stevenlix f4a5d17294 Upgrade to CUDA10.2 for TensorRT (#3084) ... * Switch to CUDA10.2 * Update win-gpu-tensorrt-ci-pipeline.yml * Update win-gpu-tensorrt-ci-pipeline.yml * remove dynamic_shape * update onnx-tensorrt submodule * check if input shape is specified for TensorRT subgraph input and enable some TensorRT unit tests * fix format issue * add shape inference instruction for TensorRT * update according to the reviews * Update win-gpu-tensorrt-ci-pipeline.yml		2020-02-25 05:36:01 -08:00
..
codegen	Add SafeInt bounds checking to memory allocation size calculations. (#3022)	2020-02-20 11:41:03 -08:00
common	Add SafeInt bounds checking to memory allocation size calculations. (#3022)	2020-02-20 11:41:03 -08:00
dll	populate file metadata for onnxruntime.dll (#2978)	2020-02-07 11:00:28 -08:00
framework	Use a custom allocator for temporary buffers in reduction_ops.cc (#2775)	2020-02-23 16:04:30 +10:00
graph	Use CUDA 10.1 for Linux build (#3057)	2020-02-21 11:55:32 -08:00
language_interop_ops	Introduce PrimitiveType into a Type System along with an integer constant (#2307)	2019-11-08 17:47:06 -08:00
mlas	NCHWc ReorderOutput->Transpose(NHWC) fusion (#3035)	2020-02-18 10:23:48 -08:00
optimizer	GPT2 Gelu Fusion & Test (#3009)	2020-02-21 18:25:43 +08:00
platform	Remove USE_NSYNC macro (#3052)	2020-02-20 13:29:19 -08:00
protobuf
providers	Upgrade to CUDA10.2 for TensorRT (#3084)	2020-02-25 05:36:01 -08:00
session	No need to create a copy of graph proto when checking to see if there is fp16 input (#3061)	2020-02-24 15:14:29 -08:00
util	Optimize Math::Im2col + ConvInteger pointwise (#3017)	2020-02-14 14:25:47 -08:00