- All languages
- Bicep
- C
- C#
- C++
- CMake
- CSS
- Cap'n Proto
- CartoCSS
- Common Workflow Language
- Cuda
- Dockerfile
- Go
- HTML
- Haskell
- IDL
- Java
- JavaScript
- Jsonnet
- Julia
- Jupyter Notebook
- Lean
- Lua
- MATLAB
- MDX
- Makefile
- Markdown
- NASL
- OCaml
- Objective-C
- Objective-C++
- PHP
- Perl
- PostScript
- Prolog
- Python
- Ruby
- Rust
- Scala
- Shell
- Smarty
- Swift
- TSQL
- TeX
- TypeScript
- Verilog
- Vue
- YAML
Starred repositories
Super basic implementation (gist-like) of RLMs with REPL environments.
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
An interface library for RL post training with environments.
Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch
DeepDetect: Learning All-in-One Dense Keypoints β DeepDetect is an intelligent, adaptable, all-in-one, dense keypoint detector that leverages deep learning to learn the strengths of 7 keypoint and β¦
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.
Training LLMs to reason and analyze data with notebooks
πͺ β¨ Jupyter AI Agents are agents equipped with tools like 'execute', 'insert_cell', and more, to transform your Jupyter Notebooks into an intelligent, interactive workspace!
You Only Pose Once - Neural network for pose Estimation
Project management system for Claude Code using GitHub Issues and Git worktrees for parallel agent execution.
LLM agents built for control. Designed for real-world use. Deployed in minutes.
γμ€μ ! ν μνλ‘ 2λ₯Ό νμ©ν λ₯λ¬λ μ»΄ν¨ν° λΉμ γ μμ μ½λ
Multimodal RAG to search and interact locally with technical documents of any kind
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
A powerful Python library for creating complex visual compositions and beautifully styled images
Distributed Reinforcement Learning accelerated by Lightning Fabric
This repository contains the toolkit for replicating results from our technical report.
A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.
Complete solutions to the Programming Massively Parallel Processors Edition 4
OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page conteβ¦
π RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platforms such as MinIO and Ceph.