Tang, Cheng 8f34c8c8ed Introduce collective ops to ort inference build (#14399) ... ### Description Introduce collective ops into onnxruntime inference build, including 1) AllReduce and AllGather schema in contrib op, controlled by USE_MPI flag 2) AllReduce and AllGather kernel in cuda EP, controlled by ORT_USE_NCCL flag ### Motivation and Context Enable the collective ops in onnxruntime inference build so we have the ability to run distributed inference with multiple GPUs. The original ncclAllReduce ops in training build require quite complex configurations, which is not suitable for inference case, and it already broken. so we introduce a new implementation. --------- Co-authored-by: Cheng Tang <chenta@microsoft.com@orttrainingdev9.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>		2023-02-07 13:47:48 -08:00
..
nodejs/templates
nuget/templates
templates	Revert mimalloc from v2.0.9 to v2.0.3 (#14603)	2023-02-07 09:58:25 -08:00
android-x86_64-crosscompile-ci-pipeline.yml	Free OrtStatus in ASSERT_ORT_STATUS_OK, make run_android_emulator.py work with newer JDK version (#14369)	2023-01-20 09:27:47 -08:00
anybuild.yml
binary-size-checks-pipeline.yml
build-perf-test-binaries-pipeline.yml
c-api-noopenmp-packaging-pipelines.yml	Update package pipelines to support TRT 8.5 (#13998)	2022-12-16 15:01:50 -08:00
clean-build-docker-image-cache-pipeline.yml
linux-ci-pipeline.yml	Use today's cache only (#14120)	2023-01-04 17:48:52 +08:00
linux-cpu-aten-pipeline.yml	Add Cache in Linux CPU Aten Pipeline (#14313)	2023-01-17 10:49:29 +08:00
linux-cpu-eager-pipeline.yml
linux-cpu-minimal-build-ci-pipeline.yml
linux-dnnl-ci-pipeline.yml
linux-gpu-ci-pipeline.yml	Add compilation cache for Linux GPU (#13995)	2022-12-16 16:38:12 +08:00
linux-gpu-tensorrt-ci-pipeline.yml	[TensorRT EP] support TensorRT 8.5 (#13867)	2022-12-14 13:06:03 -08:00
linux-gpu-tensorrt-daily-perf-pipeline.yml	Update package pipelines to support TRT 8.5 (#13998)	2022-12-16 15:01:50 -08:00
linux-gpu-tensorrt-packaging-pipeline.yml	[TensorRT EP] support TensorRT 8.5 (#13867)	2022-12-14 13:06:03 -08:00
linux-migraphx-ci-pipeline.yml	[ROCm] Update ROCm and MigraphX CI to ROCm5.4 (#14011)	2022-12-22 10:01:05 +08:00
linux-multi-gpu-ci-pipeline.yml
linux-multi-gpu-tensorrt-ci-pipeline.yml
linux-openvino-ci-pipeline.yml	Openvino ep 2022.3 v4.3 (#14210)	2023-01-11 16:31:26 -08:00
linux-openvino-nightly-pipeline.yml
mac-ci-pipeline.yml	make WITHCACHE as an option in MacOS workflow (#14188)	2023-01-10 10:54:19 +08:00
mac-coreml-ci-pipeline.yml
mac-ios-ci-pipeline.yml	Add ability to register custom ops by specifying a function name (#14177)	2023-01-12 15:11:34 +10:00
mac-ios-packaging-pipeline.yml
mac-objc-static-analysis-ci-pipeline.yml
mac-react-native-ci-pipeline.yml
npm-packaging-pipeline.yml
orttraining-linux-ci-pipeline.yml	increase the time limit as more unit tests added (#14327)	2023-01-18 15:51:21 -08:00
orttraining-linux-external-custom-ops.yml
orttraining-linux-gpu-amd-e2e-test-ci-pipeline.yml
orttraining-linux-gpu-ci-pipeline.yml	Update torch to 1.13.1 in CI and packaging pipelines for ort training (#14055)	2023-01-03 20:03:33 -08:00
orttraining-linux-gpu-distributed-e2e-test-pipeline.yml
orttraining-linux-gpu-docker-release-pipeline.yml
orttraining-linux-gpu-ortmodule-distributed-test-ci-pipeline.yml	Introduce collective ops to ort inference build (#14399)	2023-02-07 13:47:48 -08:00
orttraining-linux-gpu-ortmodule-test-clear-cache-pipeline.yml
orttraining-linux-gpu-training-apis.yml	Refactor training build options (#13964)	2023-01-03 13:28:16 -08:00
orttraining-linux-nightly-ortmodule-test-pipeline.yml	Fix onnxruntime-CI-nightly-ort-pipeline Failure (#14464)	2023-01-28 16:05:56 +08:00
orttraining-mac-ci-pipeline.yml
orttraining-pai-ci-pipeline.yml	Enable ccache for HIP objects (#14465)	2023-01-28 22:34:24 +08:00
orttraining-py-packaging-pipeline-cpu.yml	Add support for python 3.10 for onnxruntime-training cuda and cpu (#14100)	2023-02-02 11:32:41 -08:00
orttraining-py-packaging-pipeline-cuda116.yml	Create dedicated build for training api (#14136)	2023-01-10 20:58:04 -08:00
orttraining-py-packaging-pipeline-rocm.yml	[ROCm] Add ROCm5.4 to python package pipeline (#14012)	2022-12-22 10:01:40 +08:00
post-merge-jobs.yml	Android package custom build script update (#14403)	2023-01-25 09:19:05 -08:00
py-package-build-pipeline.yml
py-package-test-pipeline.yml
py-packaging-pipeline.yml	CloudEP (#13855)	2023-01-03 10:03:15 -08:00
python-checks-ci-pipeline.yml
sign_ov_ep_binaries.yml
snpe-ep-nuget-packaging-pipeline.yml
web-ci-pipeline.yml
web-packaging-pipeline.yml
win-ci-fuzz-testing.yml
win-ci-pipeline.yml	Remove intermedia obj files once build finished (#14361)	2023-01-20 13:37:15 +08:00
win-eager-ci-pipeline.yml
win-gpu-ci-pipeline.yml	Enable cache for msbuild (#14085)	2023-01-06 11:19:57 +08:00
win-gpu-reduce-op-ci-pipeline.yml
win-gpu-tensorrt-ci-pipeline.yml	[TensorRT EP] support TensorRT 8.5 (#13867)	2022-12-14 13:06:03 -08:00