stevenlix 1c5b15c2b8 Remove memory copy between TensorRT and CUDA (#1561) ... * remove memory copy between CUDA and TRT * add info to RegisterExecutionProvider input * use new IDeviceAllocator for trt allocator * remove SetDefaultInputsMemoryType from TRT EP * remove onnx-tensorrt 5.0 * add submodule onnx-tensorrt branch 5.1 * remove redundancy * Update transformer_memcpy.cc * Update tensorrt_execution_provider.cc * switch to TensorRT 5.1.5.0 * update python binding * disable failed test case on TensorRT * Update activation_op_test.cc * upgrade to TensorRT container 19.06 * update according to feedback * add comments * remove tensorrt allocator and use cuda(gpu) allocator * update onnx-tensorrt submodule * change ci build cuda directory name		2019-08-08 19:31:39 -07:00
..
common	Remove unneeded C APIs + some refactoring. (#1555)	2019-08-07 11:05:29 -07:00
framework	Remove memory copy between TensorRT and CUDA (#1561)	2019-08-08 19:31:39 -07:00
graph	Don't create implicit input for outer scope value if there is a subgraph input with the same name. (#1186)	2019-08-02 07:23:41 +10:00
optimizer	Add/correct missing SAL annotations + avoid using unsigned types (except where counts are involved). (#1451)	2019-07-22 23:25:53 -07:00
platform	Enable use of session based threadpool. (#854)	2019-04-18 10:20:46 -07:00
providers	Remove memory copy between TensorRT and CUDA (#1561)	2019-08-08 19:31:39 -07:00
session	Remove unneeded C APIs + some refactoring. (#1555)	2019-08-07 11:05:29 -07:00