# External Delegate Options Since the setup:External Delegate Interface dynamically loads the Qualcomm® AI Engine Direct Delegate, it has no static knowledge of the Qualcomm® AI Engine Direct Delegate options. Instead, the External Delegate passes key value pairs of strings down to the Qualcomm® AI Engine Direct Delegate to be parsed as the options. As a result, the application using the External Delegate Interface requires previous knowledge of the accepted key and value options strings. The following table lists the key value option strings that are available in Qualcomm® AI Engine Direct Delegate. | Option Key | Option Value | Default Value | Mandatory | Description | | --- | --- | --- | --- | --- | | backend\_type | gpu, htp, dsp | N/A | Yes | The backend Qualcomm® AI Engine Direct library to open and execute the graph with.
See [Acceleration Support](https://docs.qualcomm.com/doc/80-63442-50/topic/support.html) for the supported backends. | | gpu\_precision | 0, 1, 2, 3 | 2 = Float16 for best performance | No | Precision for GPU backend that defines the optimization levels of the
graph tensors that are not input nor output tensors.



>
>
> | | gpu\_performance\_mode | 0, 1, 2, 3 | 0 = Default | No | Flag to provide precision modes supported by the GPU backend.



>
>
> | | dsp\_performance\_mode | 0, 1, 2, 3, 4, 5, 6, 7, 8 | 0 = Default | No | When performance\_mode is used, the delegate will
vote for the provided performance level during inference and
will return back to relaxed vote after the inference has completed.



>
>
> | | dsp\_pd\_session | unsigned, signed, adaptive | unsigned | No | Flag defines the pd session of DSP backend.
Unsigned is used for unsigned pd while signed is for signed pd.
For those without knowledge about pd, adaptive is a good option to
automatically choose the pd session from unsigned and signed pd. | | dsp\_perf\_ctrl\_strategy | 0, 1 | 0 = Manual | No | Flag to select DSP perforamnce control strategy. Manual vote the
performance while the backend is initialized, and release the performance
at the moment of the backend is destroyed.

| | dsp\_encoding\_mode | 0, 1 | 0 = Static | No | Flag to select DSP encoding mode, only support DSP backend. Dynamic encoding is more precise but
sacrifices a bit of performance.

| | htp\_performance\_mode | 0, 1, 2, 3, 4, 5, 6, 7, 8 | 0 = Default | No | When performance\_mode is used, the delegate will
vote for the provided performance level during inference and
will return back to relaxed vote after the inference has completed.



>
>
> | | htp\_pd\_session | unsigned, signed | unsigned | No | Flag defines the pd session of HTP backend. | | htp\_optimization\_strategy | 0, 1, 2 | 0 = Optimize for Inference | No | Flag to select optimization strategy used by the HTP backend. The
default optimization strategy will optimize the graph for inference.

| | htp\_perf\_ctrl\_strategy | 0, 1 | 0 = Manual | No | Flag to select HTP perforamnce control strategy. Manual vote the
performance while the backend is initialized, and release the performance
at the moment of the backend is destroyed.

| | htp\_use\_conv\_hmx | 0, 1 | 1 = enable HMX for short depth conv2d. | No | Flag to enable HMX for short depth conv2d. Please see C interface or qnn_delegate.h for details.

| | htp\_use\_fold\_relu | 0, 1 | 0 = don’t fuse Relu into conv2d. | No | Flag to enable fusion of Relu into conv2d. Please see C interface or qnn_delegate.h for details.

| | htp\_device\_id | 0 or positive integer | 0 = Default | No | If the SoC has more than 1 HTP device, you can choose a device by the device id. | | library\_path | <Path to backend library file> | Default library associated with chosen Qualcomm® AI Engine Direct backend | No | Optional parameter to override the Qualcomm® AI Engine Direct backend library. | | log\_level | 0, 1, 2, 3, 4, 5 | 0 = Off | No | Logging level of the delegate and the backend between 0-5, higher is
more verbose.



>
>
> | | cache\_dir | <Full path to a directory> | N/A | No | Specifies the directory of a compiled model. Signals intent to either:



Model Cache specific options. Only used when setting
`model_token`, else will be ignored. | | model\_token | <model token name> | N/A | No | The unique null-terminated token string that acts as a ‘namespace’ for
all serialization entries.
Should be unique to a particular model (graph & constants).
For an example of how to generate this from a TFLite model, see
StrFingerprint() in lite/delegates/serialization.h.
Model Cache specific options. Only used when setting
`cache_dir`, else will be ignored. | | profiling | 0, 1, 2 | 0 = Off | No | How to profile the delegate execution. Use to add profiling level to
TFLite/QNN Profiler object. Qnn Profiler will be used unless Tensorflow Lite benchmark\_model is used.
However, note that the behavior of profiling is subjected to change in the future.



>
>
> | | skel\_library\_dir | <Path to dir> | N/A | No | Directory of Qualcomm® AI Engine Direct Skel Library. Optional parameter to directory of the
Qualcomm® AI Engine Direct Skel library. Only useful for backends which have a Skel library. | Last Published: Oct 10, 2025 [Previous Topic External Delegate Interface](https://docs.qualcomm.com/bundle/publicresource/80-63442-50/topics/TfLite-Delegate_api.md) [Next Topic Qualcomm® AI Engine Direct Backend Library](https://docs.qualcomm.com/bundle/publicresource/80-63442-50/topics/qnn_libs.md)