Struct ModelInferRequest 

pub struct ModelInferRequest {
    pub model_name: String,
    pub model_version: String,
    pub id: String,
    pub parameters: HashMap<String, InferParameter>,
    pub inputs: Vec<InferInputTensor>,
    pub outputs: Vec<InferRequestedOutputTensor>,
    pub raw_input_contents: Vec<Vec<u8>>,
}

@@ @@.. cpp:var:: message ModelInferRequest @@ @@ Request message for ModelInfer. @@

Fields

model_name: String

@@ .. cpp:var:: string model_name @@ @@ The name of the model to use for inferencing. @@

model_version: String

@@ .. cpp:var:: string model_version @@ @@ The version of the model to use for inference. If not @@ given the latest/most-recent version of the model is used. @@

id: String

@@ .. cpp:var:: string id @@ @@ Optional identifier for the request. If specified will be @@ returned in the response. @@

parameters: HashMap<String, InferParameter>

@@ .. cpp:var:: map<string,InferParameter> parameters @@ @@ Optional inference parameters. @@

inputs: Vec<InferInputTensor>

@@ @@ .. cpp:var:: InferInputTensor inputs (repeated) @@ @@ The input tensors for the inference. @@

outputs: Vec<InferRequestedOutputTensor>

@@ @@ .. cpp:var:: InferRequestedOutputTensor outputs (repeated) @@ @@ The requested output tensors for the inference. Optional, if not @@ specified all outputs specified in the model config will be @@ returned. @@

raw_input_contents: Vec<Vec<u8>>

@@ @@ .. cpp:var:: bytes raw_input_contents @@ @@ The data contained in an input tensor can be represented in @@ “raw” bytes form or in the repeated type that matches the @@ tensor’s data type. Using the “raw” bytes form will @@ typically allow higher performance due to the way protobuf @@ allocation and reuse interacts with GRPC. For example, see @@ https://github.com/grpc/grpc/issues/23231. @@ @@ To use the raw representation ‘raw_input_contents’ must be @@ initialized with data for each tensor in the same order as @@ ‘inputs’. For each tensor, the size of this content must @@ match what is expected by the tensor’s shape and data @@ type. The raw data must be the flattened, one-dimensional, @@ row-major order of the tensor elements without any stride @@ or padding between the elements. Note that the FP16 and BF16 data @@ types must be represented as raw content as there is no @@ specific data type for a 16-bit float type. @@ @@ If this field is specified then InferInputTensor::contents @@ must not be specified for any input tensor. @@

Trait Implementations

impl Clone for ModelInferRequest

fn clone(&self) -> ModelInferRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelInferRequest

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

Formats the value using the given formatter.

impl Default for ModelInferRequest

fn default() -> Self

Returns the “default value” for a type.

impl Message for ModelInferRequest

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 ModelInferRequest

fn eq(&self, other: &ModelInferRequest) -> 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 TryFrom<ModelInferRequest> for NvCreateCompletionRequest

type Error = Status

The type returned in the event of a conversion error.

fn try_from(request: ModelInferRequest) -> Result<Self, Self::Error>

Performs the conversion.

impl TryFrom<ModelInferRequest> for NvCreateTensorRequest

type Error = Status

The type returned in the event of a conversion error.

fn try_from(request: ModelInferRequest) -> Result<Self, Self::Error>

Performs the conversion.

impl StructuralPartialEq for ModelInferRequest