Struct CoreMLExecutionProvider

pub struct CoreMLExecutionProvider { /* private fields */ }

Implementations

impl CoreMLExecutionProvider

pub fn with_cpu_only(self) -> Self

Limit CoreML to running on CPU only. This may decrease the performance but will provide reference output value without precision loss, which is useful for validation.

pub fn with_subgraphs(self) -> Self

Enable CoreML EP to run on a subgraph in the body of a control flow operator (i.e. a Loop, Scan or If operator).

pub fn with_ane_only(self) -> Self

By default the CoreML EP will be enabled for all compatible Apple devices. Setting this option will only enable CoreML EP for Apple devices with a compatible Apple Neural Engine (ANE). Note, enabling this option does not guarantee the entire model to be executed using ANE only.

pub fn build(self) -> ExecutionProviderDispatch

Trait Implementations

impl Clone for CoreMLExecutionProvider

fn clone(&self) -> CoreMLExecutionProvider

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for CoreMLExecutionProvider

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

Formats the value using the given formatter.

impl Default for CoreMLExecutionProvider

fn default() -> CoreMLExecutionProvider

Returns the “default value” for a type.

impl ExecutionProvider for CoreMLExecutionProvider

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: &mut 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<CoreMLExecutionProvider> for ExecutionProviderDispatch

fn from(value: CoreMLExecutionProvider) -> Self

Converts to this type from the input type.