GitHub Hot Board · Archive du dépôt

NVIDIA/Model-Optimizer

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. (Cette description provient du dépôt lui-même.)

Données au October 21NVIDIA