Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

I trained a small model to do syntax highlighting in the browser with GPU. Meet gpu-lexer from Vercel Labs: Small (27.5KB), fast (runs on WebGPU), and language-agnostic (model guesses the syntax). It is experimental and built for learning!

Shu

61,083 subscribers

408,805 Aufrufe • vor 21 Stunden •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

made an interactive video model trained on tap-conditioned data.. tap the screen and it generates the next frames in realtime (small enough to run in the browser with webgpu, even on iphone)

made an interactive video model trained on tap-conditioned data.. tap the screen and it generates the next frames in realtime (small enough to run in the browser with webgpu, even on iphone)

sahir

24,731 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 2 Jahren

I won an RTX 5090 GPU at Mistral AI worldwide hackathon in Paris, and I have absolutely no idea on how to use it. Here's what I actually built: an image generation model fine-tuned to do technical analysis on trading charts. I trained it on an NVIDIA cloud GPU then back-tested it against Binance historical data. The model was profitable. The jury didn't quite catch the vibe. But apparently someone did because two weeks later, they reached out to tell me I'd won the NVIDIA track. Today, a €4,000 RTX Founders Edition showed up at my door. Absolutely gorgeous piece of hardware. One small problem: I use a MacBook. So if anyone has creative suggestions for what to do with a top-tier GPU and no desktop to put it in… I'm listening Huge thanks to NVIDIA, Mistral AI and Iterate team for appreciating my weird idea and an attempt to push tech to its boundaries

I won an RTX 5090 GPU at Mistral AI worldwide hackathon in Paris, and I have absolutely no idea on how to use it. Here's what I actually built: an image generation model fine-tuned to do technical analysis on trading charts. I trained it on an NVIDIA cloud GPU then back-tested it against Binance historical data. The model was profitable. The jury didn't quite catch the vibe. But apparently someone did because two weeks later, they reached out to tell me I'd won the NVIDIA track. Today, a €4,000 RTX Founders Edition showed up at my door. Absolutely gorgeous piece of hardware. One small problem: I use a MacBook. So if anyone has creative suggestions for what to do with a top-tier GPU and no desktop to put it in… I'm listening Huge thanks to NVIDIA, Mistral AI and Iterate team for appreciating my weird idea and an attempt to push tech to its boundaries

Kirill

52,518 Aufrufe • vor 4 Monaten

Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser. This demo runs Voxtral-Mini-4B, a powerful streaming ASR model from Mistral AI, locally on WebGPU. The model supports 13 languages and is capable of <500 ms latency. Fully private. Zero cost.

Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser. This demo runs Voxtral-Mini-4B, a powerful streaming ASR model from Mistral AI, locally on WebGPU. The model supports 13 languages and is capable of <500 ms latency. Fully private. Zero cost.

Xenova

94,356 Aufrufe • vor 6 Monaten

Vibe coding is cool. But have you tried vibe-tuning? Here’s Claude Code using the Lightning Rod Labs SDK to turn messy Fed PDFs into a small, specialized economic forecaster. The agent: - parses raw historical PDFs - builds a training set - fine-tunes a smaller model - evaluates it against GPT-5 Result: a fine-tuned model that beats GPT-5 and runs anywhere, on a single GPU. Try it in your coding agent of choice.

Vibe coding is cool. But have you tried vibe-tuning? Here’s Claude Code using the Lightning Rod Labs SDK to turn messy Fed PDFs into a small, specialized economic forecaster. The agent: - parses raw historical PDFs - builds a training set - fine-tunes a smaller model - evaluates it against GPT-5 Result: a fine-tuned model that beats GPT-5 and runs anywhere, on a single GPU. Try it in your coding agent of choice.

Ben Turtel

423,542 Aufrufe • vor 3 Monaten

i built the animation tool i’ve needed for years. framezero v1 is live. i call it "the whiteboard video editor" - sketch visually - add motion + animations instantly - show code w/ syntax highlighting - quick use icons + GIFS to your video - export 4k — all in your browser

i built the animation tool i’ve needed for years. framezero v1 is live. i call it "the whiteboard video editor" - sketch visually - add motion + animations instantly - show code w/ syntax highlighting - quick use icons + GIFS to your video - export 4k — all in your browser

Matt Maribojoc

70,119 Aufrufe • vor 6 Monaten

NEW: Perplexity just released pplx-embed, a series of powerful embedding models. Inspired by their logo, I built a small semantic search demo: enter a query and the model retrieves the most relevant page. Everything runs locally in your browser with Transformers.js and Three.js

Xenova

11,092 Aufrufe • vor 6 Monaten

I built this little tool to optimize and re-export GLTF/GLB assets to GPU-compressed KTX2. It runs entirely client-side/in-browser. You can fiddle with the parameters, compare the before/after, and export to GLB. Try it here: #threejs #gamedev

I built this little tool to optimize and re-export GLTF/GLB assets to GPU-compressed KTX2. It runs entirely client-side/in-browser. You can fiddle with the parameters, compare the before/after, and export to GLB. Try it here: #threejs #gamedev

Simon

24,265 Aufrufe • vor 9 Monaten

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

261,455 Aufrufe • vor 2 Jahren

You can run CUDA, on a Mac ARM GPU, in the browser. It sounds ridiculous but it actually works. HipScript chains CUDA, to OpenCL, to Vulkan, to Tint (Google’s shader translator), to a WASM WebGPU. I got a plasma simulation in running in just a few minutes, no NVIDIA GPU!

You can run CUDA, on a Mac ARM GPU, in the browser. It sounds ridiculous but it actually works. HipScript chains CUDA, to OpenCL, to Vulkan, to Tint (Google’s shader translator), to a WASM WebGPU. I got a plasma simulation in running in just a few minutes, no NVIDIA GPU!

LaurieWired

160,600 Aufrufe • vor 1 Jahr

Ideogram just released the #1 open weight image model in the world. It punches way above its weight - it's small enough to run on a consumer GPU, but goes head-to-head with Nano Banana and GPT Image for design. We went deep with Mohammad Norouzi on how they did it + hot takes 👇

Ideogram just released the #1 open weight image model in the world. It punches way above its weight - it's small enough to run on a consumer GPU, but goes head-to-head with Nano Banana and GPT Image for design. We went deep with Mohammad Norouzi on how they did it + hot takes 👇

Justine Moore

39,900 Aufrufe • vor 2 Monaten

Introducing SmolVLM 256M (& 500M): The world’s smallest multimodal model. Designed for efficiency and perfect for on-device applications! 🔥 It’s so small, it can even run 100% locally in your browser on WebGPU! 🤏 Powered by Transformers.js! ⚡️ Try it out yourself! 👇

Introducing SmolVLM 256M (& 500M): The world’s smallest multimodal model. Designed for efficiency and perfect for on-device applications! 🔥 It’s so small, it can even run 100% locally in your browser on WebGPU! 🤏 Powered by Transformers.js! ⚡️ Try it out yourself! 👇

Xenova

25,302 Aufrufe • vor 1 Jahr

$A crypto project actually trained a 72B parameter AI model from scratch using decentralized GPU compute. Not fine-tuned, not a wrapper: trained from zero. The model benchmarks competitively against Meta's LLaMA 3 on reasoning tasks, and the entire training run cost a fraction of what centralized labs spend. If decentralized compute can produce frontier-class models, the moat around OpenAI and Anthropic is thinner than people think.$

A crypto project actually trained a 72B parameter AI model from scratch using decentralized GPU compute. Not fine-tuned, not a wrapper: trained from zero. The model benchmarks competitively against Meta's LLaMA 3 on reasoning tasks, and the entire training run cost a fraction of what centralized labs spend. If decentralized compute can produce frontier-class models, the moat around OpenAI and Anthropic is thinner than people think.

VirtualBacon

40,647 Aufrufe • vor 5 Monaten

#WATCH | Bengaluru, Karnataka: Co-founder, Sarvam AI, Pratyush Kumar says, "... It's been three years now. We started off building on top of the Llama model, which was the best open model at that time. Sarvam was the only company outside, or maybe in Asia, that contributed to the Llama 3 Series. We understood how to add language skills into models, and Llama 3 was reasonable in Indian languages. When the first set of GPUs arrived in India, we pre-trained from scratch a 2-billion model and worked with Infosys to make it useful for IT services. Then we recognised the importance of scaling up reinforcement learning and built a reasoning model called Sarvam M on top of Mistral's small model. Over the last year, we pre-trained from scratch in India on 4,000 Hopper Series GPUs a 100-billion-plus-parameter model..."

#WATCH | Bengaluru, Karnataka: Co-founder, Sarvam AI, Pratyush Kumar says, "... It's been three years now. We started off building on top of the Llama model, which was the best open model at that time. Sarvam was the only company outside, or maybe in Asia, that contributed to the Llama 3 Series. We understood how to add language skills into models, and Llama 3 was reasonable in Indian languages. When the first set of GPUs arrived in India, we pre-trained from scratch a 2-billion model and worked with Infosys to make it useful for IT services. Then we recognised the importance of scaling up reinforcement learning and built a reasoning model called Sarvam M on top of Mistral's small model. Over the last year, we pre-trained from scratch in India on 4,000 Hopper Series GPUs a 100-billion-plus-parameter model..."

ANI

163,060 Aufrufe • vor 1 Monat

Here's Qwen3.8-27B Runs on any macbook/gpu with 24gb or more I gave it an hour of video, and told it to find the latest session with claude where it helped me make edit yesterdays video and create the thumbnail Running on Openrouter, big models do first Small models follow

Here's Qwen3.8-27B Runs on any macbook/gpu with 24gb or more I gave it an hour of video, and told it to find the latest session with claude where it helped me make edit yesterdays video and create the thumbnail Running on Openrouter, big models do first Small models follow

0xSero

23,510 Aufrufe • vor 5 Tagen

NEW: Google releases FunctionGemma, a lightweight (270M), open foundation model built for creating specialized function calling models! 🤯 To test it out, I built a small game: use natural language to solve fun physics simulation puzzles, running 100% locally in your browser! 🕹️

NEW: Google releases FunctionGemma, a lightweight (270M), open foundation model built for creating specialized function calling models! 🤯 To test it out, I built a small game: use natural language to solve fun physics simulation puzzles, running 100% locally in your browser! 🕹️

Xenova

58,200 Aufrufe • vor 8 Monaten

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team Google DeepMind.

🚀Meet Gemini Diffusion, our first diffusion-based and super fast language model, just announced at Google I/O!🚀 Very excited to be able to share what I've been working on for the past little while with our amazing small team Google DeepMind.

Ivana Balazevic

43,562 Aufrufe • vor 1 Jahr

We’re excited to introduce Pocket TTS: a 100M-parameter text-to-speech model with high-quality voice cloning that runs on your laptop—no GPU required. Open-source, lightweight, and incredibly fast. 🧵👇

We’re excited to introduce Pocket TTS: a 100M-parameter text-to-speech model with high-quality voice cloning that runs on your laptop—no GPU required. Open-source, lightweight, and incredibly fast. 🧵👇

kyutai

238,392 Aufrufe • vor 7 Monaten

i built the animation tool i've needed for years... framezero beta is OUT NOW! - whiteboard-like editing - built-in transitions - hand-drawn style w/ 500+ icons - syntax highlighting - 1080p export and we're just getting started 😈

i built the animation tool i've needed for years... framezero beta is OUT NOW! - whiteboard-like editing - built-in transitions - hand-drawn style w/ 500+ icons - syntax highlighting - 1080p export and we're just getting started 😈

Matt Maribojoc

63,083 Aufrufe • vor 1 Jahr

Congrats to the Kimi.ai team! This is awesome. Great to see this level of research coming from open-source frontier model labs. I liked the paper so much I built a Rust implementation of it ;) Full AttnRes + Block AttnRes with two-phase inference, built using Burn (tensor library and Deep Learning Framework, in Rust, by Tracel AI). Runs on CPU, CUDA, Metal, wgpu. Includes an interactive TUI that trains a model live and visualizes depth attention evolving from uniform to selective in real time. Repo link and more on what is implemented in the comments.

Congrats to the Kimi.ai team! This is awesome. Great to see this level of research coming from open-source frontier model labs. I liked the paper so much I built a Rust implementation of it ;) Full AttnRes + Block AttnRes with two-phase inference, built using Burn (tensor library and Deep Learning Framework, in Rust, by Tracel AI). Runs on CPU, CUDA, Metal, wgpu. Includes an interactive TUI that trains a model live and visualizes depth attention evolving from uniform to selective in real time. Repo link and more on what is implemented in the comments.

abdel

95,651 Aufrufe • vor 5 Monaten