# Advanced model techniques

In addition to the standard model workflow, the Cloud AI SDK provides specialized techniques for handling high-complexity models. Use the following resources to tune performance, implement custom logic, optimize performance through model sharding, and configure advanced postprocessing for vision-based workloads.

- [Custom operations (C++)](https://docs.qualcomm.com/doc/80-99100-3/topic/index_custom_ops.html)
- [Model sharding](https://docs.qualcomm.com/doc/80-99100-3/topic/index_model_sharding.html)
- [Object detection postprocessing](https://docs.qualcomm.com/doc/80-99100-3/topic/Object-Detection-Post-processing.html)
- [Model fine tuning](https://docs.qualcomm.com/doc/80-99100-3/topic/model-fine-tuning.html)

Last Published: Aug 25, 2026

[Previous Topic
Text Generation Inference (TGI)](https://docs.qualcomm.com/bundle/publicresource/80-99100-3/topics/index_TGI-Serving.md) [Next Topic
Custom operations (C++)](https://docs.qualcomm.com/bundle/publicresource/80-99100-3/topics/index_custom_ops.md)