Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

What does it actually take to run A/B testing at nearly a billion-user scale? Prudhvi Vatala, Head of Engineering Platforms at Snap Inc., explains how his team migrated 10+ petabytes of daily data processing to GPU-accelerated pipelines on Google Cloud — cutting job costs by 76% and memory footprint... show more

NVIDIA

2,610,799 subscribers

50,091 просмотров • 2 месяцев назад •via X (Twitter)

Новости и политика Наука и технологии Финансы

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

What Lisa Su actually held on stage: A mini PC the size of a lunchbox running Qwen3-235B locally, with no cloud and no discrete GPU Inside: the Ryzen AI Max+ 395, 128GB unified memory, 110GB usable as VRAM on Linux The first x86 chip that handles 200+ billion parameters on a single die AMD claims it beats the RTX 5080 by several times on memory-bound models — because the 5080 simply cannot fit them $1,400 to $2,500 once. cloud bills run $200 to $400 a month It pays for itself in a few months, then costs nothing per request This is not a faster GPU. it is the first real argument that your AI does not belong in someone else's data center

What Lisa Su actually held on stage: A mini PC the size of a lunchbox running Qwen3-235B locally, with no cloud and no discrete GPU Inside: the Ryzen AI Max+ 395, 128GB unified memory, 110GB usable as VRAM on Linux The first x86 chip that handles 200+ billion parameters on a single die AMD claims it beats the RTX 5080 by several times on memory-bound models — because the 5080 simply cannot fit them $1,400 to $2,500 once. cloud bills run $200 to $400 a month It pays for itself in a few months, then costs nothing per request This is not a faster GPU. it is the first real argument that your AI does not belong in someone else's data center

plutos

1,236,133 просмотров • 1 месяц назад

What does it take to produce spacecraft at scale? At Rocket Lab, it takes expert teams, vertical integration, and a whole lot of precision. From structure and harnesses to full spacecraft assembly and testing—our team builds it all. Go behind the scenes with us 👇 📽️ Watch the full video

What does it take to produce spacecraft at scale? At Rocket Lab, it takes expert teams, vertical integration, and a whole lot of precision. From structure and harnesses to full spacecraft assembly and testing—our team builds it all. Go behind the scenes with us 👇 📽️ Watch the full video

Rocket Lab

54,486 просмотров • 1 год назад

Energy efficiency in LLM inference has improved 100,000x in the past 10 years — demonstrating that accelerated computing is sustainable computing. Josh Parker, head of sustainability at NVIDIA, explains how. #ClimateWeekNYC Learn more:

Energy efficiency in LLM inference has improved 100,000x in the past 10 years — demonstrating that accelerated computing is sustainable computing. Josh Parker, head of sustainability at NVIDIA, explains how. #ClimateWeekNYC Learn more:

NVIDIA

32,252 просмотров • 10 месяцев назад

What a week at #GoogleCloudNext in Las Vegas ✨ From sessions to showfloor demos to networking events, we were excited to partner with Google Cloud to advance how the AI ecosystem can build, deploy, and innovate in the cloud. Looking forward to working together to advance AI agents, physical AI, and beyond.

What a week at #GoogleCloudNext in Las Vegas ✨ From sessions to showfloor demos to networking events, we were excited to partner with Google Cloud to advance how the AI ecosystem can build, deploy, and innovate in the cloud. Looking forward to working together to advance AI agents, physical AI, and beyond.

NVIDIA

32,762 просмотров • 3 месяцев назад

Introducing the NVIDIA Project DIGITS personal AI supercomputer, powered by the GB10 Grace Blackwell Superchip: Project DIGITS enables developers to prototype, fine-tune and inference models locally and seamlessly deploy at scale to the data center or cloud. #CES2025 #NVIDIAGraceBlackwell

Introducing the NVIDIA Project DIGITS personal AI supercomputer, powered by the GB10 Grace Blackwell Superchip: Project DIGITS enables developers to prototype, fine-tune and inference models locally and seamlessly deploy at scale to the data center or cloud. #CES2025 #NVIDIAGraceBlackwell

NVIDIA

51,991 просмотров • 1 год назад

The universe is constantly unfolding—sending back more data and imagery than any team of scientists could ever interpret alone. AI and accelerated computing are changing that, helping researchers unlock discoveries at a scale and speed that wasn't possible before. 🔭 This #AstronomyDay, we're celebrating the scientists from UC Santa Cruz, Brant Robertson and his colleagues are turning cosmic complexity into real discovery, and making it available to everyone.

The universe is constantly unfolding—sending back more data and imagery than any team of scientists could ever interpret alone. AI and accelerated computing are changing that, helping researchers unlock discoveries at a scale and speed that wasn't possible before. 🔭 This #AstronomyDay, we're celebrating the scientists from UC Santa Cruz, Brant Robertson and his colleagues are turning cosmic complexity into real discovery, and making it available to everyone.

NVIDIA

24,456 просмотров • 3 месяцев назад

What MrBeast said. Sidekick changes entrepreneurship. It understands your store, Shopify, and commerce at scale. An AI cofounder in your pocket. Data, growth, ops. And everything else you need to run a business. Personalized. With voice mode, you run your business from your phone. Decisions in seconds. Scale in weeks. Powered by 20 years of Shopify intelligence. Only we could build this.

What MrBeast said. Sidekick changes entrepreneurship. It understands your store, Shopify, and commerce at scale. An AI cofounder in your pocket. Data, growth, ops. And everything else you need to run a business. Personalized. With voice mode, you run your business from your phone. Decisions in seconds. Scale in weeks. Powered by 20 years of Shopify intelligence. Only we could build this.

Harley Finkelstein

43,832 просмотров • 5 месяцев назад

The creator of High Bandwidth Memory (HBM) put a number on the AI build that should stop every infra investor cold. A cluster of a million GPUs runs at roughly 10-20% utilization (Save this). Kim Jung-ho spent thirty years building what feeds the GPU, and his claim is that the GPU is barely working. Here is what is actually happening. Every time a model generates output, the data has to be read out of memory, computed, and written back. The read and the write swallow almost the entire cycle. While that data moves, the GPU does nothing. It sits there, fully powered, fully paid for, waiting. By Kim's estimate the memory is doing only about 30 percent of the work it needs to do. The processor idles the rest. So a million installed GPUs run at 10 to 20 percent. You are not compute constrained. You are memory constrained, and the expensive part is standing around. Adding more GPUs does not fix this. It gives you more processors starving for the same data. Here is the part that decides the next decade. Memory can grow. When a cell cannot shrink any further, you stack it into a high-rise, layer on layer. A GPU cannot be stacked. It runs too hot and needs a cooler bolted to its back, so the one move that rescues memory is closed to the processor. The thing that can keep stacking compounds. The thing that cannot plateaus. The marginal dollar in an AI build now buys more by fixing the memory path than by bolting on another idle GPU. Which is why the companies that control memory bandwidth and supply are not suppliers to the AI trade. They are the AI trade.

The creator of High Bandwidth Memory (HBM) put a number on the AI build that should stop every infra investor cold. A cluster of a million GPUs runs at roughly 10-20% utilization (Save this). Kim Jung-ho spent thirty years building what feeds the GPU, and his claim is that the GPU is barely working. Here is what is actually happening. Every time a model generates output, the data has to be read out of memory, computed, and written back. The read and the write swallow almost the entire cycle. While that data moves, the GPU does nothing. It sits there, fully powered, fully paid for, waiting. By Kim's estimate the memory is doing only about 30 percent of the work it needs to do. The processor idles the rest. So a million installed GPUs run at 10 to 20 percent. You are not compute constrained. You are memory constrained, and the expensive part is standing around. Adding more GPUs does not fix this. It gives you more processors starving for the same data. Here is the part that decides the next decade. Memory can grow. When a cell cannot shrink any further, you stack it into a high-rise, layer on layer. A GPU cannot be stacked. It runs too hot and needs a cooler bolted to its back, so the one move that rescues memory is closed to the processor. The thing that can keep stacking compounds. The thing that cannot plateaus. The marginal dollar in an AI build now buys more by fixing the memory path than by bolting on another idle GPU. Which is why the companies that control memory bandwidth and supply are not suppliers to the AI trade. They are the AI trade.

Fireside Alpha

38,370 просмотров • 1 месяц назад

Chamath said AI is not like the internet. Every new user costs real money. And the infrastructure making it possible was built by everyone. His argument was the clearest case for government ownership of AI labs I have ever heard. And it had nothing to do with Bernie Sanders. Start with the internet comparison. Google and Facebook became the most profitable companies in human history because of one number. The marginal cost of adding a new user was effectively zero. One more search query cost Google nothing. One more Facebook profile cost Meta nothing. They could serve a billion people and the incremental cost of that billion person was rounding error. That is the money printer. Infinite scale at zero marginal cost. AI breaks that model completely. Every single user taxes a GPU. Every query costs electricity. Every response requires memory and compute. The marginal cost of AI is real, significant, and does not disappear at scale. You cannot print money the same way. Then Chamath made the point that landed hardest. The infrastructure these companies depend on, the power grid, the land, the data centers, the permitting, the national security apparatus that protects their chips from being stolen, none of that was built by Anthropic or OpenAI. It was built by the public. By taxpayers. By decades of government investment in the physical and legal foundation these companies are now running on. He compared it to the interstate highway system. If the federal government built the roads and two companies transported all the goods on them, a logical question at that point would be how much of that should I own? You are riding on my rails. His conclusion was direct. If he were running a sovereign wealth fund and had the negotiating leverage of the US government, he would own 75% of these companies when he was done. The internet had zero marginal cost. That is why the founders captured almost all of the value. AI has real marginal cost and runs on public infrastructure. That changes who has a claim on what gets built. WATCH THE FULL PODCAST ON The All-In Podcast

Ihtesham Ali

79,066 просмотров • 1 месяц назад

Chamath Palihapitiya just dropped the number that explains the entire AI infrastructure trade (Save this). A gigawatt of compute now costs $100 billion and when he started his Arizona data center project it was $4 to $5 billion, it has gone up 20x in a single investment cycle. The implication is not just that AI infrastructure is expensive but rather that the capital barrier to owning meaningful compute has become so high that only a handful of entities in the world can actually build it and the companies who got there early are sitting on what may be the most durable pricing power in the history of the technology industry. This is the neocloud trade. The neocloud market, purpose-built GPU cloud providers like CoreWeave, Nebius, and Lambda Labs was worth $35 billion in 2026 and is projected to reach $236 billion by 2031, compounding at 46% annually. For context, that is faster growth than cloud computing itself posted in its first decade. The reason is very simple, hyperscalers like AWS, Azure, and Google are building for everything, storage, databases, enterprise software, networking and their GPU pricing reflects the overhead of that full-stack infrastructure. Neoclouds build for one thing only, AI compute. The result is a 60% to 85% cost advantage on the same Nvidia silicon, bare metal H100s at $0.78 to $2.79 per GPU-hour on a neocloud versus $3.43 to $5.07 per GPU-hour on a hyperscaler. That spread does not close as AI demand scales but rather it widens, because hyperscalers have to amortize legacy infrastructure and margin expectations that neoclouds do not carry. Gartner projects that by 2030, neoclouds will capture 20% of the $267 billion AI cloud market, and Vultr's own analysis says at least 80% of GPU market share by end of 2026 will be held by a small group of scaled neocloud providers. Now zoom into Nebius specifically, because it is the most interesting publicly traded proxy for this trade. Nebius is the infrastructure arm of the former Yandex Russia's equivalent of Google rebuilt from the ground up after Russia's invasion of Ukraine by Arkady Volozh and relisted on Nasdaq in October 2024. The team that built it already knew how to run internet-scale infrastructure at the lowest possible cost, which is exactly the operational DNA a neocloud requires. In Q1 2026, Nebius reported revenue of $399 million and already generating serious cash on a young business with revenue growing nearly eightfold year-over-year. Then in March 2026, Meta signed a five-year infrastructure agreement with Nebius worth up to $27 billion, $12 billion in committed dedicated GPU capacity deployments beginning early 2027, plus up to $15 billion more tied to Meta purchasing Nebius's unsold third-party capacity. The deal will be executed on one of the first large-scale deployments of Nvidia's Vera Rubin platform, the next-generation architecture after Blackwell making Nebius one of a tiny number of operators in the world with confirmed priority access to the most advanced AI hardware available. Following the contract, Nebius guided to $7 to $9 billion in annualized recurring revenue for 2026 representing 540% year-over-year growth. Chamath Palihapitiya point about the $100 billion capital moat is the bear case for new entrants and the bull case for incumbents. No one can afford to build the next CoreWeave or Nebius from scratch at current hardware and power costs. The companies that are already built, already contracted, and already deploying Nvidia's latest silicon have a moat that compounds with every GPU generation cycle because they get allocations first, they deploy fastest, and their customers re-sign rather than wait for a new operator that does not yet exist. Come join Milk Road Pro for our full breakdown, the complete neocloud competitive landscape, how to think about Nebius's valuation versus CoreWeave and AI entire thesis. Link below.

Chamath Palihapitiya just dropped the number that explains the entire AI infrastructure trade (Save this). A gigawatt of compute now costs $100 billion and when he started his Arizona data center project it was $4 to $5 billion, it has gone up 20x in a single investment cycle. The implication is not just that AI infrastructure is expensive but rather that the capital barrier to owning meaningful compute has become so high that only a handful of entities in the world can actually build it and the companies who got there early are sitting on what may be the most durable pricing power in the history of the technology industry. This is the neocloud trade. The neocloud market, purpose-built GPU cloud providers like CoreWeave, Nebius, and Lambda Labs was worth $35 billion in 2026 and is projected to reach $236 billion by 2031, compounding at 46% annually. For context, that is faster growth than cloud computing itself posted in its first decade. The reason is very simple, hyperscalers like AWS, Azure, and Google are building for everything, storage, databases, enterprise software, networking and their GPU pricing reflects the overhead of that full-stack infrastructure. Neoclouds build for one thing only, AI compute. The result is a 60% to 85% cost advantage on the same Nvidia silicon, bare metal H100s at $0.78 to $2.79 per GPU-hour on a neocloud versus $3.43 to $5.07 per GPU-hour on a hyperscaler. That spread does not close as AI demand scales but rather it widens, because hyperscalers have to amortize legacy infrastructure and margin expectations that neoclouds do not carry. Gartner projects that by 2030, neoclouds will capture 20% of the $267 billion AI cloud market, and Vultr's own analysis says at least 80% of GPU market share by end of 2026 will be held by a small group of scaled neocloud providers. Now zoom into Nebius specifically, because it is the most interesting publicly traded proxy for this trade. Nebius is the infrastructure arm of the former Yandex Russia's equivalent of Google rebuilt from the ground up after Russia's invasion of Ukraine by Arkady Volozh and relisted on Nasdaq in October 2024. The team that built it already knew how to run internet-scale infrastructure at the lowest possible cost, which is exactly the operational DNA a neocloud requires. In Q1 2026, Nebius reported revenue of $399 million and already generating serious cash on a young business with revenue growing nearly eightfold year-over-year. Then in March 2026, Meta signed a five-year infrastructure agreement with Nebius worth up to $27 billion, $12 billion in committed dedicated GPU capacity deployments beginning early 2027, plus up to $15 billion more tied to Meta purchasing Nebius's unsold third-party capacity. The deal will be executed on one of the first large-scale deployments of Nvidia's Vera Rubin platform, the next-generation architecture after Blackwell making Nebius one of a tiny number of operators in the world with confirmed priority access to the most advanced AI hardware available. Following the contract, Nebius guided to $7 to $9 billion in annualized recurring revenue for 2026 representing 540% year-over-year growth. Chamath Palihapitiya point about the $100 billion capital moat is the bear case for new entrants and the bull case for incumbents. No one can afford to build the next CoreWeave or Nebius from scratch at current hardware and power costs. The companies that are already built, already contracted, and already deploying Nvidia's latest silicon have a moat that compounds with every GPU generation cycle because they get allocations first, they deploy fastest, and their customers re-sign rather than wait for a new operator that does not yet exist. Come join Milk Road Pro for our full breakdown, the complete neocloud competitive landscape, how to think about Nebius's valuation versus CoreWeave and AI entire thesis. Link below.

Milk Road AI

138,663 просмотров • 1 месяц назад

📣 We are collaborating with the Naval Postgraduate School to empower thousands of students to work and build applications with AI. Hear from Todd Lyons, EVP at the NPS Foundation & Alumni Association, on how #NVIDIADGX and NVIDIA Omniverse are helping to create synthetic data, train tailored foundational models, and deploy solutions at scale for the public sector.

📣 We are collaborating with the Naval Postgraduate School to empower thousands of students to work and build applications with AI. Hear from Todd Lyons, EVP at the NPS Foundation & Alumni Association, on how #NVIDIADGX and NVIDIA Omniverse are helping to create synthetic data, train tailored foundational models, and deploy solutions at scale for the public sector.

NVIDIA

59,320 просмотров • 1 месяц назад

A Google Cloud engineer just showed how to build a full app with Claude from scratch he spent 26 minutes live on stage doing what most teams take weeks to do worth more than any $500 vibe-coding course here's what he covers: > zero to deployed app in a single session > handling five engineering roles alone with Claude > the exact workflow Google uses internally > no team, no setup, just Claude and a goal the people who figure out what Claude can actually do are building things everyone else thinks requires a team that's exactly why I wrote a step by step guide on how to build your first AI agent the guide is in the article below

A Google Cloud engineer just showed how to build a full app with Claude from scratch he spent 26 minutes live on stage doing what most teams take weeks to do worth more than any $500 vibe-coding course here's what he covers: > zero to deployed app in a single session > handling five engineering roles alone with Claude > the exact workflow Google uses internally > no team, no setup, just Claude and a goal the people who figure out what Claude can actually do are building things everyone else thinks requires a team that's exactly why I wrote a step by step guide on how to build your first AI agent the guide is in the article below

Anatoli Kopadze

458,531 просмотров • 1 месяц назад

Every day, millions of videos compete for advertising dollars. Ensuring brands appear alongside the right content requires AI that can understand context at scale. PYLER is helping advertisers improve brand safety and campaign performance with NVIDIA-accelerated AI that analyzes video content in near real time. 🎯 Driving smarter advertising with AI ⚡ Analyzes 2M videos daily for contextual understanding and brand-safe placements 🛡️ Reduced unsafe content exposure by 76.7% for major advertisers 💰 Cut operational costs by 10X while accelerating content validation from seconds to milliseconds Built on the NVIDIA AI platform, PYLER is helping brands and marketers scale trust, transparency, and performance across digital video advertising.

NVIDIA

48,142 просмотров • 1 месяц назад

APPLE JUST SHOWED HOW TO RUN 10 AI AGENTS LOCALLY ON MAC - NO CLOUD, NO API KEYS, ZERO COSTS 00:10 Apple engineer says: "your data stays on your device, AI available anywhere at any time, zero usage costs" agent reads your code, checks GitHub, finds what needs attention and writes a report - all on your Mac, nothing goes to the internet 10 agents work simultaneously - one writes code, another tests, third fixes bugs - parallel with no queue built a full iPad app from scratch in 2 minutes, fixed its own mistakes and compiled without issues takes 5 minutes to set up - and you never pay again for a bot that runs 24/7

APPLE JUST SHOWED HOW TO RUN 10 AI AGENTS LOCALLY ON MAC - NO CLOUD, NO API KEYS, ZERO COSTS 00:10 Apple engineer says: "your data stays on your device, AI available anywhere at any time, zero usage costs" agent reads your code, checks GitHub, finds what needs attention and writes a report - all on your Mac, nothing goes to the internet 10 agents work simultaneously - one writes code, another tests, third fixes bugs - parallel with no queue built a full iPad app from scratch in 2 minutes, fixed its own mistakes and compiled without issues takes 5 minutes to set up - and you never pay again for a bot that runs 24/7

Noisy

524,181 просмотров • 1 месяц назад

AI UGC has reached a point where it outperforms traditional UGC on both cost AND quality this video is 100% AI and cost under $5 with my new system we can mass produce ads and scale offers across dozens of accounts while constantly testing new GEOs what used to take weeks can now be done in a few hours, while cutting costs by 99%

AI UGC has reached a point where it outperforms traditional UGC on both cost AND quality this video is 100% AI and cost under $5 with my new system we can mass produce ads and scale offers across dozens of accounts while constantly testing new GEOs what used to take weeks can now be done in a few hours, while cutting costs by 99%

MAX

29,622 просмотров • 2 месяцев назад

A Google Cloud engineer just showed how to build a full app with Claude from scratch. He spent 26 minutes live on stage doing what most teams take weeks to do. Worth more than any $500 vibe-coding course, no team, no setup, just Claude and a goal. The ones who learn what Claude actually does are shipping what everyone else outsources to a team. Watch it, then read the guide below on the Claude features 99% of users never find.

A Google Cloud engineer just showed how to build a full app with Claude from scratch. He spent 26 minutes live on stage doing what most teams take weeks to do. Worth more than any $500 vibe-coding course, no team, no setup, just Claude and a goal. The ones who learn what Claude actually does are shipping what everyone else outsources to a team. Watch it, then read the guide below on the Claude features 99% of users never find.

Anatoli Kopadze

405,336 просмотров • 14 дней назад

TWO BOXES THE SIZE OF A MAC MINI JUST RAN A 235 BILLION PARAMETER MODEL ON A DESK It is two NVIDIA DGX Spark units linked by a single cable. A year ago a model this size meant renting a GPU cluster by the hour. Now it sits next to your monitor for around $8,000. Here is the twist most people miss. Linking them does not create one shared 256GB memory pool. The model is split across both boxes, and that is the only reason a 235B model fits at all. It answers at roughly 10 tokens per second, and both chips sit at just 74 degrees while sipping around 50 watts. Every token stays on the desk. Nothing touches a cloud, and nothing leaves the room. The ceiling for what you can run at home just jumped from 70B to 235B. Bookmark this & Watch it run ↓

TWO BOXES THE SIZE OF A MAC MINI JUST RAN A 235 BILLION PARAMETER MODEL ON A DESK It is two NVIDIA DGX Spark units linked by a single cable. A year ago a model this size meant renting a GPU cluster by the hour. Now it sits next to your monitor for around $8,000. Here is the twist most people miss. Linking them does not create one shared 256GB memory pool. The model is split across both boxes, and that is the only reason a 235B model fits at all. It answers at roughly 10 tokens per second, and both chips sit at just 74 degrees while sipping around 50 watts. Every token stays on the desk. Nothing touches a cloud, and nothing leaves the room. The ceiling for what you can run at home just jumped from 70B to 235B. Bookmark this & Watch it run ↓

slash1s

101,240 просмотров • 1 месяц назад

As machine learning models grow in size, so too does their carbon footprint. As AI scales, it's important that we quantify and mitigate these emissions. In our new short course Carbon Aware Computing for GenAI Developers you'll learn from Google Cloud Developer Advocate Nikita Namjoshi how to: - Query the ElectricityMaps API for real-time data on regional electricity grid carbon intensity - Route your model training jobs to data centers in regions primarily powered by low-carbon sources like wind, solar, hydro and nuclear - Measure the carbon footprint of your ML training, inference, storage and API usage with the Google Cloud's Carbon Footprint tool - Optimize training job scheduling to run when clean energy is most abundant in a given region. You can sign up here:

As machine learning models grow in size, so too does their carbon footprint. As AI scales, it's important that we quantify and mitigate these emissions. In our new short course Carbon Aware Computing for GenAI Developers you'll learn from Google Cloud Developer Advocate Nikita Namjoshi how to: - Query the ElectricityMaps API for real-time data on regional electricity grid carbon intensity - Route your model training jobs to data centers in regions primarily powered by low-carbon sources like wind, solar, hydro and nuclear - Measure the carbon footprint of your ML training, inference, storage and API usage with the Google Cloud's Carbon Footprint tool - Optimize training job scheduling to run when clean energy is most abundant in a given region. You can sign up here:

Andrew Ng

105,900 просмотров • 2 лет назад

Full Stack Verifiability | Verifiable Cloud ☁️ Sreeram Kannan explains how EigenCloud delivers verifiability across the entire stack. It starts at the base with the EigenLayer, where computation is guaranteed by a decentralized network of hundreds of operators backed by $12B of stake. That’s the trust foundation of the cloud. On top of this: ✅ EigenDA: a data availability protocol that guarantees verifiable data publication.Publish data once, and anyone can retrieve it without trust. ✅ EigenCompute: execute arbitrary programs off-chain and bring the results back onchain verifiably. ✅ EigenAI: run AI inference today and return inference outputs directly onchain. All of them deliver strong verifiability for computation, inference, and data, all anchored by the underlying decentralized layer. And it doesn’t stop at first-party services, EigenCloud includes a growing ecosystem of third-party systems like zkTLS, proof-of-location, and decentralized prover networks, adding even deeper verification guarantees throughout the cloud. This is what a fully verifiable cloud looks like. A cloud you can check, not just trust.

Full Stack Verifiability | Verifiable Cloud ☁️ Sreeram Kannan explains how EigenCloud delivers verifiability across the entire stack. It starts at the base with the EigenLayer, where computation is guaranteed by a decentralized network of hundreds of operators backed by $12B of stake. That’s the trust foundation of the cloud. On top of this: ✅ EigenDA: a data availability protocol that guarantees verifiable data publication.Publish data once, and anyone can retrieve it without trust. ✅ EigenCompute: execute arbitrary programs off-chain and bring the results back onchain verifiably. ✅ EigenAI: run AI inference today and return inference outputs directly onchain. All of them deliver strong verifiability for computation, inference, and data, all anchored by the underlying decentralized layer. And it doesn’t stop at first-party services, EigenCloud includes a growing ecosystem of third-party systems like zkTLS, proof-of-location, and decentralized prover networks, adding even deeper verification guarantees throughout the cloud. This is what a fully verifiable cloud looks like. A cloud you can check, not just trust.

EigenCloud

47,983 просмотров • 8 месяцев назад

What does it take to run 3, 5, or even 10 concurrent instances of Gemma 4 locally? We've open-sourced a demo letting you run multiple models side-by-side on your hardware. Gemma 4 26B A4B easily runs 10+ concurrent requests on a MacBook Pro M4 Max at 18 tokens/sec per request.

What does it take to run 3, 5, or even 10 concurrent instances of Gemma 4 locally? We've open-sourced a demo letting you run multiple models side-by-side on your hardware. Gemma 4 26B A4B easily runs 10+ concurrent requests on a MacBook Pro M4 Max at 18 tokens/sec per request.

Google Gemma

913,368 просмотров • 3 месяцев назад