PaulKinlan
Follow
Stars
DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported …
A tool to monitor and track the status of all Web Platform features across dimensions that are related to availability and implementation quality across browsers, and adoption by web developers.
A Webapp that uses Retrieval Augmented Generation (RAG) and Large Language Models to interact with a PDF directly in the browser.
Wordpress plugin to serverside render enhance components in wordpress
A library for prototyping generative AI applications.
notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references und…
Convert Google discovery API documents to fully compliant OpenAPI3 specifications
A free tool for generating social share links
A web-app to explore topics using LLM (less typing and more clicks)
✨ Build SEO-friendly websites, super fast full-stack web applications, and much more with Elegant. 💜 Built with Next.js, TipTap, Tailwind CSS, and more.
📸 Quickly generate image from DOM node using HTML5 canvas and SVG
🔥Highlighting the top ML papers every week.
smol-podcaster is your podcast production agent 🎙️
A machine-readable list of Web specifications
Generative Agents: Interactive Simulacra of Human Behavior
Community interface for generative AI
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
English language description of compat data for use in LLM
Backward compatible ML compute opset inspired by HLO/MHLO
InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. Th…
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
QLoRA: Efficient Finetuning of Quantized LLMs
Easy-to-use headless React Hooks to run LLMs in the browser with WebGPU. Just useLLM().
A guidance language for controlling large language models.