Skip to main content

Articles

Python

NVIDIA/Model-Optimizer — a trending Python project

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

via GitHub · 4 min

Looking for an older post? See every article in the archive.