- All languages
- Assembly
- AutoHotkey
- Batchfile
- Bikeshed
- C
- C#
- C++
- CMake
- CSS
- Clojure
- CoffeeScript
- Cuda
- Cython
- DTrace
- Dart
- Dockerfile
- Emacs Lisp
- GDScript
- GLSL
- Go
- HLSL
- HTML
- Java
- JavaScript
- Jupyter Notebook
- Kotlin
- LLVM
- Less
- Lex
- Lua
- MATLAB
- MDX
- MLIR
- Makefile
- Markdown
- Mathematica
- NSIS
- Objective-C
- Objective-C++
- OpenSCAD
- PHP
- Pascal
- Perl
- PowerShell
- Processing
- Python
- QML
- Raku
- Ruby
- Rust
- SCSS
- SWIG
- Sass
- Scala
- ShaderLab
- Shell
- Svelte
- Swift
- TeX
- TypeScript
- Verilog
- Vim Script
- Visual Basic .NET
- Vue
- WebIDL
- XSLT
Starred repositories
Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
InternVLA-A1: Unifying Understanding, Generation, and Action for Robotic Manipulation
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
A privacy-first, open-source platform for knowledge management and collaboration. Download link: http://github.com/logseq/logseq/releases. roadmap: https://discuss.logseq.com/t/logseq-product-roadm…
A highly compressive and high-quality neural audio codec for speech models.
Minimal reproduction of DeepSeek R1-Zero
deepbeepmeep / Wan2GP
Forked from Wan-Video/Wan2.1A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.
[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
The purpose of this project is to share knowledge on how awesome Streamlit is and can be
LeIsaac provides teleoperation functionality in IsaacLab using the SO101Leader (LeRobot), including data collection, data conversion, and subsequent policy training.
"Paper2Slides: From Paper to Presentation in One Click"
Dissecting NVIDIA GPU Architecture
My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT p…
Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion
Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization
Metropolis Smart-City Synthetic Data Generation Recipe allows you to generate synthetic data and then augment them. The generated data then can be used to fine-tune VLM models such as Cosmos Reason…
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
GigaWorld-0: World Models as Data Engine to Empower Embodied AI
Janus-Series: Unified Multimodal Understanding and Generation Models
Multi-system emulator (NES, SNES, GB, GBA, PCE, SMS/GG, WS) for Windows, Linux and macOS
A fix that adds custom resolutions, ultrawide support and much more to the Metal Gear Solid Master Collection.
琥珀是第一款符合传统汉字纵向排版习惯的Typora主题。 Amber is the first vertical Typora theme that conforms to the tradition of ancient Chinese typography.
将Typora伪装成LaTeX的中文样式主题,本科生轻量级课程论文撰写的好帮手。This is a theme disguising Typora into Chinese LaTeX style.