Skip to content

S
Serving

PaddlePaddle / Serving
1 年多 前同步成功

通知 186
Star 833
Fork 253
S
Serving
切换分支/标签
历史 查找文件
云IDE
克隆
D
Dong Daxiang 推送
Merge pull request #475 from guru4elephant/inference_to_serving e7b6be6b
1864次提交
名称 最后提交 最后更新
..
deprecated move DOCKER.md to deprecated
4v100_bert_as_service_benchmark.png add doc
ABTEST_IN_PADDLE_SERVING.md Merge pull request #422 from wangjiawei04/doc_night
ABTEST_IN_PADDLE_SERVING_CN.md add desc of pip mirror source && fix docker images tag
BENCHMARKING.md move benchmarking
BERT_10_MINS.md Update BERT_10_MINS.md
BERT_10_MINS_CN.md move docs
COMPILE.md update doc
COMPILE_CN.md update doc
CONTRIBUTE.md add cpplint and pylint into CONTRIBUTE doc
CUBE_LOCAL.md Update CUBE_LOCAL.md
CUBE_LOCAL_CN.md Update CUBE_LOCAL_CN.md
CUBE_QUANT.md fix pre-commit test=serving
CUBE_QUANT_CN.md fix pre-commit test=serving
DESIGN.md refine design
DESIGN_CN.md Update DESIGN_CN.md
DESIGN_DOC.md Update DESIGN_DOC.md
DESIGN_DOC_CN.md Update DESIGN_DOC_CN.md
GPU_BENCHMARKING.md Add model name in GPU_BENCHMARKING.md
HOT_LOADING_IN_SERVING.md fix doc
HOT_LOADING_IN_SERVING_CN.md fix doc
IMDB_GO_CLIENT.md refine IMDB_GO_CLIENT document
IMDB_GO_CLIENT_CN.md Merge pull request #404 from barrierye/doc-fix
INFERNCE_TO_SERVING.md add doc
INFERNCE_TO_SERVING_CN.md add doc
MODEL_ENSEMBLE_IN_PADDLE_SERVING.md
MODEL_ENSEMBLE_IN_PADDLE_SERVING_CN.md
MULTI_SERVICE_ON_ONE_GPU_CN.md
Makefile
NEW_OPERATOR.md
NEW_OPERATOR_CN.md
PERFORMANCE_OPTIM_CN.md
README.md
README_CN.md
RUN_IN_DOCKER.md
RUN_IN_DOCKER_CN.md
SAVE.md
SAVE_CN.md
SERVER_DAG.md
SERVER_DAG_CN.md
TRAIN_TO_SERVICE.md
TRAIN_TO_SERVICE_CN.md
UWSGI_DEPLOY.md
abtest.png
architecture.png
bert-benchmark-batch-size-1.png
blank.png
client-side-proxy.png
client_inferface.png
coding_mode.png
complex_dag.png
criteo-cube-benchmark-avgcost.png
criteo-cube-benchmark-qps.png
cube-cli.png
cube.png
cube_eng.png
demo.gif
design_doc.png
doc_test_list
framework.png
gpu-local-qps-batchsize.png
gpu-local-qps-concurrency.png
gpu-local-time-batchsize.png
gpu-local-time-concurrency.png
gpu-serving-multi-card-multi-concurrency-qps-batchsize-concurrency-client1.png
gpu-serving-multi-card-multi-concurrency-qps-batchsize-concurrency-client2.png
gpu-serving-multi-card-multi-concurrency-time-batchsize-concurrency-client1.png
gpu-serving-multi-card-multi-concurrency-time-batchsize-concurrency-client2.png
gpu-serving-multi-card-single-concurrency-qps-batchsize-client1.png
gpu-serving-multi-card-single-concurrency-qps-batchsize-client2.png
gpu-serving-multi-card-single-concurrency-time-batchsize-client1.png
gpu-serving-multi-card-single-concurrency-time-batchsize-client2.png
gpu-serving-single-card-qps-batchsize.png
gpu-serving-single-card-qps-concurrency.png
gpu-serving-single-card-time-batchsize.png
gpu-serving-single-card-time-concurrency.png
imdb-benchmark-server-16.png
imdb_loss.png
index.rst
markdown2rst.py
model_ensemble_example.png
multi-service.png
multi-variants.png
predict-service.png
pruned-ctr-network.png
qps-threads-bow.png
qps-threads-cnn.png
qps-threads-lstm.png
requirements.txt
server-side.png
server_dag.png
server_interface.png
serving-timings.png
simple_dag.png
timeline-example.png
user_groups.png

项目简介

A flexible, high-performance carrier for machine learning models（『飞桨』服务化部署框架）

:rocket: Github 镜像仓库 :rocket:

源项目地址 :arrow_down: :arrow_down: :arrow_down:

https://github.com/PaddlePaddle/Serving

dagdeep-learningdockergpumicro-servicemicroservice-toolkitonline-servicepaddlepaddle-servingpipelinepredictionpredictorpythonrpc-serviceserving

发行版本 14

Release v0.9.0

全部发行版

贡献者 36

T S W H T H F B L B Z B
全部贡献者

开发语言

  • C++ 51.6 %
  • Python 27.0 %
  • Shell 8.0 %
  • CMake 6.0 %
  • Go 4.4 %
新手
引导 客服 返回
顶部