2026-09-25 · America/Los_Angeles · 开源项目 · #3

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.

热度 54.4 / 100；排名与评分保留该期记录。