Struct ModelConfig

pub struct ModelConfig {

    pub name: String,
    pub platform: String,
    pub backend: String,
    pub version_policy: Option<ModelVersionPolicy>,
    pub max_batch_size: i32,
    pub input: Vec<ModelInput>,
    pub output: Vec<ModelOutput>,
    pub batch_input: Vec<BatchInput>,
    pub batch_output: Vec<BatchOutput>,
    pub optimization: Option<ModelOptimizationPolicy>,
    pub instance_group: Vec<ModelInstanceGroup>,
    pub default_model_filename: String,
    pub cc_model_filenames: HashMap<String, String>,
    pub metric_tags: HashMap<String, String>,
    pub parameters: HashMap<String, ModelParameter>,
    pub model_warmup: Vec<ModelWarmup>,
    pub model_operations: Option<ModelOperations>,
    pub model_transaction_policy: Option<ModelTransactionPolicy>,
    pub model_repository_agents: Option<ModelRepositoryAgents>,
    pub response_cache: Option<ModelResponseCache>,
    pub scheduling_choice: Option<SchedulingChoice>,
}

@@ @@.. cpp:var:: message ModelConfig @@ @@ A model configuration. @@

Fields

name: String

@@ .. cpp:var:: string name @@ @@ The name of the model. @@

platform: String

@@ .. cpp:var:: string platform @@ @@ The framework for the model. Possible values are @@ “tensorrt_plan”, “tensorflow_graphdef”, @@ “tensorflow_savedmodel”, “onnxruntime_onnx”, @@ “pytorch_libtorch”. @@

backend: String

@@ .. cpp:var:: string backend @@ @@ The backend used by the model. @@

version_policy: Option<ModelVersionPolicy>

@@ .. cpp:var:: ModelVersionPolicy version_policy @@ @@ Policy indicating which version(s) of the model will be served. @@

max_batch_size: i32

@@ .. cpp:var:: int32 max_batch_size @@ @@ Maximum batch size allowed for inference. This can only decrease @@ what is allowed by the model itself. A max_batch_size value of 0 @@ indicates that batching is not allowed for the model and the @@ dimension/shape of the input and output tensors must exactly @@ match what is specified in the input and output configuration. A @@ max_batch_size value > 0 indicates that batching is allowed and @@ so the model expects the input tensors to have an additional @@ initial dimension for the batching that is not specified in the @@ input (for example, if the model supports batched inputs of @@ 2-dimensional tensors then the model configuration will specify @@ the input shape as [ X, Y ] but the model will expect the actual @@ input tensors to have shape [ N, X, Y ]). For max_batch_size > 0 @@ returned outputs will also have an additional initial dimension @@ for the batch. @@

input: Vec<ModelInput>

@@ .. cpp:var:: ModelInput input (repeated) @@ @@ The inputs request by the model. @@

output: Vec<ModelOutput>

@@ .. cpp:var:: ModelOutput output (repeated) @@ @@ The outputs produced by the model. @@

batch_input: Vec<BatchInput>

@@ .. cpp:var:: BatchInput batch_input (repeated) @@ @@ The model input(s) that the server should use to communicate @@ batch related values to the model. @@

batch_output: Vec<BatchOutput>

@@ .. cpp:var:: BatchOutput batch_output (repeated) @@ @@ The outputs produced by the model that requires special handling @@ by the model backend. @@

optimization: Option<ModelOptimizationPolicy>

@@ .. cpp:var:: ModelOptimizationPolicy optimization @@ @@ Optimization configuration for the model. If not specified @@ then default optimization policy is used. @@

instance_group: Vec<ModelInstanceGroup>

@@ .. cpp:var:: ModelInstanceGroup instance_group (repeated) @@ @@ Instances of this model. If not specified, one instance @@ of the model will be instantiated on each available GPU. @@

default_model_filename: String

@@ .. cpp:var:: string default_model_filename @@ @@ Optional filename of the model file to use if a @@ compute-capability specific model is not specified in @@ :cpp:var:cc_model_filenames. If not specified the default name @@ is ‘model.graphdef’, ‘model.savedmodel’, ‘model.plan’ or @@ ‘model.pt’ depending on the model type. @@

cc_model_filenames: HashMap<String, String>

@@ .. cpp:var:: map<string,string> cc_model_filenames @@ @@ Optional map from CUDA compute capability to the filename of @@ the model that supports that compute capability. The filename @@ refers to a file within the model version directory. @@

metric_tags: HashMap<String, String>

@@ .. cpp:var:: map<string,string> metric_tags @@ @@ Optional metric tags. User-specific key-value pairs for metrics @@ reported for this model. These tags are applied to the metrics @@ reported on the HTTP metrics port. @@

parameters: HashMap<String, ModelParameter>

@@ .. cpp:var:: map<string,ModelParameter> parameters @@ @@ Optional model parameters. User-specified parameter values. @@

model_warmup: Vec<ModelWarmup>

@@ .. cpp:var:: ModelWarmup model_warmup (repeated) @@ @@ Warmup setting of this model. If specified, all instances @@ will be run with the request samples in sequence before @@ serving the model. @@ This field can only be specified if the model is not an ensemble @@ model. @@

model_operations: Option<ModelOperations>

@@ .. cpp:var:: ModelOperations model_operations @@ @@ Optional metadata of the libraries providing custom operations for @@ this model. @@

model_transaction_policy: Option<ModelTransactionPolicy>

@@ .. cpp:var:: ModelTransactionPolicy model_transaction_policy @@ @@ Optional specification that describes the nature of transactions @@ to be expected from the model. @@

model_repository_agents: Option<ModelRepositoryAgents>

@@ .. cpp:var:: ModelRepositoryAgents model_repository_agents @@ @@ Optional specification of the agent(s) that should be invoked @@ with repository actions are performed for this model. @@

response_cache: Option<ModelResponseCache>

@@ .. cpp:var:: ModelResponseCache response_cache @@ @@ Optional setting for utilizing the response cache for this @@ model. @@

scheduling_choice: Option<SchedulingChoice>

@@ .. cpp:var:: oneof scheduling_choice @@ @@ The scheduling policy for the model. If not specified the @@ default scheduling policy is used for the model. The default @@ policy is to execute each inference request independently. @@

Trait Implementations

impl Clone for ModelConfig

fn clone(&self) -> ModelConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelConfig

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

Formats the value using the given formatter.

impl Default for ModelConfig

fn default() -> Self

Returns the “default value” for a type.

impl Message for ModelConfig

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<B>(&self, buf: &mut B) -> Result<(), EncodeError>

where B: BufMut, 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<B>(&self, buf: &mut B) -> Result<(), EncodeError>

where B: BufMut, 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<B>(buf: B) -> Result<Self, DecodeError>

where B: Buf, Self: Default,

Decodes an instance of the message from a buffer.

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

where B: Buf, Self: Default,

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

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

where B: Buf, Self: Sized,

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

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

where B: Buf, Self: Sized,

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

impl PartialEq for ModelConfig

fn eq(&self, other: &ModelConfig) -> 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 ModelConfig