Modelopt Qad

Run explicitly requested ModelOpt Quantization-Aware Distillation (QAD) through Megatron Bridge (recommended) or Hugging Face Transformers to recover a measured BF16-to-PTQ accuracy gap. Use only when the user explicitly asks for QAD, including its topology, data preparation, launch, resume, checkpoint export, or recovery decisions.

NVIDIA Updated 23k repo stars
Banner image

File contents

NVIDIA/Model-Optimizer commit ea8f4ae9bc Runs: nvidia/common

Frequently asked questions

npx get-skill add nvidia/modelopt-qad