- All languages
- Assembly
- Batchfile
- C
- C#
- C++
- CMake
- CSS
- Clojure
- CoffeeScript
- Common Workflow Language
- Cuda
- Cython
- Dockerfile
- Fortran
- GAP
- Go
- HCL
- HTML
- Haskell
- Java
- JavaScript
- Jsonnet
- Julia
- Jupyter Notebook
- Kotlin
- Limbo
- Lua
- MATLAB
- MDX
- MLIR
- Makefile
- Markdown
- Objective-C
- Objective-C++
- OpenEdge ABL
- PHP
- PLSQL
- Perl
- PostScript
- PureBasic
- Python
- QML
- R
- Roff
- Ruby
- Rust
- SCSS
- Sass
- Scala
- Shell
- SourcePawn
- Svelte
- Swift
- SystemVerilog
- TSQL
- TeX
- Thrift
- TypeScript
- Vim Script
- Vue
- WebAssembly
- Zig
Starred repositories
SkyRL: A Modular Full-stack RL Library for LLMs
The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
MedSAM3: Delving into Segment Anything with Medical Concepts
UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios
Official repository for “DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation”
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
TTS model capable of streaming conversational audio in realtime.
Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
PyTorch building blocks for the OLMo ecosystem
Open-source release accompanying Gao et al. 2025
Video Content Customization Using First Frame
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505
Code release for "UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity"
Intelligent Router for Mixture-of-Models
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
Rust-powered API framework for Django achieving 60k+ RPS. Uses Actix Web for HTTP, PyO3 for Python bridging, msgspec for serialization. Decorator-based routing with built-in auth and middleware.
[EMNLP 2025🔥] UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
An early research stage expert-parallel load balancer for MoE models based on linear programming.