Struct ort::QNNExecutionProvider

pub struct QNNExecutionProvider { /* private fields */ }

Implementations

impl QNNExecutionProvider

pub fn with_backend_path(self, path: impl ToString) -> Self

The file path to QNN backend library. On Linux/Android, this is libQnnCpu.so to use the CPU backend, or libQnnHtp.so to use the accelerated backend.

pub fn with_enable_context_cache(self, enable: bool) -> Self

Configure whether to enable QNN graph creation from a cached QNN context file. If enabled, the QNN EP will load from the cached QNN context binary if it exists, or create one if it does not exist.

pub fn with_context_cache_path(self, path: impl ToString) -> Self

Explicitly provide the QNN context cache file (see QNNExecutionProvider::with_enable_context_cache). Defaults to model_file.onnx.bin if not provided.

pub fn with_profiling(self, level: QNNExecutionProviderProfilingLevel) -> Self

pub fn with_rpc_control_latency(self, latency: u32) -> Self

Allows client to set up RPC control latency in microseconds.

pub fn with_performance_mode( self, mode: QNNExecutionProviderPerformanceMode ) -> Self

pub fn build(self) -> ExecutionProviderDispatch

Trait Implementations

impl Clone for QNNExecutionProvider

fn clone(&self) -> QNNExecutionProvider

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for QNNExecutionProvider

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for QNNExecutionProvider

fn default() -> QNNExecutionProvider

Returns the “default value” for a type.

impl ExecutionProvider for QNNExecutionProvider

fn as_str(&self) -> &'static str

Returns the identifier of this execution provider used internally by ONNX Runtime.

fn supported_by_platform(&self) -> bool

Returns whether this execution provider is supported on this platform.

fn register(&self, session_builder: &SessionBuilder) -> Result<()>

Attempts to register this execution provider on the given session.

fn is_available(&self) -> Result<bool>

Returns Ok(true) if ONNX Runtime was compiled with support for this execution provider, and Ok(false) otherwise.

impl From<QNNExecutionProvider> for ExecutionProviderDispatch

fn from(value: QNNExecutionProvider) -> Self

Converts to this type from the input type.