Stars
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Implement a reasoning LLM in PyTorch from scratch, step by step
τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment
A project to improve skills of large language models
Scalable toolkit for efficient model reinforcement
Ditto is an open-source framework that enables direct conversion of HuggingFace PreTrainedModels into TensorRT-LLM engines.
The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.
New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
CUDA Templates and Python DSLs for High-Performance Linear Algebra
TAO Toolkit deep learning networks with PyTorch backend
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Visualizer for neural network, deep learning and machine learning models
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Pytorch CPP implementations of several deep learning papers
Motion Retargeting Video Subjects
NVIDIA's Deep Imagination Team's PyTorch Library
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
PyTorch implementation of the REMIND method from our ECCV-2020 paper "REMIND Your Neural Network to Prevent Catastrophic Forgetting"
Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch
[CVPR 2021] VirTex: Learning Visual Representations from Textual Annotations
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.