# Delegates

Source: [https://docs.qualcomm.com/doc/80-70014-54/topic/delegates.html](https://docs.qualcomm.com/doc/80-70014-54/topic/delegates.html)

Delegates help you offload the TensorFlow Lite graph execution to the CPU, GPU, and
        Hexagon Tensor Processor hardware accelerators.

Currently, the following delegates are supported:

- **[XNNPACK delegate for CPU](https://docs.qualcomm.com/doc/80-70014-54/topic/xnnpack-delegate-for-cpu.html)**  

The XNNPACK delegate uses the XNNPACK library to accelerate TensorFlow Lite models on         CPUs efficiently.
- **[GPU delegate](https://docs.qualcomm.com/doc/80-70014-54/topic/gpu-delegate.html)**  

The GPU open-source delegate provides acceleration on various vendor-specific GPUs,         including the Adreno GPU.
- **[QNN delegate](https://docs.qualcomm.com/doc/80-70014-54/topic/qnn-delegate.html)**  

The QNN delegate is a proprietary delegate for vendor-specific hardware acceleration         to accelerate TensorFlow Lite models. The QNN delegate is designed based on the TensorFlow         Lite's [external delegate interface](https://www.tensorflow.org/lite/performance/implementing_delegate). You can use the QNN         delegate to offload parts or the entire TensorFlow Lite model to specialized Qualcomm         hardware, such as the Adreno GPU and Hexagon Tensor Processor.

**Parent Topic:** [Architecture](https://docs.qualcomm.com/doc/80-70014-54/topic/arch.html)

Last Published: Jul 12, 2024

[Previous Topic
TensorFlow Lite Runtime](https://docs.qualcomm.com/bundle/publicresource/80-70014-54/topics/tensorflow-lite-runtime.md) [Next Topic
XNNPACK delegate for CPU](https://docs.qualcomm.com/bundle/publicresource/80-70014-54/topics/xnnpack-delegate-for-cpu.md)