NVIDIA/Model-Optimizer

Compresses deep learning models for faster inference

View on index · View in 3D Map

Related repos

• Portfolio optimization with 160x speedups via NVIDIA GPUs
• Optimizing large-scale deep learning model training
• Optimizes GPU training and inference scaling with CUDA and PyTorch
• Toolkit for optimizing and deploying deep learning models across CPUs, GPUs, and NPUs
• Python framework for fast GPU simulation and graphics
• Systematically maximizes deep learning model performance
• Model quantization with hardware acceleration for Nvidia, AMD, and Intel
• Deep learning framework for inference and training on-device
• Generates synthetic datasets using LLMs and statistical samplers
• Train and deploy models for agents