Model Configuration¶

Each model in a Model Repository must include a file called config.pbtxt that contains the configuration information for the model. The model configuration must be specified as ModelConfig protobuf.

A minimal model configuration must specify name, platform, max_batch_size, input, and output.

As a running example consider a TensorRT model called mymodel that has two inputs, input0 and input1, and one output, output0, all of which are 16 entry float32 tensors. The minimal configuration is:

name: "mymodel"
platform: "tensorrt_plan"
max_batch_size: 8
input [
  {
    name: "input0"
    data_type: TYPE_FP32
    dims: [ 16 ]
  },
  {
    name: "input1"
    data_type: TYPE_FP32
    dims: [ 16 ]
  }
]
output [
  {
    name: "output0"
    data_type: TYPE_FP32
    dims: [ 16 ]
  }
]

The name of the model must match the name of the model repository directory containing the model. The platform must be one of tensorrt_plan, tensorflow_graphdef, tensorflow_savedmodel, or caffe2_netdef.

For models that support batched inputs the max_batch_size value must be >= 1. The inference server assumes that the batching occurs along a first dimension that is not listed in the inputs or outputs. For the above example the inference server expects to receive input tensors with shape [ x, 16 ] and produces an output tensor with shape [ x, 16 ], where x is the batch size of the request.

For models that do not support batched inputs the max_batch_size value must be zero. If the above example specified a max_batch_size of zero the inference server would expect to receive input tensors with shape [ 16 ], and would produce an output tensor with shape [ 16 ].

Version Policy¶

Each model can have one or more versions available in the model repository. The nvidia::inferenceserver::ModelVersionPolicy schema allows the following policies.

All: All versions of the model that are available in the model repository are available for inferencing.
Latest: Only the latest ‘n’ versions of the model in the repository are available for inferencing. The latest versions of the model are the numerically greatest version numbers.
Specific: Only the specifically listed versions of the model are available for inferencing.

If no version policy is specified, then Latest (with num_version = 1) is used as the default, indicating that only the most recent version of the model is made available by the inference server. In all cases, the addition or removal of version subdirectories from the model repository can change which model version is used on subsequent inference requests.

Continuing the above example, the following configuration specifies that all versions of the model will be available from the inference server:

name: "mymodel"
platform: "tensorrt_plan"
max_batch_size: 8
input [
  {
    name: "input0"
    data_type: TYPE_FP32
    dims: [ 16 ]
  },
  {
    name: "input1"
    data_type: TYPE_FP32
    dims: [ 16 ]
  }
]
output [
  {
    name: "output0"
    data_type: TYPE_FP32
    dims: [ 16 ]
  }
]
version_policy: { all { }}

Instance Groups¶

The inference server can provide multiple execution instances of a model so that multiple simultaneous inference requests for that model can be handled simultaneously. The model configuration ModelInstanceGroup is used to specify the number of execution instances that should be made available and what compute resource should be used for those instances.

By default, a single execution instance of the model is created for each GPU available in the system. The instance-group setting can be used to place multiple execution instances of a model on every GPU or on only certain GPUs. For example, the following configuration will place two execution instances of the model to be available on each system GPU:

instance_group [
  {
    count: 2
    kind: KIND_GPU
  }
]

And the following configuration will place one execution instance on GPU 0 and two execution instances on GPUs 1 and 2:

instance_group [
  {
    count: 1
    kind: KIND_GPU
    gpus: [ 0 ]
  },
  {
    count: 2
    kind: KIND_GPU
    gpus: [ 1, 2 ]
  }
]

The instance group setting is also used to enable exection of a model on the CPU. The following places two execution instances on the CPU:

instance_group [
  {
    count: 2
    kind: KIND_CPU
  }
]

Dynamic Batching¶

The inference server supports batch inferencing by allowing individual inference requests to specify a batch of inputs. The inferencing for a batch of inputs is processed at the same time which is especially important for GPUs since it can greatly increase inferencing throughput. In many use-cases the individual inference requests are not batched, therefore, they do not benefit from the throughput benefits of batching.

Dynamic batching is a feature of the inference server that allows non-batched inference requests to be combined by the inference server, so that a batch is created dynamically, resulting in the same increased throughput seen for batched inference requests.

Dynamic batching is enabled and configured independently for each model using the ModelDynamicBatching settings in the model configuration. These settings control the preferred size(s) of the dynamically created batches as well as a maximum time that requests can be delayed in the scheduler to allow other requests to join the dynamic batch.

The following configuration enables dynamic batching with preferred batch sizes of 4 and 8, and a maximum delay time of 100 microseconds:

dynamic_batching {
  preferred_batch_size: [ 4, 8 ]
  max_queue_delay_microseconds: 100
}

Optimization Policy¶

The model configuration ModelOptimizationPolicy is used to specify optimization settings for a model. These settings control if/how a model is optimized by the backend framework. See the protobuf documentation for the currently available settings.