The Website and web infrastructure for learning TypeScript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

API-aware Networking and Security using eBPF and XDP

make LLMs improve through experience

Investment Research for Everyone.

Want to play around with C but aren't sure where to start? This project template will help.

Copilot template to bring your own copilots into the OpenBB Terminal Pro

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

MoH: Multi-Head Attention as Mixture-of-Head Attention

Second Order Optimization and Curvature Estimation with K-FAC in JAX.

A library for generative social simulation

Multi-Joint dynamics with Contact. A general purpose physics simulator.

TORAX: Tokamak transport simulation in JAX

SGLang is a fast serving framework for large language models and vision language models.

Use PEFT or Full-parameter to finetune 350+ LLMs or 100+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-V…

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

LayaAir is a fully platform rendering engine with rich 2D/3D rendering capabilities and a mature integrated development platform

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight) / / / / When Does Perceptual Alignment Benefit Vision Representations? (NeurIPS 2024)

Official Pytorch Implementation of Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Convo is a conversational programming language that's designed to be generated and interpreted by a Large Language Model (LLM).

The AI Code Editor

A Free Newsletter for Quantitative and Algorithmic Trading, Portfolio Analysis, and Investing

Anthropic's educational courses

The simplest way to serve AI/ML models in production

Entropy Based Sampling and Parallel CoT Decoding

Use your Neovim like using Cursor AI IDE!