diff --git a/README_CN.md b/README_CN.md index c6490d4..3b56390 100644 --- a/README_CN.md +++ b/README_CN.md @@ -105,15 +105,15 @@ MindSpore Serving运行需要配置以下环境变量： ## 快速入门 -以一个简单的[Add网络示例](https://www.mindspore.cn/tutorial/inference/zh-CN/serving_example.html)，演示MindSpore Serving如何使用。 +以一个简单的[Add网络示例](https://www.mindspore.cn/tutorial/inference/zh-CN/master/serving_example.html)，演示MindSpore Serving如何使用。 ## 文档 ### 开发者教程 -- [基于gRPC接口访问MindSpore Serving服务](https://www.mindspore.cn/tutorial/inference/zh-CN/serving_grpc.html) -- [基于RESTful接口访问MindSpore Serving服务](https://www.mindspore.cn/tutorial/inference/zh-CN/serving_restful.html) -- [通过配置模型提供Servable](https://www.mindspore.cn/tutorial/inference/zh-CN/serving_model.html) +- [基于gRPC接口访问MindSpore Serving服务](https://www.mindspore.cn/tutorial/inference/zh-CN/master/serving_grpc.html) +- [基于RESTful接口访问MindSpore Serving服务](https://www.mindspore.cn/tutorial/inference/zh-CN/master/serving_restful.html) +- [通过配置模型提供Servable](https://www.mindspore.cn/tutorial/inference/zh-CN/master/serving_model.html) 有关安装指南、教程和API的更多详细信息，请参阅[用户文档](https://www.mindspore.cn/doc/api_python/zh-CN/master/index.html)。 diff --git a/mindspore_serving/ccsrc/common/servable.h b/mindspore_serving/ccsrc/common/servable.h index ffb6a50..6025879 100644 --- a/mindspore_serving/ccsrc/common/servable.h +++ b/mindspore_serving/ccsrc/common/servable.h @@ -83,7 +83,7 @@ struct RequestSpec { struct MS_API ServableMeta { std::string servable_name; std::string servable_file; // file name - ModelType model_format; // OM， MindIR + ModelType model_format; // OM, MindIR bool with_batch_dim = true; // whether there is batch dim in model's inputs/outputs size_t inputs_count = 0; size_t outputs_count = 0; diff --git a/mindspore_serving/client/python/client.py b/mindspore_serving/client/python/client.py index 6524ba7..1b0efc6 100644 --- a/mindspore_serving/client/python/client.py +++ b/mindspore_serving/client/python/client.py @@ -143,19 +143,17 @@ def _check_int(arg_name, int_val, mininum=None, maximum=None): class Client: """ The Client encapsulates the serving gRPC API, which can be used to create requests, - access serving, and parse results. + access serving, and parse results. Args: - ip(str): Serving ip. - port(int): Serving port. - servable_name(str): The name of servable supplied by Serving. - method_name(str): The name of method supplied by servable. - version_number(int): The version number of servable, default 0, - 0 meaning the maximum version number in all running versions. - max_msg_mb_size(int): The maximum acceptable gRPC message size in megabytes(MB), default 512, - value range [1, 512]. + ip (str): Serving ip. + port (int): Serving port. + servable_name (str): The name of servable supplied by Serving. + method_name (str): The name of method supplied by servable. + version_number (int): The version number of servable, default 0, + which means the maximum version number in all running versions. Raises: - RuntimeError: The type or value of the parameters is invalid, or other error happened. + RuntimeError: The type or value of the parameters is invalid, or other errors happened. Examples: >>> from mindspore_serving.client import Client @@ -169,13 +167,12 @@ class Client: >>> print(result) """ - def __init__(self, ip, port, servable_name, method_name, version_number=0, max_msg_mb_size=512): + def __init__(self, ip, port, servable_name, method_name, version_number=0): _check_str("ip", ip) - _check_int("port", port, 0, 65535) + _check_int("port", port, 1, 65535) _check_str("servable_name", servable_name) _check_str("method_name", method_name) _check_int("version_number", version_number, 0) - _check_int("max_msg_mb_size", max_msg_mb_size, 1, 512) self.ip = ip self.port = port @@ -184,7 +181,7 @@ class Client: self.version_number = version_number channel_str = str(ip) + ":" + str(port) - msg_bytes_size = max_msg_mb_size * 1024 * 1024 + msg_bytes_size = 512 * 1024 * 1024 # 512MB channel = grpc.insecure_channel(channel_str, options=[ ('grpc.max_send_message_length', msg_bytes_size), @@ -197,11 +194,11 @@ class Client: Used to create requests, access serving, and parse results. Args: - instances(map, tuple of map): Instance or tuple of instance, every instance item is the inputs map. + instances (map, tuple of map): Instance or tuple of instances, every instance item is the inputs map. The map key is the input name, and the value is the input value. Raises: - RuntimeError: The type or value of the parameters is invalid, or other error happened. + RuntimeError: The type or value of the parameters is invalid, or other errors happened. """ if not isinstance(instances, (tuple, list)): instances = (instances,) diff --git a/mindspore_serving/master/_master.py b/mindspore_serving/master/_master.py index f825575..f0a05e5 100644 --- a/mindspore_serving/master/_master.py +++ b/mindspore_serving/master/_master.py @@ -72,12 +72,12 @@ def start_grpc_server(ip="0.0.0.0", grpc_port=5500, max_msg_mb_size=100): Args: ip (str): gRPC server ip. - grpc_port (int): gRPC port ip, default 5500，ip port range [0, 65535]. + grpc_port (int): gRPC port ip, default 5500, ip port range [1, 65535]. max_msg_mb_size (int): The maximum acceptable gRPC message size in megabytes(MB), default 100, value range [1, 512]. Raises: - RuntimeError: Start gRPC server failed. + RuntimeError: Fail to start the gRPC server. Examples: >>> from mindspore_serving import master @@ -96,17 +96,17 @@ def start_grpc_server(ip="0.0.0.0", grpc_port=5500, max_msg_mb_size=100): @stop_on_except def start_master_server(ip="127.0.0.1", master_port=6100): r""" - Start gRPC server for the commication between workers and the master. + Start the gRPC server for the communication between workers and the master. Note: The ip is expected to be accessed only by workers, not clients. Args: - ip (str): gRPC ip for worker to commnicate with, default '127.0.0.1'. - master_port (int): gRPC port ip, default 6100，ip port range [0, 65535]. + ip (str): gRPC ip for workers to communicate with, default '127.0.0.1'. + master_port (int): gRPC port ip, default 6100, ip port range [1, 65535]. Raises: - RuntimeError: Start gRPC server failed. + RuntimeError: Fail to start the master server. Examples: >>> from mindspore_serving import master @@ -129,12 +129,12 @@ def start_restful_server(ip="0.0.0.0", restful_port=5900, max_msg_mb_size=100): Args: ip (str): RESTful server ip. - restful_port (int): gRPC port ip, default 5900，ip port range [0, 65535]. + restful_port (int): gRPC port ip, default 5900, ip port range [1, 65535]. max_msg_mb_size (int): The maximum acceptable RESTful message size in megabytes(MB), default 100, value range [1, 512]. Raises: - RuntimeError: Start RESTful server failed. + RuntimeError: Fail to start the RESTful server. Examples: >>> from mindspore_serving import master diff --git a/mindspore_serving/worker/_worker.py b/mindspore_serving/worker/_worker.py index 25f5c82..d5b4133 100644 --- a/mindspore_serving/worker/_worker.py +++ b/mindspore_serving/worker/_worker.py @@ -98,22 +98,22 @@ def start_servable(servable_directory, servable_name, version_number=0, Serving has two running modes. One is running in a single process, providing the Serving service of a single model. The other includes a master and multiple workers. This interface is for the second scenario. - The master is responsible for providing the Serving access interface for client, - while the worker is responsible for providing the inference service of the specific model. The master - and worker communicate through gPRC defined as (master_ip, master_port) and (worker_ip, worker_port). + The master is responsible for providing the Serving access interface for clients, + while the worker is responsible for providing the inference service of the specific model. The communications + between the master and workers through gPRC are defined as (master_ip, master_port) and (worker_ip, worker_port). Args: - servable_directory (str): The directory where the servable located in, there expected to has a directory named - `servable_name`. For more detail: - `How to config Servable `_ + servable_directory (str): The directory where the servable is located in. There expects to has a directory + named `servable_name`. For more detail: + `How to config Servable `_ . servable_name (str): The servable name. - version_number (int): Servable version number to be loaded. Version number should be a positive integer, - started from 1, and 0 means to load the latest version. Default: 0. - device_type (str): Current only support "Ascend", "Davinci" and None, Default: None. - "Ascend" which means device type can be Ascend910 or Ascend310, etc. - "Davinci" has the same meanings of "Ascend". - None: The device type is determined by the mindspore environment. + version_number (int): Servable version number to be loaded. The version number should be a positive integer, + starting from 1, and 0 means to load the latest version. Default: 0. + device_type (str): Currently only supports "Ascend", "Davinci" and None, Default: None. + "Ascend" means the device type can be Ascend910 or Ascend310, etc. + "Davinci" has the same meaning as "Ascend". + None means the device type is determined by the MindSpore environment. device_id (int): The id of the device the model loads into and runs in. master_ip (str): The master ip the worker linked to. master_port (int): The master port the worker linked to. @@ -161,24 +161,24 @@ def start_servable(servable_directory, servable_name, version_number=0, def start_servable_in_master(servable_directory, servable_name, version_number=0, device_type=None, device_id=0): r""" - Start up the servable named 'servable_name' defined in 'svable_directory', and the worker will running in + Start up the servable named 'servable_name' defined in 'svable_directory', and the worker will run in the process of the master. Serving has two running modes. One is running in a single process, providing the Serving service of a single model. The other includes a master and multiple workers. This interface is for the first scenario. Args: - servable_directory (str): The directory where the servable located in, there expected to has a directory named - `servable_name`. For more detail: - `How to config Servable `_ + servable_directory (str): The directory where the servable is located in. There expects to has a directory named + `servable_name`. For more detail: + `How to config Servable `_ . servable_name (str): The servable name. - version_number (int): Servable version number to be loaded. Version number should be a positive integer, - started from 1, and 0 means to load the latest version. Default: 0. - device_type (str): Current only support "Ascend", "Davinci" and None, Default: None. - "Ascend" which means device type can be Ascend910 or Ascend310, etc. - "Davinci" has the same meanings of "Ascend". - None: The device type is determined by the mindspore environment. + version_number (int): Servable version number to be loaded. The version number should be a positive integer, + starting from 1, and 0 means to load the latest version. Default: 0. + device_type (str): Currently only supports "Ascend", "Davinci" and None, Default: None. + "Ascend" means the device type can be Ascend910 or Ascend310, etc. + "Davinci" has the same meaning as "Ascend". + None means the device type is determined by the MindSpore environment. Examples: >>> import os diff --git a/mindspore_serving/worker/register/method.py b/mindspore_serving/worker/register/method.py index 8775eed..01d9cb7 100644 --- a/mindspore_serving/worker/register/method.py +++ b/mindspore_serving/worker/register/method.py @@ -368,7 +368,7 @@ def register_method(output_names): Preprocess and postprocess are optional. Args: - output_names(str, tuple or list of str): The output names of method. The input names is + output_names (str, tuple or list of str): The output names of method. The input names is the args names of the registered function. Raises: