Precision & Quantization
=========================

Control numerical precision with FP16, BF16, and mixed-precision autocast,
and reduce model size with INT8/FP8/FP4 quantization via ModelOpt.

.. toctree::
   :maxdepth: 1

   mixed_precision
   ../../tutorials/_rendered_examples/dynamo/autocast_example
   quantization
   ../../tutorials/_rendered_examples/dynamo/vgg16_ptq