Stars
Large graphs analysis, drawing and visualization framework
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Unified framework for robot learning built on NVIDIA Isaac Sim
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
This is the official implementation of Multi-Agent PPO (MAPPO).
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
Training transferable end-to-end quadrotor control policies on a laptop in 18 seconds.
A generative speech model for daily dialogue.
GNN-RAG: Graph Neural Retrieval for Large Language Modeling Reasoning
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
[I3D 2024] Deblur-GS: 3D Gaussian Splatting from Camera Motion Blurred Images
A fast and simple implementation of RL algorithms, designed to run fully on GPU.
A natural language interface for computers
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
协程执行器,起一个额外的线程执行事件循环,主线程则管理这个事件循环线程, 这个执行器不要用在协程中.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A simple and highly efficient RTS-game-inspired environment for reinforcement learning (formerly Gym-MicroRTS)
A toolkit for developing and comparing reinforcement learning algorithms.
Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch
Simple autoencoder pruned with Fisher Information Metric (NNGeometry)
A curated list of awesome NVIDIA Issac Gym frameworks, papers, software, and resources
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
MaRS: A Modular and Robust Sensor-Fusion Framework