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
Zhaolong Xing ae576f3c68
fix: when use the load model from memory mode, the RAM occupy is high (#17788)
6 years ago
..
anakin TRT: Support set dynamic range in int8 mode. (#17524) 6 years ago
analysis fix: when use the load model from memory mode, the RAM occupy is high (#17788) 6 years ago
api fix: when use the load model from memory mode, the RAM occupy is high (#17788) 6 years ago
tensorrt fix: when use the load model from memory mode, the RAM occupy is high (#17788) 6 years ago
tests fix: when use the load model from memory mode, the RAM occupy is high (#17788) 6 years ago
utils Merge branch 'develop' of https://github.com/paddlepaddle/paddle into HEAD 6 years ago
CMakeLists.txt Polish DGC code (#16818) 6 years ago
check_symbol.sh Cherry-pick benchmark related changes from release/1.4 (#17156) 6 years ago
engine.h add static model load for trt 6 years ago
io.cc load persistables with selected rows, test=develop (#17047) 6 years ago
io.h update with comments 7 years ago
paddle_fluid.map add shared library for analysis 7 years ago
paddle_fluid.sym