Open Overleaf/ShareLaTex projects in vscode, with full collaboration support.

CRS-自建Claude Code镜像，一站式开源中转服务，让 Claude、OpenAI、Gemini、Droid 订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

DeepEP: an efficient expert-parallel communication library

PyTorch building blocks for the OLMo ecosystem

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Elevate your AI research writing, no more tedious polishing ✨

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀

A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.

Supercharge Your LLM with the Fastest KV Cache Layer

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

CUDA Core Compute Libraries

A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resources in your applications.

A simple example language built using the Truffle API.

The uncompromising Python code formatter

verl: Volcano Engine Reinforcement Learning for LLMs

A high-throughput and memory-efficient inference and serving engine for LLMs

List of papers related to neural network quantization in recent AI conferences and journals.

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

A framework for building native applications using React

Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics

🧡 Folo is the AI RSS Reader

Code for the paper "Evaluating Large Language Models Trained on Code"

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch

Dream 7B, a large diffusion language model

An extremely fast Python package and project manager, written in Rust.