Shortcuts

ts package

Subpackages

Submodules

ts.arg_parser module

This module parses the arguments given through the torchserve command-line. This is used by model-server at runtime.

class ts.arg_parser.ArgParser[source]

Bases: object

Argument parser for torchserve and torchserve-export commands TODO : Add readme url

static extract_args(args=None)[source]
static model_service_worker_args()[source]

ArgParser for backend worker. Takes the socket name and socket type. :return:

static ts_parser()[source]

Argument parser for torchserve start service

ts.context module

Context object of incoming request

class ts.context.Context(model_name, model_dir, manifest, batch_size, gpu, mms_version, limit_max_image_pixels=True, metrics=None, model_yaml_config=None)[source]

Bases: object

Context stores model relevant worker information Some fixed during load times and some set by the service

get_all_request_header(idx: int) Dict[str, str][source]
get_request_header(idx: int, key: str) Optional[str][source]
get_request_id(idx: int = 0) Optional[str][source]
get_response_content_type(idx: int) Optional[str][source]
get_response_headers(idx: int) Dict[str, str][source]
get_response_status(idx: int) Tuple[int, str][source]
get_sequence_id(idx: int) str[source]
property metrics
property request_processor
set_all_response_status(code: int = 200, phrase: str = '') None[source]

Set the status code of individual requests :param phrase: :param code: :return:

set_response_content_type(idx: int, value: str) None[source]
set_response_header(idx, key, value)[source]
set_response_status(code: int = 200, phrase: str = '', idx: int = 0)[source]

Set the status code of individual requests :param phrase: :param idx: The index data in the list(data) that is sent to the handle() method :param code: :return:

property system_properties
class ts.context.RequestProcessor(request_header: dict)[source]

Bases: object

Request processor

add_response_property(key: str, value: str) None[source]
get_request_properties() dict[source]
get_request_property(key: str) Optional[str][source]
get_response_header(key: str) Optional[str][source]
get_response_headers() dict[source]
get_response_status_code() int[source]
get_response_status_phrase() Optional[str][source]
report_status(code, reason_phrase=None) None[source]

ts.model_loader module

Model loader.

class ts.model_loader.ModelLoader[source]

Bases: object

Base Model Loader class.

abstract load(model_name: str, model_dir: str, handler: Optional[str] = None, gpu_id: Optional[int] = None, batch_size: Optional[int] = None, envelope: Optional[str] = None, limit_max_image_pixels: Optional[bool] = True)[source]

Load model from file.

Parameters:
  • model_name

  • model_dir

  • handler

  • gpu_id

  • batch_size

  • envelope

  • limit_max_image_pixels

Returns:

Model

class ts.model_loader.ModelLoaderFactory[source]

Bases: object

static get_model_loader()[source]
class ts.model_loader.TsModelLoader[source]

Bases: ModelLoader

TorchServe 1.0 Model Loader

load(model_name: str, model_dir: str, handler: Optional[str] = None, gpu_id: Optional[int] = None, batch_size: Optional[int] = None, envelope: Optional[str] = None, limit_max_image_pixels: Optional[bool] = True, metrics_cache: Optional[MetricsCacheYamlImpl] = None) Service[source]

Load TorchServe 1.0 model from file.

Parameters:
  • model_name

  • model_dir

  • handler

  • gpu_id

  • batch_size

  • envelope

  • limit_max_image_pixels

  • metrics_cache – MetricsCacheYamlImpl object

Returns:

ts.model_server module

File to define the entry point to Model Server

ts.model_server.load_properties(file_path: str) Dict[str, str][source]

Read properties file into map.

ts.model_server.start() None[source]

This is the entry point for model server :return:

ts.model_service_worker module

ModelServiceWorker is the worker that is started by the MMS front-end. Communication message format: binary encoding

class ts.model_service_worker.TorchModelServiceWorker(s_type: Optional[str] = None, s_name: Optional[str] = None, host_addr: Optional[str] = None, port_num: Optional[int] = None, metrics_config: Optional[str] = None, async_comm: Optional[bool] = False)[source]

Bases: object

Backend worker to handle Model Server’s python service code

handle_connection(cl_socket)[source]

Handle socket connection.

Parameters:

cl_socket

Returns:

handle_connection_async(cl_socket)[source]

Handle socket connection.

Parameters:

cl_socket

Returns:

load_model(load_model_request)[source]

Expected command {

“command” : “load”, string “modelPath” : “/path/to/model/file”, string “modelName” : “name”, string “gpu” : None if CPU else gpu_id, int “handler” : service handler entry point if provided, string “envelope” : name of wrapper/unwrapper of request data if provided, string “batchSize” : batch size, int “limitMaxImagePixels”: limit pillow image max_image_pixels, bool

}

Parameters:

load_model_request

Returns:

run_server()[source]

Run the backend worker process and listen on a socket :return:

ts.service module

CustomService class definitions

class ts.service.Service(model_name, model_dir, manifest, entry_point, gpu, batch_size, limit_max_image_pixels=True, metrics_cache=None)[source]

Bases: object

Wrapper for custom entry_point

property context
predict(batch)[source]
PREDICT COMMAND = {

“command”: “predict”, “batch”: [ REQUEST_INPUT ]

} :param batch: list of request :return:

static retrieve_data_for_inference(batch)[source]
REQUEST_INPUT = {

“requestId” : “111-222-3333”, “parameters” : [ PARAMETER ]

}

PARAMETER = {

“name” : parameter name “contentType”: “http-content-types”, “value”: “val1”

}

Parameters:

batch

Returns:

set_cl_socket(cl_socket)[source]
ts.service.emit_metrics(metrics)[source]

Emit the metrics in the provided Dictionary

Parameters:
  • metrics (A dictionary of all) –

  • metrics

  • metric_name (when key is) –

  • object (value is a metric) –

ts.version module

This is the current version of TorchServe

Module contents

This module does the following: a. Starts model-server. b. Creates end-points based on the configured models. c. Exposes standard “ping” and “api-description” endpoints. d. Waits for servicing inference requests.

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources