Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

A Google Pixel 1 from 2016 is now running iOS 16 with GPU acceleration.😱 The developer ported Mesa’s open-source Freedreno driver to power the Adreno 530 GPU, bringing smoother UI rendering and boot times of around 20 seconds. GitHub: Still a work in progress. Wi-Fi, cellular, camera, audio and... show more

Aman

11,048 subscribers

93,489 görüntüleme • 18 gün önce •via X (Twitter)

Sanat Eğitim Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

32 Yorum

Marlow Marlena profil fotoğrafı

Marlow Marlena18 gün önce

It funny because that pixel looks a lot like old iPhone designs

Aman profil fotoğrafı

Aman17 gün önce

Those massive forehead and chin bezels definitely give strong iPhone 7 vibes haha

ilikenwf profil fotoğrafı

ilikenwf18 gün önce

The next gen of knockoff iphones is going to be insane.

Aman profil fotoğrafı

Aman17 gün önce

Imagine buying a clone and it's literally running real iOS instead of a sketchy reskinned Android💀

Mama mo Gray profil fotoğrafı

Mama mo Gray17 gün önce

I thought that was old models of iPhone due to the bezels ahahaha

Aman profil fotoğrafı

Aman17 gün önce

Those iconic 2016 bezels make it fit iOS UI way too naturally haha 💀😂

Rudi profil fotoğrafı

Rudi18 gün önce

Is the GPU acceleration in the room with us?

Aman profil fotoğrafı

Aman17 gün önce

It actually is! Mesa Freedreno handling the Adreno 530 is what keeps the UI compositor from completely crawling on software rendering

j0sh1x profil fotoğrafı

j0sh1x18 gün önce

This has been a thing on HD2 since a week just noone knew it lol

Aman profil fotoğrafı

Aman17 gün önce

The classic HTC HD2 legacy lives on—if hardware exists, people will force an OS onto it! 😂

christian p profil fotoğrafı

christian p18 gün önce

With HW accel? insane work!

Aman profil fotoğrafı

Aman17 gün önce

Tell me you didn't read the Freedreno commit without telling me you didn't read it

vivid profil fotoğrafı

vivid17 gün önce

anything but using the unlimited cloud storage it comes with

Aman profil fotoğrafı

Aman17 gün önce

Gotta keep the lifetime original-quality Google Photos backup holy, but side quests first

azaad_media profil fotoğrafı

azaad_media18 gün önce

💐👍

Aman profil fotoğrafı

Aman17 gün önce

🙌✨

★x profil fotoğrafı

★x17 gün önce

@nosoyeleladio mira mira pixa cada día que pasa empieza a ir mejor, tu manzanita se va a quedar sin monopolio >:)

Jerry profil fotoğrafı

Jerry18 gün önce

That’s very crazy

Aman profil fotoğrafı

Aman17 gün önce

Wild times in the cross-platform scene right now

Miracast profil fotoğrafı

Miracast18 gün önce

这倒是真的还是假的

Aman profil fotoğrafı

Aman17 gün önce

It's 100% real! The project is open-source on GitHub, powered by the Mesa Freedreno driver for Adreno 530 GPU hardware acceleration

Makinde profil fotoğrafı

Makinde17 gün önce

@Elewur3 Google pixel 1 or iPhone se 1 or iPhone 7?

Manolo doble V profil fotoğrafı

Manolo doble V17 gün önce

se ve que es un video, no es el sistema operativo

Aman profil fotoğrafı

Aman17 gün önce

Not a video! It’s actually running live with real hardware acceleration via Mesa Freedreno check the open-source GitHub repo in the post

Poppy from DreamWorks' Trolls x Maychelle 🤯 profil fotoğrafı

Poppy from DreamWorks' Trolls x Maychelle 🤯17 gün önce

Hacked ROM what!? 🤣 @MrSujano

jdfrmtha509 profil fotoğrafı

jdfrmtha50917 gün önce

With how dark the video is it almost, just almost, looks like an iPhone 8/SE2/3

Spawn Lau profil fotoğrafı

Spawn Lau17 gün önce

Anyone remember when someone got the iOS kernel running on a Nokia back in 2013? That was wild.

cursedfrogdayo profil fotoğrafı

cursedfrogdayo17 gün önce

Shut the fuck up cuck coder

c.c_630 profil fotoğrafı

c.c_63017 gün önce

看起來還是好卡

Dave profil fotoğrafı

Dave17 gün önce

Dont kid yourself. Its a aosp skin

monter profil fotoğrafı

monter17 gün önce

بس بطيئ.. شو الفايدة

Adrian profil fotoğrafı

Adrian17 gün önce

Działa to za dużo powiedziane

Benzer Videolar

After improving my GPU driver patch, the iOS VM now has fully* working Metal rendering 🥹 * WebKit rendering is still broken, but it's the only broken thing I could find

After improving my GPU driver patch, the iOS VM now has fully* working Metal rendering 🥹 * WebKit rendering is still broken, but it's the only broken thing I could find

Guilherme Rambo

22,344 görüntüleme • 9 ay önce

Beam (Beam) is an open source serverless platform for AI apps. Run GPU inference, background jobs, and sandboxes with ultrafast boot times and no vendor lock-in.

Beam (Beam) is an open source serverless platform for AI apps. Run GPU inference, background jobs, and sandboxes with ultrafast boot times and no vendor lock-in.

Y Combinator

11,965 görüntüleme • 11 ay önce

Ray tracing sound on the GPU (Work in progress). Since the whole game is running on the GPU, I found it convenient to do the sound management and the ray tracing on the GPU as well. Each frame the CPU receives a sound queue from the GPU to process, and applies effects like reverb

Ray tracing sound on the GPU (Work in progress). Since the whole game is running on the GPU, I found it convenient to do the sound management and the ray tracing on the GPU as well. Each frame the CPU receives a sound queue from the GPU to process, and applies effects like reverb

xima

19,839 görüntüleme • 2 yıl önce

$RTX 3090 was never designed to be a server GPU. Yet someone just built a 4-GPU AI workstation around four of them. 4× RTX 3090 96GB VRAM 256GB ECC RAM AMD EPYC 7K62 2000W PSU 11 fans The interesting part isn't the performance. It's the memory. Four 24GB cards can be found for a fraction of what you'd pay for modern datacenter GPUs with similar total VRAM. The catch is obvious: 96GB doesn't behave like one 96GB GPU. You still have to deal with GPU-to-GPU communication, power and heat. But for local AI, this is exactly why the 3090 refuses to disappear. Would you build this today?$

RTX 3090 was never designed to be a server GPU. Yet someone just built a 4-GPU AI workstation around four of them. 4× RTX 3090 96GB VRAM 256GB ECC RAM AMD EPYC 7K62 2000W PSU 11 fans The interesting part isn't the performance. It's the memory. Four 24GB cards can be found for a fraction of what you'd pay for modern datacenter GPUs with similar total VRAM. The catch is obvious: 96GB doesn't behave like one 96GB GPU. You still have to deal with GPU-to-GPU communication, power and heat. But for local AI, this is exactly why the 3090 refuses to disappear. Would you build this today?

KyzoroX

36,552 görüntüleme • 2 ay önce

Audio Transcription with Google Gemini 1.5 Flash In this video, Gemini-Flash was able to transcribe 13 minutes of audio in 50-60 seconds. I have tested this with multiple audio files, and the transcription accuracy is close to 99%. If the audio is clear, you get 100% correct transcription. Even if the audio is really bad with a lot of noise, you still get around 95-96% accuracy. The code for this is available on GitHub. If you're interested, you can download and run it. You just need a Google API key.

Audio Transcription with Google Gemini 1.5 Flash In this video, Gemini-Flash was able to transcribe 13 minutes of audio in 50-60 seconds. I have tested this with multiple audio files, and the transcription accuracy is close to 99%. If the audio is clear, you get 100% correct transcription. Even if the audio is really bad with a lot of noise, you still get around 95-96% accuracy. The code for this is available on GitHub. If you're interested, you can download and run it. You just need a Google API key.

AshutoshShrivastava

123,061 görüntüleme • 2 yıl önce

Revolutionizing Access to #GPU Power - One Node at a Time.⚡️ Our 10th Utility is coming out on June 20.🚨 BIG GPU Nodes Platform isn’t just another name in the crowded GPU cloud services space, we’re a game-changer. Our platform is purpose-built to bridge the gap between server owners and those hungry for raw, high-performance computing power. 🖥️ We specialize in connecting suppliers from individual server owners to enterprise-scale GPU rig operators with consumers who demand serious horsepower for AI, machine learning, data science, and other compute-heavy applications. Whether you’re offering a sleek single-GPU setup or a massive mining-style array with multiple GPUs, BIG GPU Nodes is your launchpad. We make it simple to rent out underutilized GPU resources and just as easy for users to find exactly what they need — fast, affordable, and tailored to their workload.⛓️‍💥 This is more than cloud computing. This is decentralized GPU power for the future of innovation. ♾️ This product will generate revenue and we will give back to our loyal $CNCT holders. ✨ We’re proud to have MESSIER | M87 as our trusted partner and advisor, backing us with this vision. #M87 🤝 $CNCT From the very beginning, we promised you ONE BIG ECOSYSTEM, and a seamless space where everything you need comes together. Now, that vision is becoming reality. Millions of users will soon be connected, working, creating, and thriving within it. 🌍

Revolutionizing Access to #GPU Power - One Node at a Time.⚡️ Our 10th Utility is coming out on June 20.🚨 BIG GPU Nodes Platform isn’t just another name in the crowded GPU cloud services space, we’re a game-changer. Our platform is purpose-built to bridge the gap between server owners and those hungry for raw, high-performance computing power. 🖥️ We specialize in connecting suppliers from individual server owners to enterprise-scale GPU rig operators with consumers who demand serious horsepower for AI, machine learning, data science, and other compute-heavy applications. Whether you’re offering a sleek single-GPU setup or a massive mining-style array with multiple GPUs, BIG GPU Nodes is your launchpad. We make it simple to rent out underutilized GPU resources and just as easy for users to find exactly what they need — fast, affordable, and tailored to their workload.⛓️‍💥 This is more than cloud computing. This is decentralized GPU power for the future of innovation. ♾️ This product will generate revenue and we will give back to our loyal $CNCT holders. ✨ We’re proud to have MESSIER | M87 as our trusted partner and advisor, backing us with this vision. #M87 🤝 $CNCT From the very beginning, we promised you ONE BIG ECOSYSTEM, and a seamless space where everything you need comes together. Now, that vision is becoming reality. Millions of users will soon be connected, working, creating, and thriving within it. 🌍

Fixera AI

26,682 görüntüleme • 1 yıl önce

Few lenders, if any, have reviewed more GPU deals than USDAI: ~700 and $25B in demand. The data led to one revelation: Power and capital aren’t what’s holding back compute credit. The cost of structuring each GPU-backed loan is. USDAI is bringing the cost down.

Few lenders, if any, have reviewed more GPU deals than USDAI: ~700 and $25B in demand. The data led to one revelation: Power and capital aren’t what’s holding back compute credit. The cost of structuring each GPU-backed loan is. USDAI is bringing the cost down.

USD.AI

21,260 görüntüleme • 25 gün önce

AI Devs, this one’s for you. AMD is bringing together serious AI infrastructure and a real developer community. Join the AMD AI Developer Program to get $100 in cloud credits, monthly GPU sweepstakes, and more.

AI Devs, this one’s for you. AMD is bringing together serious AI infrastructure and a real developer community. Join the AMD AI Developer Program to get $100 in cloud credits, monthly GPU sweepstakes, and more.

AI at AMD

2,705,816 görüntüleme • 9 ay önce

Gemini 4 Argon + Flutter is cracked. Google Antigravity built this car infotainment screen and driver cluster with Flutter Scene in a day. It's all one Flutter app. :) The map uses real OpenStreetMap buildings in downtown Boston and a live route from OSRM. The x-ray chassis uses a custom material, and the brake discs glow as the car brakes. The car is a glTF model with working doors, hood, hatch, headlights, and paint options. The parking screen is a mockup of a 360 surround camera view. No embedded engine, no native map SDK, no platform views, just vanilla Flutter with Impeller and built-in SDK features: Flutter GPU. 3D rendered by Flutter Scene, a complete 3D game engine for Flutter. The app is 14,000 lines of Dart, with a center screen, a driver cluster, and a panoramic view of both. No subscriptions, no paid seats, no royalties. Free and open source, forever. Flutter can just do it all.

Gemini 4 Argon + Flutter is cracked. Google Antigravity built this car infotainment screen and driver cluster with Flutter Scene in a day. It's all one Flutter app. :) The map uses real OpenStreetMap buildings in downtown Boston and a live route from OSRM. The x-ray chassis uses a custom material, and the brake discs glow as the car brakes. The car is a glTF model with working doors, hood, hatch, headlights, and paint options. The parking screen is a mockup of a 360 surround camera view. No embedded engine, no native map SDK, no platform views, just vanilla Flutter with Impeller and built-in SDK features: Flutter GPU. 3D rendered by Flutter Scene, a complete 3D game engine for Flutter. The app is 14,000 lines of Dart, with a center screen, a driver cluster, and a panoramic view of both. No subscriptions, no paid seats, no royalties. Free and open source, forever. Flutter can just do it all.

Brandon DeRosier

38,051 görüntüleme • 26 gün önce

I tested this on the 4070 Super, and while there is a performance difference, it’s not huge. The GPU also pulls more power on the older driver. If you’re using Path Tracing and have a higher-power 40 series GPU, it’s still worth trying, you might see a bigger performance boost.

I tested this on the 4070 Super, and while there is a performance difference, it’s not huge. The GPU also pulls more power on the older driver. If you’re using Path Tracing and have a higher-power 40 series GPU, it’s still worth trying, you might see a bigger performance boost.

BenchmarKing

54,108 görüntüleme • 8 ay önce

I got Llama 3 running in my browser using only my GPU with my Wi-Fi switched OFF completely client-side WebGPU is a new feature in browsers where JS can use the GPU of the device and apparently you can run LLMs on it too, and it's fast! My end goal for 🧠 is a locally run client side 100% private conversation where nothing gets sent to, processed in or stored in the cloud This will be helpful because I prefer making it web based instead of coding for 4 different native platforms (iOS, Android, MacOS, Windows) Two challenges still: 1) the user has to download the LLM model first and the smallest model is still ~3GB, but they only have to download it once 2) not all devices have fast GPUs yet for LLMs, but it's starting to become a default in most devices e.g.s smartphones

I got Llama 3 running in my browser using only my GPU with my Wi-Fi switched OFF completely client-side WebGPU is a new feature in browsers where JS can use the GPU of the device and apparently you can run LLMs on it too, and it's fast! My end goal for 🧠 is a locally run client side 100% private conversation where nothing gets sent to, processed in or stored in the cloud This will be helpful because I prefer making it web based instead of coding for 4 different native platforms (iOS, Android, MacOS, Windows) Two challenges still: 1) the user has to download the LLM model first and the smallest model is still ~3GB, but they only have to download it once 2) not all devices have fast GPUs yet for LLMs, but it's starting to become a default in most devices e.g.s smartphones

@levelsio

261,483 görüntüleme • 2 yıl önce

Hi all, I wanted to share my first open source Swift package, it’s a fork of DialKit by joshpuckett shoutout to the amazing work by Josh and the other contributors, Josh reached out to me if I was interested in working on the iOS version, this is work in progress, and I’m a designer so would love feedback on ways to improve this

Hi all, I wanted to share my first open source Swift package, it’s a fork of DialKit by joshpuckett shoutout to the amazing work by Josh and the other contributors, Josh reached out to me if I was interested in working on the iOS version, this is work in progress, and I’m a designer so would love feedback on ways to improve this

Mike Lee

64,151 görüntüleme • 7 ay önce

I made a Mac app for fx, the coding agent from Vercel. fx-ui runs libfx inside the app and draws every pixel on the GPU through GPUIX. Bring a Grok or Codex subscription, or a Vercel AI Gateway key. It's open source:

I made a Mac app for fx, the coding agent from Vercel. fx-ui runs libfx inside the app and draws every pixel on the GPU through GPUIX. Bring a Grok or Codex subscription, or a Vercel AI Gateway key. It's open source:

Zaid

15,322 görüntüleme • 1 ay önce

Open a Linux terminal and type: watch -d -n 1 sensors This displays CPU, GPU, Wi-Fi, NVMe SSD, and HDD temperature data in real time. See for more info. #Linux #opensource

Open a Linux terminal and type: watch -d -n 1 sensors This displays CPU, GPU, Wi-Fi, NVMe SSD, and HDD temperature data in real time. See for more info. #Linux #opensource

nixCraft 🐧

53,825 görüntüleme • 1 yıl önce

From iOS 6 to Symbian. Pocket Shell now runs on a 2011 Nokia E7, with the same full-screen gestures and fluid animations as the iPod touch 4. This is what cross-platform JavaScript UI could feel like.

From iOS 6 to Symbian. Pocket Shell now runs on a 2011 Nokia E7, with the same full-screen gestures and fluid animations as the iPod touch 4. This is what cross-platform JavaScript UI could feel like.

PocketJS

319,234 görüntüleme • 1 ay önce

2.78 TRILLION parameter AI running on just 8GB RAM 😳 Meet kimi-k3-in-c , a free open-source project that runs Kimi K3 on a CPU. what you get : → Full 2.78T parameter model → Around 8.24GB RAM, no GPU → Just 176KB of C code → No PyTorch or CUDA → Supports Linux, macOS and Windows how to try it :) 1. Clone the GitHub repo 2. Run "make" 3. Run "./scripts/k3-doctor.sh" 4. Download the checkpoint and choose a suitable preset GitHub: It's slow and needs plenty of SSD storage, but running a model this large on a CPU is pretty wild.

2.78 TRILLION parameter AI running on just 8GB RAM 😳 Meet kimi-k3-in-c , a free open-source project that runs Kimi K3 on a CPU. what you get : → Full 2.78T parameter model → Around 8.24GB RAM, no GPU → Just 176KB of C code → No PyTorch or CUDA → Supports Linux, macOS and Windows how to try it :) 1. Clone the GitHub repo 2. Run "make" 3. Run "./scripts/k3-doctor.sh" 4. Download the checkpoint and choose a suitable preset GitHub: It's slow and needs plenty of SSD storage, but running a model this large on a CPU is pretty wild.

DEATHLESS

26,284 görüntüleme • 5 gün önce

The T-Display SF is a low-power device that integrates AMOLED, GPU+LoRa, audio, and a expandable 12-key keyboard.

The T-Display SF is a low-power device that integrates AMOLED, GPU+LoRa, audio, and a expandable 12-key keyboard.

LILYGO

114,837 görüntüleme • 10 ay önce

We are excited to share a deeper look into the GPU Sharing Platform that will power AI applications on the InfraX V4 DApp. In this demo we showcase a GPU running and completing an image generation task. Our backend successfully leverages this GPU (and CPU) in real time to complete the job, earning the user money, and powering the infraX platform. Here’s how it works 👉 when you connect to the InfraX DApp, our platform automatically detects the GPU on your machine and immediately checks it eligibility and where it can be used. From there, each user dictates exactly how and when they want to contribute their GPU power by setting the days their PC is most available (throughout the night, for example). Additional, each user will be able to pause their GPU's connection to infraX whenever they need to use it locally, resuming with a just a single click. Once activated, your GPU seamlessly plugs into the InfraX network and begins fulfilling compute jobs, earning YOU money. Go on, take the $INFRA pill..

We are excited to share a deeper look into the GPU Sharing Platform that will power AI applications on the InfraX V4 DApp. In this demo we showcase a GPU running and completing an image generation task. Our backend successfully leverages this GPU (and CPU) in real time to complete the job, earning the user money, and powering the infraX platform. Here’s how it works 👉 when you connect to the InfraX DApp, our platform automatically detects the GPU on your machine and immediately checks it eligibility and where it can be used. From there, each user dictates exactly how and when they want to contribute their GPU power by setting the days their PC is most available (throughout the night, for example). Additional, each user will be able to pause their GPU's connection to infraX whenever they need to use it locally, resuming with a just a single click. Once activated, your GPU seamlessly plugs into the InfraX network and begins fulfilling compute jobs, earning YOU money. Go on, take the $INFRA pill..

infraX | $INFRA

30,615 görüntüleme • 1 yıl önce