登录
注册
开源
企业版
高校版
搜索
帮助中心
使用条款
关于我们
开源
企业版
高校版
私有云
模力方舟
AI 队友
登录
注册
Gitee 2025年度个人数据报告已发布,快来看看你的成长👉
代码拉取完成,页面将自动刷新
仓库状态说明
开源项目
>
人工智能
>
AI-人工智能
&&
捐赠
捐赠前请先登录
取消
前往登录
扫描微信二维码支付
取消
支付完成
支付提示
将跳转至支付宝完成支付
确定
取消
Watch
不关注
关注所有动态
仅关注版本发行动态
关注但不提醒动态
123
Star
704
Fork
50
MindSpore
/
serving
暂停
代码
Issues
40
Pull Requests
0
Wiki
统计
流水线
服务
质量分析
Jenkins for Gitee
腾讯云托管
腾讯云 Serverless
悬镜安全
阿里云 SAE
Codeblitz
SBOM
我知道了,不再自动展开
发行版
最新版
v1.8.0
38a9a86
2022-08-03 09:23
对比
MindSpore Serving 1.8.0 Release Notes
徐永飞
### Major Features and Improvements - [STABLE] When deploying a large-scale model with parallel pipeline, Serving supports parallel pipeline processing of multiple inference instances.
最后提交信息为:
!464
Modify the release note files
v1.7.0
9be5921
2022-04-20 14:18
对比
MindSpore Serving 1.7.0 Release Notes
徐永飞
### Major Features and Improvements - [DEMO] Ascend 710 can be used as the inference device, for more detail see [MindSpore Serving backend](https://www.mindspore.cn/serving/docs/en/master/serving_install.html#installation). - [DEMO] Support models of MindIR format when MindSpore Lite is used as the MindSpore Serving inference backend, for more detail see [MindSpore Serving backend](https://www.mindspore.cn/serving/docs/en/master/serving_install.html#installation). #### Deprecations ##### Python API - `AclOptions` and `GpuOptions` are removed from version 1.7.0, and use `AscendDeviceInfo` and `GPUDeviceInfo` instead. - `register.declare_sevable` and `register.call_servable` are removed from version 1.7.0, and use `register.declare_model` and `register.add_stage` instead. - `register.call_preprocess`, `register.call_preprocess_pipeline`, `register.call_postprocess` and `register.call_postprocess_pipeline` are removed from version 1.7.0, and use `register.add_stage` instead.
最后提交信息为:
!432
Serving, fix deadlock when backend is Ascend310/710
v1.6.0
1a8b539
2022-01-21 09:39
对比
MindSpore Serving 1.6.0 Release Notes
徐永飞
### Major Features and Improvements - [STABLE] We can use existing interfaces(`decalre_model` and `add_stage`) that define single-model services to define multi-model composite services. - [STABLE] When the number of occupied devices is fixed, additional worker processes(using parameter `num_parallel_workers`) are supported to accelerate Python functions such as preprocessing and postprocessing, improving device utilization. - [STABLE] The interface `Model.call` is a stable feature, and can be used to define complex model invocation processes in the Serving server, such as looping and conditional branching. - [STABLE] The new interfaces `Context`, `CPUDeviceInfo`, `GPUDeviceInfo`, `AscendDeviceInfo` are provided to set user-defined device information. The original interfaces `GpuOptions` and `AclOptions` are deprecated. - [BETA] We support MindSpore Lite as the MindSpore Serving inference backend, for more detail see [MindSpore Serving backend](https://www.mindspore.cn/serving/docs/en/master/serving_install.html#installation).
最后提交信息为:
!416
Serving, fix LD_LIBRARY_PATH
v1.5.0
7f5f345
2021-10-25 15:45
对比
MindSpore 1.5.0 Release Notes
徐永飞
### Major Features and Improvements - [STABLE] To support multi-model orchestration (to be released in version 1.6), a set of APIs (`decalre_model` and `add_stage`) is added. The new APIs will be used in single-model and multi-model scenarios. The old APIs(`register.declare_servable`,`call_servable`,`call_preprocess`,`call_postprocess`) used in single-model scenarios are deprecated. - [BETA] When the number of occupied devices is fixed, additional worker processes are supported to accelerate Python functions such as preprocessing and postprocessing, improving device utilization. - [BETA]`Model.call` interface is added to support invoking models in Python functions. ### API Change #### API Incompatible Change ##### Python API ###### New set of APIs for single-model and multi-model scenarios To support multiple models(will be officially released in version 1.6), a set of APIs (`decalre_model` and `add_stage`) is added. The single-model and multi-model scenarios will use the same set of APIs. New APIs are recommended in single-model scenarios. Old APIs (`declare_servable`,`call_servable`,`call_preprocess`, `call_postprocess`) are deprecated. <table> <tr> <td style="text-align:center"> 1.4 </td> <td style="text-align:center"> 1.5 </td> </tr> <tr> <td> ```python from mindspore_serving.server import register register.declare_servable(servable_file="resnet.mindir", model_format="MindIR") def resnet_preprocess(image): .... def resnet_postprocess(scores): .... @register.register_method(output_names=["label"]) def predict(image): x = register.call_preprocess(resnet_preprocess, image) x = register.call_servable(x) x = register.call_postprocess(resnet_postprocess, x) return x ``` </td> <td> ```python from mindspore_serving.server import register resnet_model = register.declare_model(model_file="resnet.mindir", model_format="MindIR") def resnet_preprocess(image): .... def resnet_postprocess(scores): .... @register.register_method(output_names=["label"]) def predict(image): x = register.add_stage(resnet_preprocess, image, outputs_count=1) x = register.add_stage(resnet_model, x, outputs_count=1) x = register.add_stage(resnet_postprocess, x, outputs_count=1) return x ``` </td> </tr> </table> #### New features ##### Python API ###### Additional worker processes are supported to accelerate Python functions(preprocessing and postprocessing) Parameter `num_parallel_workers` is added to class `ServableStartConfig` to configure the total number of workers. The number of workers occupying devices is determined by the length of parameter `device_ids`. Additional worker processes use worker processes that occupy devices for model inference. ```python class ServableStartConfig: def __init__(self, servable_directory, servable_name, device_ids, version_number=0, device_type=None, num_parallel_workers=0, dec_key=None, dec_mode='AES-GCM') ``` Start the serving server that contains the `resnet50` servable. The `resnet50` servable has four worker processes(`num_parallel_workers`), one of which occupies the device(`device_ids`). ```python import os import sys from mindspore_serving import server def start(): servable_dir = os.path.dirname(os.path.realpath(sys.argv[0])) # Total 4 worker, one worker occupy device 0, the model inference tasks of other workers are forwarded to the worker # that occupies the device. config = server.ServableStartConfig(servable_directory=servable_dir, servable_name="resnet50", device_ids=0, num_parallel_workers=4) server.start_servables(config) server.start_grpc_server("127.0.0.1:5500") server.start_restful_server("127.0.0.1:1500") if __name__ == "__main__": start() ``` ###### Model.call interface is added to support invoking models in Python functions ```python from mindspore_serving.server import register add_model = register.declare_model(model_file="tensor_add.mindir", model_format="MindIR") def add_func(x1, x2, x3, x4): instances = [] instances.append((x1, x2)) instances.append((x3, x4)) output_instances = add_model.call(instances) # for multi instances y1 = output_instances[0][0] # instance 0 output 0 y2 = output_instances[1][0] # instance 1 output 0 y = add_model.call(y1, y2) # for single instance return y @register.register_method(output_names=["y"]) def predict(x1, x2, x3, x4): y = register.add_stage(add_func, x1, x2, x3, x4, outputs_count=1) return y ``` #### Deprecations ##### Python API - `register.declare_servable`,`call_servable`,`call_preprocess`,`call_postprocess`,`call_preprocess_pipeline` and`call_postprocess_pipeline` are now deprecated in favor of`register.declare_model` and`add_stage`, as shown above. Deprecated interfaces will be deleted in the future. - Beta interfaces`PipelineServable` and`register_pipeline` introduced in version 1.3 will be deleted and replaced with`Model.call`. ### Contributors Thanks goes to these wonderful people: chenweifeng, qinzheng, xuyongfei, zhangyinxia, zhoufeng. Contributions of any kind are welcome!
最后提交信息为:
!368
Serving, update mindspore commit
v1.4.0
745d474
2021-08-05 20:06
对比
MindSpore Serving 1.4.0 Release Notes
徐永飞
### Major Features and Improvements - This release is based on MindSpore version 1.4.0
最后提交信息为:
!325
Serving, udpate version to 1.4
v1.3.0
3fb0503
2021-07-14 12:02
对比
MindSpore 1.3.0 Release Notes
徐永飞
### Major Features and Improvements - [STABLE] Enhances and simplifies the deployment and startup of single-chip models. Multiple models can be loaded by a single script. Each model can have multiple copies on multiple chips. Requests can be split and distributed to these copies for concurrent execution. - [STABLE] The `master`+`worker` interface of the Serving server is changed to the `server` interface. - [STABLE] The client and server support Unix Domain Socket-based gRPC communication. - [STABLE] gRPC and RESTful interfaces support TLS/SSL security authentication. - [STABLE] The MindIR encryption model is supported. - [BETA] Incremental inference models consisting of multiple static graphs are supported, including single-card models and distributed models.
最后提交信息为:
!319
Serving, update mindspore commit
v1.2.0
4b6d49f
2021-04-17 16:30
对比
MindSpore Serving 1.2.0 Release Notes
徐永飞
### Major Features and Improvements - [STABLE] Support distributed inference, it needs to cooperate with distributed training to export distributed models for super-large-scale neural network parameters(Ascend 910). - [STABLE] Support GPU platform, Serving worker nodes can be deployer on Nvidia GPU, Ascend 310 and Ascend 910. - This release is based on MindSpore version 1.2.0 - Support Python 3.8 and 3.9. ### API Change #### API Incompatible Change ##### Python API Support deployment of distributed model, refer to [distributed inference tutorial](https://www.mindspore.cn/tutorial/inference/en/r1.2/serving_distributed_example.html) for related API. #### Deprecations ##### Python API ### Bug Fixes ## Contributors Thanks goes to these wonderful people: chenweifeng, qinzheng, xujincai, xuyongfei, zhangyinxia, zhoufeng. Contributions of any kind are welcome!
最后提交信息为:
!231
update mindspore submodule in branch r1.2
v1.1.1
daa15b2
2021-01-30 19:25
对比
MindSpore Serving 1.1.1 Release Notes
徐永飞
## Major Features and Improvements * Adapts new C++ inference interface for MindSpore version 1.1.1. ## Bug fixes * [BUGFIX] Fix bug in transforming result of type int16 in python Client. * [BUGFIX] Fix bytes type misidentified as str type after python preprocess and postprocess. * [BUGFIX] Fix bug releasing C++ tensor data when it's wrapped as numpy object sometimes. * [BUGFIX] Update RuntimeError to warning log when check Ascend environment failed.
最后提交信息为:
!118
Serving, update spelling
v1.1.0
484415b
2020-12-31 18:03
对比
Release 1.1.0
徐永飞
## Major Features and Improvements ### Ascend 310 & Ascend 910 Serving Framework * Support gRPC and RESTful API. * Support simple Python API for Client and Server. * Support Model configuration,User can customize preprocessing & postprocessing for model. * Support multiple models,Multiple models can run simultaneously. * Support Model batching,Multiple instances will be split and combined to meet the batch size requirements of the model.
最后提交信息为:
!89
Serving, update RELEASE note && mindspore
下载
请输入验证码,防止盗链导致资源被占用
取消
下载
C++
1
https://gitee.com/mindspore/serving.git
git@gitee.com:mindspore/serving.git
mindspore
serving
serving
点此查找更多帮助
搜索帮助
Git 命令在线学习
如何在 Gitee 导入 GitHub 仓库
Git 仓库基础操作
企业版和社区版功能对比
SSH 公钥设置
如何处理代码冲突
仓库体积过大,如何减小?
如何找回被删除的仓库数据
Gitee 产品配额说明
GitHub仓库快速导入Gitee及同步更新
什么是 Release(发行版)
将 PHP 项目自动发布到 packagist.org
仓库举报
回到顶部
登录提示
该操作需登录 Gitee 帐号,请先登录后再操作。
立即登录
没有帐号,去注册