more sync engine shenanigans. using CF's new oauth stuff... to build a reactive kv editor with the cloudflare api. here it's syncing across chrome and safari, even though the kv api isn't reactive at all. instant reloads and everything.show more

Today, we're announcing four new capabilities on the Anthropic... API to help developers build more powerful AI agents. A code execution tool, MCP connector, Files API, and extended prompt caching:show more

🤔 Imagine if your backend worked like `useState`. No... API calls. No fetching. Just reactive, real-time state that syncs across devices. That’s what InstantDB is doing. With Instant your frontend gets a real-time database. You write queries that stay in sync and work offline. Every save updates immediately, and it comes with built-in auth and permissions. See how InstantDB looks in action in this deeply technical blog post from Stopa ↓show more

iPad Safari and desktop Chrome syncing a WebAssembly program... that’s unaware it’s being synced.show more

One million particles created using GitHub Spark, using the... KV data to configure and remember the properties #GitHubUniverse #WebGLshow more

The fastest, cheapest, and easiest way to confirm blockchain... payments. Enable instant crypto checkouts, onchain invoicing, and real-time payment detection, all with one API.show more

Day 11/90 of Inference Engineering How does vLLM work... and how is it used in production? Before we discuss how vLLM works internally, it helps to understand what vLLM is. At a high level, vLLM is an inference engine that is designed to serve LLMs to thousands of concurrent users efficiently while managing scarce compute and memory. The goal for vLLM is to maximize throughput and minimize latency; optimizing for the best inference economics and experience for end users. With every request from the end user, it eventually ends up in the engine core, gets scheduled alongside other requests from other concurrent users, executes on the GPU, and updates the KV cache with the new key and value vectors, and streams the tokens back to the user. The Scheduler decides what requests should execute next while continuously batching requests together to maximize GPU utilization. Continuous batching is an inference optimization that allows new requests to join a running batch as other requests finish generating tokens. This helps with keeping the GPU utilization high instead of letting it sit idle waiting for an entire batch to complete generating. After the scheduler dispatches the selected batch to the Model Executor, the Model Executor prepares the tensors and metadata required for inference, retrieves each request’s block table from KV Cache Manager, launches the optimized transformer forward pass on the GPU, computes the logits, updates the KV cache with the new key and value vectors, and finally returns the results for sampling and streaming. The KV Cache Manager uses the PagedAttention memory layout to allocate fixed-size cache blocks on demand and maintains a Free Block Queue on the CPU that tracks which blocks in the GPU’s Paged KV Cache are currently free. When a request needs additional KV cache space, the KV Cache manager takes a free block from the queue and assigns it to that request, thus avoiding an expensive search through GPU memory for available cache blocks. All of these components form the core of vLLM’s inference engine. The Scheduler determines what requests are executed, the Model Executor determines how those requests are executed, the KV Cache Manager determines where each request’s KV cache lives using the PagedAttention Memory Layout. This architecture enables vLLM to serve thousands of concurrent requests with high throughput, low latency, and efficient GPU memory utilization. Heres a little animation that visualizes everything! - I've also completed the forward pass for my mnist.c project. I had a nice chat with shrey birmiwal, such a knowledgeable guy. Excited to learn more about vLLM and implement a tiny-vLLM one day.show more

🆕 Etherscan API: Build with AI The same data... behind Etherscan, now built for your agents Give your agents direct and structured access to reliable onchain data API behind Etherscan across 60+ EVM chains via MCP, CLI, and Skillsshow more

The Razer Soma Chroma brings Reactive Game Lighting to... over 300 integrated games: See every spell cast, takedown, and game-changing moment light up your space as reactive Razer Chroma RGB lighting surrounds you, bringing the action beyond your screen and making every match feel even more exhilarating.show more

Introducing the VEED Lip Sync 2.0 API: One video,... endless versions. Change the hook, fix lines, or dub. At scale. Lip Sync 2.0 API is built on our most powerful model to date. And we're stoked to be launching with Magnific as our partner. One of the world's leading generative media platforms! The Lip Sync 2.0 API handles these things beautifully: 🚧 Objects blocking the face 💡Low lighting 🎥Fast camera movements 📐Multiple anglesshow more

I made a thing! 🐱 Clipcat (link in the... next tweet) is an API for rendering videos in the cloud with smooth animations, multiple scenes, at up to 60fps. It's like Bannerbear, but with complex animations / tweening, and a keyframe-based editor.show more

🛠️ Getting started with the Gemini API? Check out... our collection of prompts and code samples for developers to build with the API and leverage the power of Gemini 1.5 Pro and 1.5 Flash in Google AI Studio. ✨ →show more

This is crazy... You can now build full apps... using OpenAI’s image API. This new agentic vibecoding platform connects to OpenAI’s image API and turns ideas into real apps. Here’s how I vibecoded a moodboard generator:show more

AN ENTIRE PLAYABLE CYBERPUNK CITY FROM ONE SINGLE PROMPT... → give Kimi K3 the idea and it builds you the whole city → move through the streets in 3D → neon lights, traffic, reactive buildings → all running in the browser $3 in API with K3. the same would run about $9 with Fable 5 this needed a full game studio a month agoshow more

Ukrainian HIMARS strikes hit energy infrastructure in Belgorod, Russia,... with at least 25 rockets reportedly used. Targets included the Avtoremzavod 110 kV substation, the Belgorod Thermal Power Plant and the Dubovoe 110 kV substation at the Luch power facility. Multiple reports said the attack caused power and water outages across parts of the city, while Russian authorities acknowledged damage to energy infrastructure. #Russiashow more

You can run full browser automations for AI agents... without worrying about Chrome, Puppeteer, or infrastructure. Steel is an open-source browser API that wraps Chrome, manages sessions, handles proxies, and exposes everything via a REST API or SDKs.show more

UNIfication is here 🦄 All interface fees have been... set to zero across Uniswap apps and API Happy swappingshow more

Nice! We no longer need a depth sensor, a... Kinect, or even Windows to build amazing interactive installations. Just an Apple device, ARKit, and AI. Rendered with Three.js in Electron, using its new SharedTexture API for direct GPU-to-GPU texture sharing. 🚀show more