Загрузка видео...

Не удалось загрузить видео

На главную

Muse Spark Open is built to plan, act, and use computer across agentic tasks for life and work. You can now build a powerful personal AI agent with an open stack, and SGLang to make it: - Ultra-responsive with NVFP4 MegaMoE and sequence parallelism - Faster for agentic and...

sgl_project's profile picture

SGLang

12,501 subscribers

286,622 просмотров • 14 дней назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 4

Фото профиля SGLang
SGLang14 дней назад

For agentic workloads on 8×B300, SGLang delivers over 540 tokens/s per user at batch size 1, while sustaining over 60 tokens/s per user with 128 concurrent requests. With Miles, we improved Geometry3K accuracy from 88.2% to 94.9% in just 30 training updates. Read our technical blog for details 👇

Фото профиля SGLang
SGLang14 дней назад

Deploy Muse Spark Open on NVIDIA, AMD, and Intel hardware with the SGLang Cookbook! For the first time, SGLang has day-0 support for @Google TPUs via sglang-torchtpu (more details coming soon)!

Фото профиля catman
catman14 дней назад

An open agent stack is like a workshop with interchangeable tools: SGLang speeds the workbench, DFlash2 helps draft faster, and Miles lets you customize the tools for the job.

Фото профиля gQ
gQ14 дней назад

No thanks bro, no meta products for me

Похожие видео

Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise workflows. Up to 5x faster inference and up to 30% lower cost for agentic tasks. Learn more:
0:24

Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise workflows. Up to 5x faster inference and up to 30% lower cost for agentic tasks. Learn more:

NVIDIA

230,981 просмотров • 4 месяцев назад

📈 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

85,910 просмотров • 6 месяцев назад

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth
0:40

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth

Marktechpost AI Dev News ⚡

31,551 просмотров • 10 месяцев назад

OpenAI just released access to Computer Use Agent via an API. It combines GPT-4o vision with advanced reasoning for an AI Agent to simulate controlling computer interfaces and performing tasks just like humans. You can try it for free using this Agent Playground.
1:18

OpenAI just released access to Computer Use Agent via an API. It combines GPT-4o vision with advanced reasoning for an AI Agent to simulate controlling computer interfaces and performing tasks just like humans. You can try it for free using this Agent Playground.

Shubham Saboo

64,206 просмотров • 1 год назад

Opera Neon uses agentic AI to act for you and with you as you browse and work on complex projects. Whether you’re researching, planning, or creating 👉 it's built for everyone who uses AI extensively in their day-to-day life. Key features: Tasks, Do, Chat, Cards and Make.
1:53

Opera Neon uses agentic AI to act for you and with you as you browse and work on complex projects. Whether you’re researching, planning, or creating 👉 it's built for everyone who uses AI extensively in their day-to-day life. Key features: Tasks, Do, Chat, Cards and Make.

Opera

582,691 просмотров • 1 год назад

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source
0:59

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source

Sumanth

62,485 просмотров • 1 год назад

AI at Meta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on NVIDIA AI Developer RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been the blockers for a local agent. SGLang and Muse Glimmer make a local agent that's blazing fast, always on, and gets things done. Go build and run a local agent on your own machine!🚀
0:32

AI at Meta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on NVIDIA AI Developer RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been the blockers for a local agent. SGLang and Muse Glimmer make a local agent that's blazing fast, always on, and gets things done. Go build and run a local agent on your own machine!🚀

LMSYS Org

44,226 просмотров • 2 месяцев назад

What does it take to build an AI factory ready for the agentic era? 80+ partners joined Jensen Huang at #NVIDIAGTC Taipei to show how NVIDIA MGX is making it possible. With NVIDIA Vera Rubin, 800 VDC, and partners spanning systems, power, and cooling, NVIDIA MGX is turning modular design into deployed AI infrastructure for the agentic AI era. ⚡ #NVIDIAGTC 🔗
0:38

What does it take to build an AI factory ready for the agentic era? 80+ partners joined Jensen Huang at #NVIDIAGTC Taipei to show how NVIDIA MGX is making it possible. With NVIDIA Vera Rubin, 800 VDC, and partners spanning systems, power, and cooling, NVIDIA MGX is turning modular design into deployed AI infrastructure for the agentic AI era. ⚡ #NVIDIAGTC 🔗

NVIDIA

145,062 просмотров • 4 месяцев назад

GLM-5.3 weights from Z.ai are live, with SGLang powering day-0 serving support! GLM-5.3 inherits every optimization and feature we battle-tested for GLM-5.2 over the past months. On real-world multi-turn agentic workloads, we measured 537.6 tok/s/user on NVFP4 and 413 tok/s/user on FP8, at BS=1 with TP8 on 8x B300. It's fast, efficient, and production-ready today on NVIDIA AI Blackwell and Hopper, and AI at AMD MI300X/325X/355X. We believe this is a big step forward for GLM-Series in agentic tasks, with a path toward mythos-class cyber capability. Can't wait to see what people build with GLM-5.3 and SGLang🚀 Cookbook👇
0:20

GLM-5.3 weights from Z.ai are live, with SGLang powering day-0 serving support! GLM-5.3 inherits every optimization and feature we battle-tested for GLM-5.2 over the past months. On real-world multi-turn agentic workloads, we measured 537.6 tok/s/user on NVFP4 and 413 tok/s/user on FP8, at BS=1 with TP8 on 8x B300. It's fast, efficient, and production-ready today on NVIDIA AI Blackwell and Hopper, and AI at AMD MI300X/325X/355X. We believe this is a big step forward for GLM-Series in agentic tasks, with a path toward mythos-class cyber capability. Can't wait to see what people build with GLM-5.3 and SGLang🚀 Cookbook👇

SGLang

99,455 просмотров • 2 месяцев назад

INSANE: Grok 3 + Lovable = BEST AI Agent Apps!!!! Grok 3 generated the code for an AI agent that manages your Gmail - send, reply, and draft effortlessly Here's how it works: - Connect with your Gmail using Composio - Use Lovable to build an extremely cool frontend for the Agent - Agentic workflow with LlamaIndex Built with LlamaIndex 🦙 To connect your agents with more tools like Gmail, use
1:09

INSANE: Grok 3 + Lovable = BEST AI Agent Apps!!!! Grok 3 generated the code for an AI agent that manages your Gmail - send, reply, and draft effortlessly Here's how it works: - Connect with your Gmail using Composio - Use Lovable to build an extremely cool frontend for the Agent - Agentic workflow with LlamaIndex Built with LlamaIndex 🦙 To connect your agents with more tools like Gmail, use

Karan Vaidya

62,030 просмотров • 1 год назад

Our CEO Jensen Huang and Dell Technologies Chairman & CEO Michael Dell kicked things off at #DellTechWorld in Las Vegas with a look at how the Dell AI Factory with NVIDIA is redefining how companies build, run, and scale AI. We saw NemoClaw powering agentic AI on-prem, robots demonstrating physical AI in the real world, and sessions packed with enterprise use cases.
0:30

Our CEO Jensen Huang and Dell Technologies Chairman & CEO Michael Dell kicked things off at #DellTechWorld in Las Vegas with a look at how the Dell AI Factory with NVIDIA is redefining how companies build, run, and scale AI. We saw NemoClaw powering agentic AI on-prem, robots demonstrating physical AI in the real world, and sessions packed with enterprise use cases.

NVIDIA

93,829 просмотров • 5 месяцев назад

Create and run LLMs locally? You can do it with #IntelCoreUltra Series 3 plus Intel AI Super Builder version 2.7, both released at #CES2026. Check out how we’re fine-tuning Intel AI Super Builder for use on our new processors.
0:37

Create and run LLMs locally? You can do it with #IntelCoreUltra Series 3 plus Intel AI Super Builder version 2.7, both released at #CES2026. Check out how we’re fine-tuning Intel AI Super Builder for use on our new processors.

Intel

14,635 просмотров • 8 месяцев назад

Open models are accelerating development and deployment across agentic AI, physical AI, and a growing range of industries. ✨ “We have billions of dollars of supercomputers in operation, so we can develop our open models,” said NVIDIA CEO Jensen Huang in a recent keynote. “That work is starting to attract attention across industries worldwide, as we build frontier AI models in many different domains.” This includes leading open models from NVIDIA, including: ⚙️ NVIDIA Nemotron for agentic AI ⚙️ NVIDIA Cosmos and GR00T for physical AI ⚙️ NVIDIA Alpamayo for autonomous vehicles ⚙️ NVIDIA Clara for biomedical AI Learn more about open source and AI ➡️
0:20

Open models are accelerating development and deployment across agentic AI, physical AI, and a growing range of industries. ✨ “We have billions of dollars of supercomputers in operation, so we can develop our open models,” said NVIDIA CEO Jensen Huang in a recent keynote. “That work is starting to attract attention across industries worldwide, as we build frontier AI models in many different domains.” This includes leading open models from NVIDIA, including: ⚙️ NVIDIA Nemotron for agentic AI ⚙️ NVIDIA Cosmos and GR00T for physical AI ⚙️ NVIDIA Alpamayo for autonomous vehicles ⚙️ NVIDIA Clara for biomedical AI Learn more about open source and AI ➡️

NVIDIA AI

19,296 просмотров • 9 месяцев назад

Laguna S 2.1 is built to run locally. We heard the ask for a serious open model in the 80–120B range. Laguna S 2.1 is our answer, and we want it to redefine what this size class can do. Weights ship in BF16, FP8, INT4 and NVFP4, with official GGUF and MLX conversions, plus official DFlash draft models for faster inference. Day-one support across llama.cpp, ollama, Valerie Lee Make Up, SGLang, NVIDIA TRT-LLM, Hugging Face transformers and ZML. Watch it run on an NVIDIA AI DGX Spark.
0:39

Laguna S 2.1 is built to run locally. We heard the ask for a serious open model in the 80–120B range. Laguna S 2.1 is our answer, and we want it to redefine what this size class can do. Weights ship in BF16, FP8, INT4 and NVFP4, with official GGUF and MLX conversions, plus official DFlash draft models for faster inference. Day-one support across llama.cpp, ollama, Valerie Lee Make Up, SGLang, NVIDIA TRT-LLM, Hugging Face transformers and ZML. Watch it run on an NVIDIA AI DGX Spark.

Poolside

31,242 просмотров • 3 месяцев назад

New agentic short course! Multi AI Agent Systems with crewAI, built with CrewAI's founder and CEO João Moura. In this course, you'll learn how to break down complex tasks into subtasks for multiple AI agents, each playing a specialized role, to execute. For example, to generate a research report, you might have researcher, writer, and quality assurance agents collaborate. You'll define the roles, expectations, and interactions between the agents—like a manager organizing a team. You'll work with key agentic AI techniques like role-playing, tool use, memory, guardrails, and cross-agent collaboration. And you'll build your own multi-agent systems that can tackle complex tasks. I think you'll find it both productive and fun to design agents and watch them collaborate to get things done. Let me know what you think! I believe multi-agent architectures will drive significant progress in AI systems. Please sign up here!
2:39

New agentic short course! Multi AI Agent Systems with crewAI, built with CrewAI's founder and CEO João Moura. In this course, you'll learn how to break down complex tasks into subtasks for multiple AI agents, each playing a specialized role, to execute. For example, to generate a research report, you might have researcher, writer, and quality assurance agents collaborate. You'll define the roles, expectations, and interactions between the agents—like a manager organizing a team. You'll work with key agentic AI techniques like role-playing, tool use, memory, guardrails, and cross-agent collaboration. And you'll build your own multi-agent systems that can tackle complex tasks. I think you'll find it both productive and fun to design agents and watch them collaborate to get things done. Let me know what you think! I believe multi-agent architectures will drive significant progress in AI systems. Please sign up here!

Andrew Ng

350,175 просмотров • 2 лет назад

Build and test applications faster with a multi-agent coding system. Gain direct experience with Google Antigravity at a Build with AI event and move from design to execution using an IDE with built-in gen AI. 🔹 Multi-agent coding system and IDE 🔹 Lab testing and app development 🔹 High model quotas Get started →
0:37

Build and test applications faster with a multi-agent coding system. Gain direct experience with Google Antigravity at a Build with AI event and move from design to execution using an IDE with built-in gen AI. 🔹 Multi-agent coding system and IDE 🔹 Lab testing and app development 🔹 High model quotas Get started →

Google for Developers

15,321 просмотров • 6 месяцев назад

Introducing Gemini 3 ✨ It’s the best model in the world for multimodal understanding, and our most powerful agentic + vibe coding model yet. Gemini 3 can bring any idea to life, quickly grasping context and intent so you can get what you need with less prompting. Find Gemini 3 Pro rolling out today in the Google Gemini and AI Mode in Search. For developers, build with it now in Google AI Studio and Vertex AI. Excited for you to try it!
0:51

Introducing Gemini 3 ✨ It’s the best model in the world for multimodal understanding, and our most powerful agentic + vibe coding model yet. Gemini 3 can bring any idea to life, quickly grasping context and intent so you can get what you need with less prompting. Find Gemini 3 Pro rolling out today in the Google Gemini and AI Mode in Search. For developers, build with it now in Google AI Studio and Vertex AI. Excited for you to try it!

Sundar Pichai

2,955,775 просмотров • 11 месяцев назад

Cetus is embracing the AI era. 🌊🐳 With Cetus Skills, AI agents can interact directly with our infrastructure and tap into different capabilities across swaps, liquidity, and on-chain execution for their own use cases. Around it, a wider AI-native network is starting to form across Sui — agent-ready wallet adapters, intent-based interfaces, AI strategies, data analytics, and other experiments are all connecting with #Cetus infra in different ways. These pieces may look separate today, but together they’re weaving a much more open and composable network for the agentic era. Cetus will keep exploring how our liquidity and trading infrastructure can become easier for both humans and AI agents to access, combine, and build on.
0:43

Cetus is embracing the AI era. 🌊🐳 With Cetus Skills, AI agents can interact directly with our infrastructure and tap into different capabilities across swaps, liquidity, and on-chain execution for their own use cases. Around it, a wider AI-native network is starting to form across Sui — agent-ready wallet adapters, intent-based interfaces, AI strategies, data analytics, and other experiments are all connecting with #Cetus infra in different ways. These pieces may look separate today, but together they’re weaving a much more open and composable network for the agentic era. Cetus will keep exploring how our liquidity and trading infrastructure can become easier for both humans and AI agents to access, combine, and build on.

Cetus🐳

21,669 просмотров • 9 дней назад

Meta is back with Muse Glimmer: a 30B open-source multimodal model built for local, agentic use. HF is shipping day-0 support and I built a few demos to see what it can do. First: we gave Glimmer tools and asked it to quantize itself.
0:30

Meta is back with Muse Glimmer: a 30B open-source multimodal model built for local, agentic use. HF is shipping day-0 support and I built a few demos to see what it can do. First: we gave Glimmer tools and asked it to quantize itself.

Ben Burtenshaw

51,554 просмотров • 2 месяцев назад