# Java Interface

## Classes

- class QnnDelegate : public Delegate, AutoCloseable

    - - long getNativeHandle()

    - Get handle to the delegate.

- void close()

    - override method

Calls to Close() frees C-runtime resources TFLite.

- public static int[] getVersion()

    - Get QNN Delegate API version.

- void performanceVote()

    - Manual vote for performance. See HtpPerfCtrlStrategy option.

- void performanceRelease()

    - Manual release the vote for performance. See HtpPerfCtrlStrategy option.

- boolean isAvailable()

    - Check if the QnnDelegate is available on the platform.

For checking backend capability only, please refer to checkCapability().

- static boolean checkCapability([Capability](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate10CapabilityE) cap)

    - Check if the input capability is supported by the platform.

Note that it can be called prior to the construction of QnnDelegate class.

- enum class Capability

    - Lists the supported runtime types of the current platform.

- enumerator HTP\_RUNTIME\_QUANTIZED = 0

    - HTP hardware accelerator with quantized parameters.

- enumerator HTP\_RUNTIME\_FP16 = 1

    - HTP hardware accelerator with both quantized and half-precision floating-point parameters.

- enumerator GPU\_RUNTIME = 2

    - GPU hardware accelerator.

- enumerator DSP\_RUNTIME = 3

    - DSP hardware accelerator.

- enumerator INVALID = 99

    - Invalid option.

- QnnDelegate([Options](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7OptionsE) options)

    - QnnDelegate constructor.

This creates QnnDelegate object by passing in the options, throws
Exception if QnnDelegate is not available.

- Throw

    - UnsupportedOperationException

- class Options

    - final static class

> 
> 
> - Options()
> 
>     - 
> 
> 
> 
> 
> 
> - enum class BackendType
> 
>     - The QNN backend used to delegate the model’s nodes.
> Each backend has its own set of supported ops and tensor types.
> 
> 
> 
> - enumerator UNDEFINED\_BACKEND = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator GPU\_BACKEND = 1
> 
>     - Backend for Adreno^TM^ GPU hardware accelerator.
> 
> 
> 
> 
> 
> - enumerator HTP\_BACKEND = 2
> 
>     - Backend for Hexagon HTP hardware accelerator.
> 
> 
> 
> 
> 
> - enumerator DSP\_BACKEND = 3
> 
>     - Backend for Hexagon DSP hardware accelerator.
> 
> 
> 
> 
> 
> - enum class LogLevel
> 
>     - Logging level of the delegate and QNN backend.
> 
> 
> 
> - enumerator LOG\_OFF = 0
> 
>     - Disable delegate and QNN backend logging messages.
> 
> 
> 
> 
> 
> - enumerator LOG\_LEVEL\_ERROR = 1
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator LOG\_LEVEL\_WARN = 2
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator LOG\_LEVEL\_INFO = 3
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator LOG\_LEVEL\_VERBOSE = 4
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator LOG\_LEVEL\_DEBUG = 5
> 
>     -
> 
> 
> 
> 
> 
> - enum class ProfilingOptions
> 
>     - Options to profile the QNN Delegate execution.
> 
> 
> 
> - enumerator PROFILING\_OFF = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator BASIC\_PROFILING = 1
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator DETAILED\_PROFILING = 2
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator LINTING\_PROFILING = 3
> 
>     -
> 
> 
> 
> 
> 
> - enum class GpuPrecision
> 
>     - Defines the optimization levels of the graph tensors that are not
> input nor output tensors. This enum controls the trade-off between
> performance and accuracy.
> 
> 
> 
> - enumerator GPU\_PRECISION\_USER\_PROVIDED = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator GPU\_PRECISION\_FP32 = 1
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator GPU\_PRECISION\_FP16 = 2
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator GPU\_PRECISION\_HYBRID = 3
> 
>     -
> 
> 
> 
> 
> 
> - enum class GpuPerformanceMode
> 
>     - Defines performance modes available for Gpu backend.
> 
> 
> 
> - enumerator GPU\_PERFORMANCE\_DEFAULT = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator GPU\_PERFORMANCE\_HIGH = 1
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator GPU\_PERFORMANCE\_NORMAL = 2
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator GPU\_PERFORMANCE\_LOW = 3
> 
>     -
> 
> 
> 
> 
> 
> - enum class HtpPerformanceMode
> 
>     - Defines performance modes available for HTP backend.
> 
> 
> 
> - enumerator PERFORMANCE\_DEFAULT = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_SUSTAINED\_HIGH\_PERFORMANCE = 1
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_BURST = 2
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_HIGH\_PERFORMANCE = 3
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_POWER\_SAVER = 4
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_LOW\_POWER\_SAVER = 5
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_HIGH\_POWER\_SAVER = 6
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_LOW\_BALANCE = 7
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_BALANCE = 8
> 
>     -
> 
> 
> 
> 
> 
> - enum class HtpPrecision
> 
>     - Defines the precision modes supported by the HTP backend. HTP\_PRECISION\_FP16 supports quantized networks, and also floating-point networks on certain SoCs. Default: HTP\_PRECISION\_FP16
> 
> 
> 
> - enumerator HTP\_PRECISION\_QUANTIZED = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator HTP\_PRECISION\_FP16 = 1
> 
>     -
> 
> 
> 
> 
> 
> - enum class HtpUseConvHmx
> 
>     - Using short conv hmx might have better performance.
> However, convolution having short depth and/or weights that are not symmetric could exhibit inaccurate results.(Default is HTP\_CONV\_HMX\_ON = 1)
> 
> 
> 
> - enumerator HTP\_CONV\_HMX\_OFF = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator HTP\_CONV\_HMX\_ON = 1
> 
>     -
> 
> 
> 
> 
> 
> - enum class HtpUseFoldRelu
> 
>     - Using fold relu might have better performance.
> However, this optimization is correct when the quantization ranges of convolutions are equal or subset of
> Relu operations.
> 
> 
> 
> - enumerator HTP\_FOLD\_RELU\_OFF = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator HTP\_FOLD\_RELU\_ON = 1
> 
>     -
> 
> 
> 
> 
> 
> - enum class HtpOptimizationStrategy
> 
>     - Defines the optimization strategy used by the HTP backend.
> 
> 
> 
> - enumerator HTP\_OPTIMIZE\_FOR\_INFERENCE = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator HTP\_OPTIMIZE\_FOR\_PREPARE = 1
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator HTP\_OPTIMIZE\_FOR\_INFERENCE\_O3 = 2
> 
>     -
> 
> 
> 
> 
> 
> - enum class DspPerformanceMode
> 
>     - Defines performance modes available for DSP backend.
> 
> 
> 
> - enumerator PERFORMANCE\_DEFAULT = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_SUSTAINED\_HIGH\_PERFORMANCE = 1
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_BURST = 2
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_HIGH\_PERFORMANCE = 3
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_POWER\_SAVER = 4
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_LOW\_POWER\_SAVER = 5
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_HIGH\_POWER\_SAVER = 6
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_LOW\_BALANCE = 7
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator PERFORMANCE\_BALANCE = 8
> 
>     -
> 
> 
> 
> 
> 
> - enum class HtpPerfCtrlStrategy
> 
>     - Defines HTP performance control strategy.
> 
> 
> **Manual**: The performance mode is voted as the backend is initialized, and released
> at the moment of the backend is destroyed.
> 
> 
> Users can control the vote/release of the performance mode by instance methods
> performanceVote() and performanceRelease().
> 
> 
> Note that this is the default strategy.
> 
> 
> For example, users can vote before inferences, and release after all inference done.
> 
> 
> QnnDelegate qnnDelegate = new QnnDelegate(htpOptions);
>     // initialize other stuff...
>     qnnDelegate.performanceVote();
>     // invoke inferences...
>     qnnDelegate.performanceRelease();
>     Copy to clipboard
> 
> 
> **AUTO**: QNN Delegate vote before an inference, and release after an idle interval,
> i.e.no more inference.
> 
> 
> 
> - enumerator HTP\_PERF\_CTRL\_MANUAL = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator HTP\_PERF\_CTRL\_AUTO = 1
> 
>     -
> 
> 
> 
> 
> 
> - enum class DspPerfCtrlStrategy
> 
>     - Defines DSP performance control strategy. Similar to HTP cases.
> 
> 
> 
> - enumerator DSP\_PERF\_CTRL\_MANUAL = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator DSP\_PERF\_CTRL\_AUTO = 1
> 
>     -
> 
> 
> 
> 
> 
> - enum class HtpPdSession
> 
>     - Defines pd sessions available for HTP backend.
> 
> 
> 
> - enumerator HTP\_PD\_SESSION\_UNSIGNED = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator HTP\_PD\_SESSION\_SIGNED = 1
> 
>     -
> 
> 
> 
> 
> 
> - enum class DspPdSession
> 
>     - Defines pd sessions available for DSP backend.
> 
> 
> 
> - enumerator DSP\_PD\_SESSION\_UNSIGNED = 0
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator DSP\_PD\_SESSION\_SIGNED = 1
> 
>     - 
> 
> 
> 
> 
> 
> - enumerator DSP\_PD\_SESSION\_ADAPTIVE = 2
> 
>     -
> 
> 
> 
> 
> 
> - class OpPackageInfo
> 
>     - static final
> 
> 
> Class containing the information needed to register and use an op
> package with QNN.
> 
> 
> 
> - OpPackageInfo(String name, String path, String provider, String Target, HashMap<String, String> opsMap)
> 
>     - OpPackageInfo constructor.
> 
> 
> 
> - Parameters
> 
>     - - **String name** – The name of the op package
> - **String path** – The path on disk to the op package library
> - **String provider** – The name of a function in the op package library which satisfies the QnnOpPackage\_InterfaceProvider\_t interface
> - **String target** – The target which this op package library was compiled for
> - **HashMap<String, String> opsMap** – Map of TFLite custom operator name to op type defined within an op package
> 
> 
> 
> 
> 
> - int getBackendType()
> 
>     - Getter function to retrieve the integer that represents the BackendType.
> 
> 
> 
> 
> 
> - String getLibraryPath()
> 
>     - Getter function to retrieve library path.
> 
> 
> 
> 
> 
> - String getSkelLibraryDir()
> 
>     - Getter function to retrieve Skel library.
> 
> 
> 
> 
> 
> - int getGpuPrecision()
> 
>     - Getter function to retrieve the integer that represents the GpuPrecision.
> 
> 
> 
> 
> 
> - int getGpuPerformanceMode()
> 
>     - Getter function to retrieve the integer that represents the GpuPerformanceMode.
> 
> 
> 
> 
> 
> - int getHtpPerformanceMode()
> 
>     - Getter function to retrieve the integer that represents the HtpPerformanceMode.
> 
> 
> 
> 
> 
> - int getHtpPrecision()
> 
>     - Getter function to retrieve the integer that represents the HtpPrecision.
> 
> 
> 
> 
> 
> - int getHtpUseConvHmx()
> 
>     - Getter function to retrieve the integer that represents the HtpUseConvHmx.
> 
> 
> 
> 
> 
> - int getHtpUseFoldRelu()
> 
>     - Getter function to retrieve the integer that represents the HtpUseFoldRelu.
> 
> 
> 
> 
> 
> - int getHtpPdSession()
> 
>     - Getter function to retrieve the integer that represents the HtpPdSession.
> 
> 
> 
> 
> 
> - int getHtpOptimizationStrategy()
> 
>     - Getter function to retrieve the integer that represents the HtpOptimizationStrategy.
> 
> 
> 
> 
> 
> - int getHtpPerfCtrlStrategy()
> 
>     - Getter function to retrieve the integer that represents the HtpPerfCtrlStrategy.
> 
> 
> 
> 
> 
> - int getDspPerformanceMode()
> 
>     - Getter function to retrieve the integer that represents the DspPerformanceMode.
> 
> 
> 
> 
> 
> - int getDspPdSession()
> 
>     - Getter function to retrieve the integer that represents the DspPdSession.
> 
> 
> 
> 
> 
> - int getDspPerfCtrlStrategy()
> 
>     - Getter function to retrieve the integer that represents the DspPerfCtrlStrategy.
> 
> 
> 
> 
> 
> - int getLogLevel()
> 
>     - Getter function to retrieve the integer that represents the LogLevel.
> 
> 
> 
> 
> 
> - int getProfiling()
> 
>     - Getter function to retrieve the integer that represents the ProfilingOptions.
> 
> 
> 
> 
> 
> - String getCacheDir()
> 
>     - Getter function to retrieve the cache directory.
> 
> 
> 
> 
> 
> - String getModelToken()
> 
>     - Getter function to retrieve the model token.
> 
> 
> 
> 
> 
> - int getOpPackageInfosLength()
> 
>     - Getter function to retrieve the number of OpPackageInfo.
> 
> 
> 
> 
> 
> - public OpPackageInfo[] getOpPackageInfos()
> 
>     - Getter function to retrieve the OpPackageInfo array.
> 
> 
> 
> 
> 
> - public int[] getSkipNodeIds()
> 
>     - Getter function to retrieve the arrays containing node ids to skip.
> 
> 
> 
> 
> 
> - public int[] getSkipOps()
> 
>     - Getter function to retrieve the arrays containing node ops to skip.
> 
> 
> 
> 
> 
> - void setBackendType([BackendType](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options11BackendTypeE) input)
> 
>     - The backend QNN library to open and execute the graph with. This is a
> required argument and will error out if kUndefinedBackend is
> supplied.
> 
> 
> 
> 
> 
> - void setLibraryPath(String input)
> 
>     - Optional parameter to override the QNN backend library.
> 
> 
> 
> 
> 
> - void setSkelLibraryDir(String input)
> 
>     - Optional parameter to directory of the QNN Skel library. Only useful
> for backends which have a Skel library.
> 
> 
> 
> 
> 
> - void setGpuOptions([GpuPrecision](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options12GpuPrecisionE) input)
> 
>     - Optional backend specific options for the GPU backend. Only used
> when selecting kGpuBackend, else will be ignored.
> 
> 
> Warning
> 
> 
> setGpuOptions() is deprecated, and will be removed in the future release.
> Instead, please use below individual setters for each options.
> 
> 
> 
> 
> 
> - void setGpuPerformanceMode([GpuPerformanceMode](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options18GpuPerformanceModeE) mode)
> 
>     - Set GPU Performance mode.
> 
> 
> 
> 
> 
> - void setGpuPrecision([GpuPrecision](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options12GpuPrecisionE) precision)
> 
>     - Set GPU Precision.
> 
> 
> 
> 
> 
> - void setHtpOptions([HtpPerformanceMode](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options18HtpPerformanceModeE) mode, [HtpPrecision](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options12HtpPrecisionE) precision, [HtpPdSession](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options12HtpPdSessionE) pdSession, [HtpOptimizationStrategy](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options23HtpOptimizationStrategyE) optimizationStrategy)
> 
>     - Optional backend specific options for the HTP backend. Only used when
> selecting HTP\_BACKEND, else will be ignored.
> 
> 
> Warning
> 
> 
> setHtpOptions() is deprecated, and will be removed in the future release.
> Instead, please use below individual setters for each options.
> 
> 
> 
> 
> 
> - void setHtpPerformanceMode([HtpPerformanceMode](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options18HtpPerformanceModeE) mode)
> 
>     - Set HTP Performance mode.
> 
> 
> 
> 
> 
> - boolean enableHtpQuickResponse()
> 
>     - This option enhances the HTP response time in performance\_mode == burst. However, it requires more power wattage than the usual burst mode.
> HTP quick response mode will be enabled if at least one delegate is in burst mode and enableHtpQuickResponse() is called.
> Return value can be used to check if HTP quick response is enabled successfully.
> 
> 
> 
> 
> 
> - void setHtpPrecision([HtpPrecision](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options12HtpPrecisionE) precision)
> 
>     - Set HTP Precision.
> 
> 
> 
> 
> 
> - void setHtpPdSession([HtpPdSession](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options12HtpPdSessionE) pdSession)
> 
>     - Set HTP PdSession.
> 
> 
> 
> 
> 
> - void setHtpOptimizationStrategy([HtpOptimizationStrategy](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options23HtpOptimizationStrategyE) optimizationStrategy)
> 
>     - Set HTP Optimization Strategy.
> 
> 
> 
> 
> 
> - void setHtpPerfCtrlStrategy([HtpPerfCtrlStrategy](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options19HtpPerfCtrlStrategyE) perfCtrl)
> 
>     - Set HTP Performance control strategy.
> 
> 
> 
> 
> 
> - void setDspOptions([DspPerformanceMode](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options18DspPerformanceModeE) mode, [DspPdSession](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options12DspPdSessionE) pdSession)
> 
>     - Optional backend specific options for the DSP backend. Only used when
> selecting DSP\_BACKEND, else will be ignored.
> 
> 
> Warning
> 
> 
> setDspOptions() is deprecated, and will be removed in the future release.
> Instead, please use below individual setters for each options.
> 
> 
> 
> 
> 
> - void setDspPerformanceMode([DspPerformanceMode](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options18DspPerformanceModeE) mode)
> 
>     - Set DSP Performance mode.
> 
> 
> 
> 
> 
> - void setDspPdSession([DspPdSession](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options12DspPdSessionE) pdSession)
> 
>     - Set DSP PdSession.
> 
> 
> 
> 
> 
> - void setDspPerfCtrlStrategy([DspPerfCtrlStrategy](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options19DspPerfCtrlStrategyE) perfCtrl)
> 
>     - Set DSP Performance control strategy.
> 
> 
> 
> 
> 
> - void setLogLevel([LogLevel](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options8LogLevelE) input)
> 
>     - Logging level of the delegate and the backend. Default is off.
> 
> 
> 
> 
> 
> - void setProfiling([ProfilingOptions](https://docs.qualcomm.com/doc/80-63442-50/topic/java_interface.html#_CPPv4N11QnnDelegate7Options16ProfilingOptionsE) input)
> 
>     - Option to enable profiling with the delegate. Default is off.
> 
> 
> 
> 
> 
> - public void setOpPackageOptions(OpPackageInfo[] info)
> 
>     - Optional structure to specify custom op packages for the backend.
> 
> 
> 
> 
> 
> - void setCacheDir(String input)
> 
>     - Specifies the directory of a compiled model.  Signals intent to either:
> 
> 
> 
> > 
> > 
> > - Save the model if the file doesn’t exist, or
> > - Restore model from the file.
> 
> 
> 
> Model Cache specific options. Only used when setting
> `setModelToken`, else will be ignored.
> 
> 
> 
> 
> 
> - void setModelToken(String input)
> 
>     - The unique nul-terminated token string that acts as a ‘namespace’ for
> all serialization entries.
> Should be unique to a particular model (graph & constants).
> 
> 
> Model Cache specific options. Only used when setting
> `setCacheDir`, else will be ignored.
> 
> 
> 
> 
> 
> - public void setSkipNodeIds(int[] ids)
> 
>     - Set nodes not to be delegated by their node ids.
> Node ids can be obtained from the nodes’ location information in .tflite files.
> 
> 
> 
> 
> 
> - public void setSkipOps(int[] ops)
> 
>     - Set ops not to be delegated by their built-in id(s).
> Please refer to tensorflow/lite/builtin\_ops.h for the op built-in ids.
> Note that we skip *ALL* same type of ops specified.
> For example, if you skip SquaredDifference in your model,
> all of the SquaredDifference ops in the model will not be delegated.
> 
> 
> 
> 
> 
> - public byte[] getProfilingResult()
> 
>     - Get the profiling result, after profiling level is set. Note that the ownership of
> the returned byte array is transferred to user. Empty result will be returned from
> the second time on if this function is called consecutively.

Last Published: Oct 10, 2025

[Previous Topic
Qualcomm® AI Engine Direct Delegate Java Interface](https://docs.qualcomm.com/bundle/publicresource/80-63442-50/topics/TfLite-Delegate_api.md) [Next Topic
External Delegate Interface](https://docs.qualcomm.com/bundle/publicresource/80-63442-50/topics/TfLite-Delegate_api.md)