Package profile
nvidia-modelopt
- Summary: Nvidia Model Optimizer: A unified library of SOTA model optimization techniques like quantization, pruning, Neural Architecture Search (NAS), distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
- Author: NVIDIA Corporation
- License: Apache-2.0
- Homepage: https://github.com/NVIDIA/Model-Optimizer
- Source: https://github.com/NVIDIA/Model-Optimizer
- Number of releases: 40
- First release: 0.11.0 on 2024-04-30
- Latest release: 0.47.0 on 2026-09-23
- Latest release size: 2.1 MB (pure Python wheel)