Weixing Zhang 299ace0759 Support to allow user to specify compute stream per session (#3723) ... * Support to allow user to specify compute stream per session Create computation cuda stream explicitly rather than use default legacy stream or per-thread default stream. remove some redudant cudaStreamSynchronize fix gpt2 model test failures don't use default stream in nccl either. add stream schronization in OnRunEnd() using cub::DeviceScan::InclusiveSum which can be called with stream specified. fix topK failure due to latest rebase fix tensorrt support user specified stream add user_stream support in tensorrt EP use same stream for both tensort and CUDA EP. fix ScatterND specify stream for adasum and p2p kernels. fix loop fix CApiTest.custom_op_handler fix CApiTest.varied_input_custom_op_handler change for cudaMemcpyFromSymbol improve provider options for user specified compute stream * add changes for ROCM EP * fix GatherGrad UT for ROCM EP * clean code and fix NonMaxSuppression * use default stream for ROCM now * fix CApiTest.custom_op_handler:OrtFormatCustomOpTests.ConvertOnnxModelToOrt * fix tensorrt ut: CApiTest.io_binding_cuda Co-authored-by: Weixing Zhang <wezhan@microsoft.com>		2021-02-05 15:48:18 -08:00
..
common	Rename MakeString and ParseString functions. (#6272)	2021-01-07 15:43:42 -08:00
framework	Support to allow user to specify compute stream per session (#3723)	2021-02-05 15:48:18 -08:00
graph	Let execution fall back to CPU EP if Compile of a partition on current EP fails (#6580)	2021-02-05 12:14:55 -08:00
optimizer	Expose recompute configs to the frontend (#5318)	2020-10-02 09:49:47 -07:00
platform	Cast Op performance fix. (#6509)	2021-02-04 14:52:37 -08:00
providers	[CoreML EP] Add CI for CoreML EP (macOS) and add coreml_flags for EP options (#6481)	2021-01-28 12:25:46 -08:00
session	Support to allow user to specify compute stream per session (#3723)	2021-02-05 15:48:18 -08:00