You asked for it, so here it is. Visualizing... CPU cache speeds relative to RAM. Cache optimization is important too!show more

Some of the biggest news today is Cloudflare Worker's... Cache. So I built this small catalog to experience it. It allows you to purge the cache for certain pages, or the entire catalog. It also shows you the exact caching headers used. See it in action or try it yourself:show more

Submitted Easy Vertex Anim for #UE5.8 too. You can... create pivot painter 2 effects and bake chaos cache to vat, 100% NO AI, check it out!show more

I don't think anyone realizes yet how powerful Convex... + Next.js 'use cache' is going to be You are able to get completely dynamic sites at the speed of static, with no flashes of incorrect data Also you will never have to think about what cache keys to set, it just worksshow more

WanGP's latest MiniMax H3 update is huge: - Way... faster Generation - 2X faster Ref2VA - Lower-RAM & new accelerators - Long videos with smoother visual/audio transitions. - Huge speed gains with Sol-Attention, First Block Cache, etc. And Pinokio launcher is optimized for it 👇show more

A lot of people asked me to post FOOTage... of Iuno's burst It features her, you guessed it, feet So here it is Enjoy!show more

Want the latest, flashiest skins? Lucky Cache is here... for you every week! Every Friday to Sunday, Step into the Lucky Cache and challenge destiny! (level 80 needed) 🎁 One free draw every week A single draw could change everything and rewards can refresh 3 times a week — are you ready? Luck doesn't wait!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

🚨 Today I published my own Stream Deck plugin... on @Elgato Marketplace . I call it SimpleStats. It's a very lightweight plugin for viewing CPU usage, Ping, Net Throughput, GPU temps, even what is using up all your RAM!!!!!!! The most important part for me: Everything is included.show more

being able to pop into a level at an... exact location is so important and so common, you NEED a button for it.show more

YOU ASKED FOR A LOVE SONG, SO HERE IS... MY FIRST ATTEMPT. IF YOU DONT LIKE IT, LIE. ORIGINAL SONG COMING OUT TOMORROW! 🎉🥳 🪩show more

The people asked… so here it is. 😂 Some... treacherous conditions out here in Wichita.show more

shroud shared his actual thoughts on new version of... Cache: "Yeah, I don't love it. I wasn't expecting to not love it, but it definitely needs some work for sure, I don't hate it either."show more

My favorite editing model, FLUX.2 [klein] 9B, just got... 2x faster: Meet FLUX.2 [klein] 9B-KV 😍💨 > Using KV-Cache Optimization to reduce computation & speed up inference by up to 2.5 times for multi-reference editing love how well it edits "around" the bulletsshow more

Thank you so much for the 9,700+ likes! Here... it is, green screen, so you can use it however you want! 😁show more

I asked #iubb freshman Prince-Alexander Moody why it was... important to him to interact with all of you here.show more

is it too thick for you?

You guys asked for a tutorial, so here it... is. Animated Apple-style websites FULLY with AI, perfect for web and UI work. Let's break it down step-by-step below. Prompts included.show more

You asked for the Item Selection Wheel to make... the item selection (and usage) less tedious, so here it is. This feature will roll out with the next update. 🧙‍♂️show more

So… is it enough for you to come?