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
Zhaolong Xing 133f1fc123
[Eernie TRT]: add slice op and add emb eltwise layernorm fp16 support (#23723)
5 years ago
..
demo_ci Remove: NGraph engine from PDPD repository (#23545) 5 years ago
details [Fix BUG]: Core when multi thread + clone + paddle-trt (#22442) 5 years ago
CMakeLists.txt Remove: NGraph engine from PDPD repository (#23545) 5 years ago
README.md Combine Inference Analysis with IR (#13914) 6 years ago
analysis_config.cc Remove: NGraph engine from PDPD repository (#23545) 5 years ago
analysis_predictor.cc [Eernie TRT]: add slice op and add emb eltwise layernorm fp16 support (#23723) 5 years ago
analysis_predictor.h Add some inference API comments for AnalysisPredictor (#23242) 5 years ago
analysis_predictor_tester.cc INT8 Fully-connected (#17641) 5 years ago
api.cc Golang inference API (#22503) 5 years ago
api_impl.cc Support LoDTensorArray in fetch (#23645) 5 years ago
api_impl.h make clone thread safe (#15363) 6 years ago
api_impl_tester.cc Support LoDTensorArray in fetch (#23645) 5 years ago
api_tester.cc add version support (#15469) 6 years ago
helper.cc rollback paddle_inference_helper.h to helper.h 6 years ago
helper.h add check for assigned data, test=develop (#22960) 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 INT8 Fully-connected (#17641) 5 years ago
mkldnn_quantizer.h INT8 Fully-connected (#17641) 5 years ago
mkldnn_quantizer_config.cc Add support for INT8 matmul in C-API quantization (#23463) 5 years ago
paddle_analysis_config.h Remove: NGraph engine from PDPD repository (#23545) 5 years ago
paddle_api.h refine the doc of paddle_api.h, test=develop (#23402) 5 years ago
paddle_inference_api.h remove anakin from code, test=develop (#22420) 5 years ago
paddle_mkldnn_quantizer_config.h Add some inference API comments for AnalysisPredictor (#23242) 5 years ago
paddle_pass_builder.cc Add scale-matmul fuse pass (#23734) 5 years ago
paddle_pass_builder.h Add three passes and api reference of paddle_pass_builder. test=develop (#23741) 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.