You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Paddle/paddle/fluid/inference/api
Shang Zhizhou ea851796e5
TensorRT中ernie模型推理性能优化,支持变长输入 (#28367)
5 years ago
..
demo_ci Modify the shell script according to the specification (#28302) 5 years ago
details use iwyu clean include (#27267) 5 years ago
CMakeLists.txt [UT] fix run type of ut test cases of test_train_recognize_digits and test_api_impl, test=develop (#27218) 5 years ago
README.md Combine Inference Analysis with IR (#13914) 7 years ago
analysis_config.cc TensorRT中ernie模型推理性能优化,支持变长输入 (#28367) 5 years ago
analysis_predictor.cc TensorRT中ernie模型推理性能优化,支持变长输入 (#28367) 5 years ago
analysis_predictor.h save operator version infomation to program desc, test=develop (#27668) 5 years ago
analysis_predictor_tester.cc Restore "Add mkldnn bfloat16 option to C-API " (#26882) 5 years ago
api.cc Enhance infer error info message (#26731) 5 years ago
api_impl.cc update for 2.0 inference api. (#27473) 5 years ago
api_impl.h use iwyu clean include (#27267) 5 years ago
api_impl_tester.cc Replace all errors thrown by LOG(FATAL) with PADDLE_THROW (#24759) 5 years ago
api_tester.cc test=develop, add log message in the function UpdateDllFlag (#24937) 5 years ago
helper.cc rollback paddle_inference_helper.h to helper.h 7 years ago
helper.h use iwyu clean include (#27267) 5 years ago
high_level_api.md remove anakin from code, test=develop (#22420) 5 years ago
high_level_api_cn.md remove anakin from code, test=develop (#22420) 5 years ago
mkldnn_quantizer.cc Enhance infer error info message (#26731) 5 years ago
mkldnn_quantizer.h INT8 Fully-connected (#17641) 6 years ago
mkldnn_quantizer_config.cc use iwyu clean include (#27267) 5 years ago
paddle_analysis_config.h TensorRT中ernie模型推理性能优化,支持变长输入 (#28367) 5 years ago
paddle_api.h refine paddle inference api (#26774) 5 years ago
paddle_infer_declare.h fix bug MD of compile, And add MD/STATIC/OPENBLAS inference lib check on windows (#27051) 5 years ago
paddle_inference_api.h Add 2.0 inference api doc. (#27125) 5 years ago
paddle_mkldnn_quantizer_config.h support C++ inference shared library on windows (#24672) 5 years ago
paddle_pass_builder.cc oneDNN BatchNorm + Act fusion pass. (#27912) 5 years ago
paddle_pass_builder.h use iwyu clean include (#27267) 5 years ago

README.md

Embed Paddle Inference in Your Application

Paddle inference offers the APIs in C and C++ languages.

You can easily deploy a model trained by Paddle following the steps as below:

  1. Optimize the native model;
  2. Write some codes for deployment.

The APIs

All the released APIs are located in the paddle_inference_api.h header file. The stable APIs are wrapped by namespace paddle, the unstable APIs are protected by namespace paddle::contrib.

Write some codes

Read paddle_inference_api.h for more information.