Stars
[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLM, VLM, and video generation models.
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
dInfer: An Efficient Inference Framework for Diffusion Language Models
An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization
My learning notes/codes for ML SYS.
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU.
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
A high-performance inference engine for LLMs, optimized for diverse AI accelerators.
AGENTS.md — a simple, open format for guiding coding agents
开源白板工具（SaaS），一体化白板，包含思维导图、流程图、自由画等。All in one open-source whiteboard tool with mind, flowchart, freehand and etc.
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
【C++面试&C++学习指南】 这里整理了C++后端研发工程师面试和工作必备的知识点 。
🔥中文 prompt 精选🔥，ChatGPT 使用指南，提升 ChatGPT 可玩性和可用性！🚀
Interactive Pytorch forward pass visualization in notebooks
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.
A research prototype of a human-centered web agent
The official implementation of the EMNLP 2023 paper LLM-FP4
SkyReels-V2: Infinite-length Film Generative model