentralized. 🔥 Reimagined. A new direction. A new era of decentralized intelligence. From privacy-first edge compute → to a global AI mesh owned by the people. From inference on your device → to digital sovereignty at scale. ✨ Every device is now a node. ✨ Every user is a Hyrasapien. ✨ Every action builds the future of AI. We’re not just rebranding ~ we’re reshaping the narrative of AI. Together, let’s build an AI infrastructure that’s secure, verifiable, and community-owned. 🔑 Your Device. Your Power. Your Sovereignty. 🌐 Explore the new era:
0:35

Hyra AI Reborn. Stronger. Faster. Decentralized. 🔥 Reimagined. A new direction. A new era of decentralized intelligence. From privacy-first edge compute → to a global AI mesh owned by the people. From inference on your device → to digital sovereignty at scale. ✨ Every device is now a node. ✨ Every user is a Hyrasapien. ✨ Every action builds the future of AI. We’re not just rebranding ~ we’re reshaping the narrative of AI. Together, let’s build an AI infrastructure that’s secure, verifiable, and community-owned. 🔑 Your Device. Your Power. Your Sovereignty. 🌐 Explore the new era:

Hyra AI

96,331 просмотров • 10 месяцев назад

Are you ready for the new Teams? It's faster, simpler, smarter, and more flexible than ever. Read more: #MicrosoftTeams
1:00

Are you ready for the new Teams? It's faster, simpler, smarter, and more flexible than ever. Read more: #MicrosoftTeams

Microsoft Teams

269,013 просмотров • 3 лет назад

Game-Changer Alert! Introducing Neuro Image Gen – The ultimate AI image generator powered by Neurolov's decentralized GPU network, delivering ultra-realistic, high-resolution, and completely free image generation! ✨ No fees. No ads. No limits. Just pure AI magic. ✨ Experience DSLR-quality AI images instantly—fueled by the power of a next-gen decentralized GPU network for unmatched speed and precision! 🔗 [ Your Vision. Our AI. Let's Create Together.
0:27

Game-Changer Alert! Introducing Neuro Image Gen – The ultimate AI image generator powered by Neurolov's decentralized GPU network, delivering ultra-realistic, high-resolution, and completely free image generation! ✨ No fees. No ads. No limits. Just pure AI magic. ✨ Experience DSLR-quality AI images instantly—fueled by the power of a next-gen decentralized GPU network for unmatched speed and precision! 🔗 [ Your Vision. Our AI. Let's Create Together.

Neurolov

29,765 просмотров • 1 год назад

🔥 Coin98 Super Wallet V15 is here, empowering smart Web3 interaction for everyone! We’re excited to introduce: ✨ The AI-powered Cypheus Assistant ✨ On-chain chat feature called Coin98 Messenger ✨ A new user-friendly interface And so much more to explore! Upgrade now for a seamless and refreshed journey on the Open Internet 👉 #SmartWeb3Interaction
1:10

🔥 Coin98 Super Wallet V15 is here, empowering smart Web3 interaction for everyone! We’re excited to introduce: ✨ The AI-powered Cypheus Assistant ✨ On-chain chat feature called Coin98 Messenger ✨ A new user-friendly interface And so much more to explore! Upgrade now for a seamless and refreshed journey on the Open Internet 👉 #SmartWeb3Interaction

Coin98 Super Wallet

10,655,158 просмотров • 1 год назад

✨ Get ready for the Hedera AI Agents Hackathon! With HOL and @HederaFndn, we’re bringing together developers, innovators, and AI engineers to explore what’s possible when AI and blockchain converge. 🧵 🛠️ Are you ready to build the future with AI and Hedera?
0:30

✨ Get ready for the Hedera AI Agents Hackathon! With HOL and @HederaFndn, we’re bringing together developers, innovators, and AI engineers to explore what’s possible when AI and blockchain converge. 🧵 🛠️ Are you ready to build the future with AI and Hedera?

Hedera

122,341 просмотров • 1 год назад

Introducing my new AI Helper for Social Media Growth & Content Creation I’ve built an advanced AI Helper designed to help creators, marketers, and businesses grow faster on social media with ease. This AI Helper can guide you step-by-step on: ✨ How to grow your social media audience ✨ How to create high-quality, engaging content ✨ How to improve content value and performance ✨ How to craft powerful titles & descriptions ✨ How to plan, create, and publish content effectively 🎯 I also created a full demo video showing how to build and use this AI Helper from scratch, so anyone can follow and implement it easily. 🔥 Try it here: 🎉 Use code BUILD85 for 85% off This is part of the new “AI Helpers” ecosystem — built to simplify content creation and help you publish smarter, not harder. If you're serious about content growth, this is for you.
3:00

Introducing my new AI Helper for Social Media Growth & Content Creation I’ve built an advanced AI Helper designed to help creators, marketers, and businesses grow faster on social media with ease. This AI Helper can guide you step-by-step on: ✨ How to grow your social media audience ✨ How to create high-quality, engaging content ✨ How to improve content value and performance ✨ How to craft powerful titles & descriptions ✨ How to plan, create, and publish content effectively 🎯 I also created a full demo video showing how to build and use this AI Helper from scratch, so anyone can follow and implement it easily. 🔥 Try it here: 🎉 Use code BUILD85 for 85% off This is part of the new “AI Helpers” ecosystem — built to simplify content creation and help you publish smarter, not harder. If you're serious about content growth, this is for you.

Ai With Piyas

19,179 просмотров • 2 месяцев назад

We're excited to join forces with Sui to bring our AI coding assistant to Sui Move developers — with full support in English, Chinese, and Korean. Now you can: ✨ Generate Move code from natural language ✨ Get smart autocomplete & real-time security checks ✨ Auto-generate docs and use ready-to-go templates All in one seamless, AI-powered dev experience on ChainIDE. Lower barriers, faster innovation — empowering the global Sui community. 👇 See the magic of AI-powered Move dev — demos in 3 languages now in replies!
0:23

We're excited to join forces with Sui to bring our AI coding assistant to Sui Move developers — with full support in English, Chinese, and Korean. Now you can: ✨ Generate Move code from natural language ✨ Get smart autocomplete & real-time security checks ✨ Auto-generate docs and use ready-to-go templates All in one seamless, AI-powered dev experience on ChainIDE. Lower barriers, faster innovation — empowering the global Sui community. 👇 See the magic of AI-powered Move dev — demos in 3 languages now in replies!

Alibaba Cloud

85,346 просмотров • 11 месяцев назад

"Agentic AI changes the role of the CPU. The CPU is now the conductor and the GPU is the orchestra". 🎼 NVIDIA Vera is the first CPU built for AI agents — purpose-built from the ground up for how AI works today. Faster. More efficient. Ready for what's next. 🔲 #NVIDIAGTC
2:53

"Agentic AI changes the role of the CPU. The CPU is now the conductor and the GPU is the orchestra". 🎼 NVIDIA Vera is the first CPU built for AI agents — purpose-built from the ground up for how AI works today. Faster. More efficient. Ready for what's next. 🔲 #NVIDIAGTC

NVIDIA AI Infrastructure

15,062 просмотров • 2 месяцев назад

🗣️ Produce polished videos even faster with the help of AI. Add #Gemini to Google Vids ✨ to give educators access to gen AI tools that make producing, editing, and customizing videos quick and easy – no special skills needed!
0:40

🗣️ Produce polished videos even faster with the help of AI. Add #Gemini to Google Vids ✨ to give educators access to gen AI tools that make producing, editing, and customizing videos quick and easy – no special skills needed!

Google for Education

16,956 просмотров • 2 лет назад

IS LIVE! The next-gen AI launchpad on Solana! ✨ Launch tokens in f*cking seconds ✨ AI does the heavy lifting for you ✨ all-in-one insane marketing suite STOP READING. START BUILDING. 👉 👈
0:30

IS LIVE! The next-gen AI launchpad on Solana! ✨ Launch tokens in f*cking seconds ✨ AI does the heavy lifting for you ✨ all-in-one insane marketing suite STOP READING. START BUILDING. 👉 👈

madness.fun | Solana's Next-Gen Launchpad

12,514 просмотров • 1 год назад

An interesting work on Physical AI: PhysX-Omni. First unified sim-ready generation framework for rigid, deformable, and articulated objects, with a diverse dataset and new benchmark. 🌐 💻 📦
5:03

An interesting work on Physical AI: PhysX-Omni. First unified sim-ready generation framework for rigid, deformable, and articulated objects, with a diverse dataset and new benchmark. 🌐 💻 📦

Ziqi Huang

27,024 просмотров • 2 месяцев назад

✨ I'm unbelievably excited to introduce Ultracite v5: the AI-ready formatter that helps you write and generate code faster. 🙅 Zero-config ⚡ Lightning fast 🤖 Designed for humans and AI 💪 Maximum type safety 🔗 Plays nice with others Here's the TL;DR 👇🧵
4:30

✨ I'm unbelievably excited to introduce Ultracite v5: the AI-ready formatter that helps you write and generate code faster. 🙅 Zero-config ⚡ Lightning fast 🤖 Designed for humans and AI 💪 Maximum type safety 🔗 Plays nice with others Here's the TL;DR 👇🧵

Hayden Bleasel

188,088 просмотров • 1 год назад

✨ Releasing Neodrag v2.0 ✨ - Smaller bundle size! (Up to 15%) - 5 new features - Multiple bug fixes - Faster runtime performance And, the most important: NEW DOCS!
1:33

✨ Releasing Neodrag v2.0 ✨ - Smaller bundle size! (Up to 15%) - 5 new features - Multiple bug fixes - Faster runtime performance And, the most important: NEW DOCS!

{PuruVijay}.svelte

94,715 просмотров • 3 лет назад

If AI can code 100x faster, why aren't you shipping 100x faster? Because AI code is not production-ready code, and definitely not code where you understand and can vouch for every line Introducing the Command Center alpha. Support our Product Hunt launch!
0:22

If AI can code 100x faster, why aren't you shipping 100x faster? Because AI code is not production-ready code, and definitely not code where you understand and can vouch for every line Introducing the Command Center alpha. Support our Product Hunt launch!

Jimmy Koppel

72,545 просмотров • 9 месяцев назад