Struct Cuda 

pub struct Cuda {
    pub graphs: bool,
    pub busy_wait_events: bool,
    pub graph_spec: Vec<GraphSpec>,
    pub output_copy_stream: bool,
}

@@ @@ .. cpp:var:: message Cuda @@ @@ CUDA-specific optimization settings. @@

Fields

graphs: bool

@@ .. cpp:var:: bool graphs @@ @@ Use CUDA graphs API to capture model operations and execute @@ them more efficiently. Default value is false. @@ Currently only recognized by TensorRT backend. @@

busy_wait_events: bool

@@ .. cpp:var:: bool busy_wait_events @@ @@ Use busy-waiting to synchronize CUDA events to achieve minimum @@ latency from event complete to host thread to be notified, with @@ the cost of high CPU load. Default value is false. @@ Currently only recognized by TensorRT backend. @@

graph_spec: Vec<GraphSpec>

@@ .. cpp:var:: GraphSpec graph_spec (repeated) @@ @@ Specification of the CUDA graph to be captured. If not specified @@ and ‘graphs’ is true, the default CUDA graphs will be captured @@ based on model settings. @@ Currently only recognized by TensorRT backend. @@

output_copy_stream: bool

@@ .. cpp:var:: bool output_copy_stream @@ @@ Uses a CUDA stream separate from the inference stream to copy the @@ output to host. However, be aware that setting this option to @@ true will lead to an increase in the memory consumption of the @@ model as Triton will allocate twice as much GPU memory for its @@ I/O tensor buffers. Default value is false. @@ Currently only recognized by TensorRT backend. @@

Trait Implementations

impl Clone for Cuda

fn clone(&self) -> Cuda

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Cuda

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

Formats the value using the given formatter.

impl Default for Cuda

fn default() -> Self

Returns the “default value” for a type.

impl Message for Cuda

fn encoded_len(&self) -> usize

Returns the encoded length of the message without a length delimiter.

fn clear(&mut self)

Clears the message, resetting all fields to their default.

fn encode(&self, buf: &mut impl BufMut) -> Result<(), EncodeError>

where Self: Sized,

Encodes the message to a buffer.

fn encode_to_vec(&self) -> Vec<u8>

where Self: Sized,

Encodes the message to a newly allocated buffer.

fn encode_length_delimited( &self, buf: &mut impl BufMut, ) -> Result<(), EncodeError>

where Self: Sized,

Encodes the message with a length-delimiter to a buffer.

fn encode_length_delimited_to_vec(&self) -> Vec<u8>

where Self: Sized,

Encodes the message with a length-delimiter to a newly allocated buffer.

fn decode(buf: impl Buf) -> Result<Self, DecodeError>

where Self: Default,

Decodes an instance of the message from a buffer.

fn decode_length_delimited(buf: impl Buf) -> Result<Self, DecodeError>

where Self: Default,

Decodes a length-delimited instance of the message from the buffer.

fn merge(&mut self, buf: impl Buf) -> Result<(), DecodeError>

where Self: Sized,

Decodes an instance of the message from a buffer, and merges it into self.

fn merge_length_delimited(&mut self, buf: impl Buf) -> Result<(), DecodeError>

where Self: Sized,

Decodes a length-delimited instance of the message from buffer, and merges it into self.

impl PartialEq for Cuda

fn eq(&self, other: &Cuda) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for Cuda