saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-22 22:01:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
5687 commits 2856 branches 57 tags 1.3 GiB
Commit graph

717 commits

Author SHA1 Message Date
Yulong Wang
5b65f1cb44
fixes SDL Native Rules warning in Node.js binding CI (#9402) 2021-10-18 13:05:46 -07:00
Changming Sun
6ecb990fae Update win-ci-pipeline.yml 2021-10-18 10:43:19 -07:00
Abhishek Jindal
87e726d1a0
Abjindal/merge eager with external custom ops (#8986) 
* switching to pytorch nightly build

* adding eager mode

* enable pybind and remove install step

* removing auditwheel repair process

* installing package

* adding auditwheel back

* disabling auditwheel repair for eager mode

* typo correction
 2021-10-14 13:19:45 -07:00
Suffian Khan
70cf61fa84
disable bart-l for now (#9305) 2021-10-07 16:55:54 -07:00
Changming Sun
4f4875b0e8 Add "workspace: clean: all" to anybuild build yaml file 2021-10-06 22:49:37 -07:00
Suffian Khan
510b58c877
Increase AMD CI pipeline timeout to 120 min (#9280) 
* increase timeout

* add timeout

* add timeout

* rename
 2021-10-06 10:43:09 -07:00
Changming Sun
334980e016 Delete nocontribops pipelines 2021-10-06 10:30:32 -07:00
Sheil Kumar
8f6fd014e4
Force Windows AI NuGet pipeline to use Windows SDK 19041 (#9255) 
* Force Windows AI Nuget pipeline to use 19041 Windows SDK as 22000 casues a downlevel regression by importing LoadLibraryW

* move into quotes

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
 2021-10-01 21:46:14 -07:00
Yulong Wang
448325b254
[js/web] name ort web for consistency (#9240) 2021-09-30 22:53:26 -07:00
Yulong Wang
8c57d51928
support WebAssembly SIMD for qgemm (#9191) 
* support WebAssembly SIMD for qgemm

* remove '--experimental-wasm-bulk-memory' for test
 2021-09-30 12:40:56 -07:00
Changming Sun
e1b84eefcc Revert "Revert "linux trt package pipeline (#7537)"" 
This reverts commit b606005858.
 2021-09-30 11:39:23 -07:00
Edward Chen
5326397a6a
[iOS] Facilitate usage of pods with custom builds (#9216) 
Refactor iOS framework build/pod package creation into a separate script that can be used with custom builds.
Add documentation.
 2021-09-30 08:44:00 -07:00
Changming Sun
b606005858 Revert "linux trt package pipeline (#7537)" 
This reverts commit faea7a222d.
 2021-09-28 19:09:04 -07:00
Suffian Khan
6f580f07de
Switch AMD CI pipeline to use environment image from onnxruntimecibuildenvironment (#9206) 
* shift docker image reference for amd ci pipeline

* fix service endpoint

* reduce perf tolerance
 2021-09-28 13:06:16 -07:00
Changming Sun
1104e8d3e5
Linux Anybuild build pipeline (#9091) 2021-09-28 11:22:27 -07:00
Sheil Kumar
f16bb37fae
make uwp store apps link to statically-linked crt desktop builds (#9182) 
Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
 2021-09-27 15:37:15 -07:00
baijumeswani
c30cc9190a
Change the agent pool for orttraining-distributed pipeline (#9179) 2021-09-26 21:26:44 -07:00
Suffian Khan
47888392ab
Fix nightly CI pipeline to generate ROCm 4.2 wheels and add ROCm 4.3.1 wheels (#9101) 
* make work for both rocm 4.2 and rocm 4.3.1

* fix rocm 4.3.1 docker image reference

* fix CUDA_VERSION to ROCM_VERSION

* fix ReduceConsts conflict def

* add ifdef to miopen_common.h as well

* trailing ws
 2021-09-19 23:36:03 -07:00
Yulong Wang
0183492931
simplify Web CI pipeline (#9094) 2021-09-17 13:00:07 -07:00
Guoyu Wang
438175cb34
Build shared host protoc in iOS CI pipelines (#9087) 
* iOS build, share host protoc build

* Change android ci

* ios packaging ci

* checkout submodule

* revert

* update package pipeline

* minor update
 2021-09-16 17:16:50 -07:00
Yulong Wang
498461485f
optimize WebAssembly CI pipeline (#9058) 2021-09-16 01:07:36 -07:00
Guoyu Wang
bee5c26580
Add CPU_ONLY runtime option to NNAPI EP (#9066) 
* Add NNAPI cpu only option

* update java

* Update comments
 2021-09-15 15:50:18 -07:00
Suffian Khan
e758870b18
Upgrade ROCm CI pipeline for ROCm 4.3.1 and permit run inside container (#9070) 
* try to run inside 4.3.1 container

* no \ in container run command

* remove networking options

* try with adding video render groups

* add job to build docker image

* try without 1st stage

* change alpha, beta to float

* try adding service connection

* retain huggingface directory

* static video and render gid

* use runtime expression for variables

* install torch-ort

* pin sacrebleu==1.5.1

* update curves for rocm 4.3.1

* try again

* disable determinism and only check tail of loss curve and with a much larger threshold of 0.05

* disable RoBERTa due to high run variablity on ROCm 4.3.1

* put reduction unit tests back in
 2021-09-15 12:32:02 -07:00
Changming Sun
4930320647
Delete linux-pytorch-custom-ops-ci-pipeline.yml (#9023) 2021-09-14 21:51:21 +00:00
Suffian Khan
4322f7e647
Fix ROCm wheels CI pipeline break by installing latest protobuf from source (#9047) 
* install protobuf from source

* fix rm command in Dockerfile

* fix options on rm command

* fix cd into protobuf source directory

* try again

* remove strip step

* debug list the files

* ls on /usr

* more debug

* more debug

* adjust LD_LIBRARY_PATH

* try remove protobuf before ORT build
 2021-09-14 12:07:00 -07:00
Guoyu Wang
cf70635d2a
Add Android executable drop in the Package pipeline (#9050) 
* add copy executable for android job

* minor fix

* Variable fix

* Move to use tgz because zip is not part of the docker image

* update compression
 2021-09-14 11:45:33 -07:00
Yulong Wang
be80698698
[js/web] a bugfix and add tests for wasm proxy worker (#9048) 
* [js/web] add tests for wasm proxy worker

* fix script src override
 2021-09-14 10:38:58 -07:00
Guoyu Wang
c709380c52
Add full iOS job in package pipeline (#9036) 
* Add full ios xcframework job

* create zip file of the xcframework
 2021-09-13 15:54:11 -07:00
Edward Chen
29d6573f3d
Increase timeouts for Mac CI builds. (#9024) 
Increase timeouts for "orttraining-mac-ci-pipeline" and "iOS CI Pipeline" CI builds.
 2021-09-10 12:57:08 -07:00
Chi Lo
0367e1f1c2
Update Nuget Packge Pipline to CUDA11.4 and TensorRT8 on Windows (#9000) 
* Update to CUDA11.4 and TensorRT-8.0.3.4

* update trt pool, remove cudnn from setup_env_gpu.bat

* revert pool

* test gpu package pipeline on t4

* back out changes

* back out changes

Co-authored-by: George Wu <jywu@microsoft.com>
 2021-09-09 06:56:37 -07:00
Guoyu Wang
1533f574e4
Add full Android job in package pipeline (#9009) 
* Add full Android job in package pipeline

* Address CR comments
 2021-09-08 21:12:59 -07:00
Yulong Wang
2e8792ca42
[js/web] fix karma launch with chrome headless (#8998) 2021-09-08 11:52:41 -07:00
George Wu
a30d9f5317
fix windows gpu pipelines that use cuda 10.2 (training, reduced_ops and 10.2 validation) (#8994) 
* build for arch 52

* arch 52

* gpu arch 52
 2021-09-07 22:01:06 -07:00
Changming Sun
0bb56a18cf
Add TRT header file to ORT GPU nuget package (#8962) 2021-09-07 09:50:09 -07:00
Scott McKay
eebcc20f10
Add netstandard2.0 framework to nuget managed package. (#8960) 
* Add netstandard2.0 to nuget managed package.
Re-does PR that was backed out due to packaging pipeline changes.
Allows deprecation of netstandard1.1 in the following release as netstandard2 is the preferred lowest level framework.
 2021-09-04 08:01:46 +10:00
Olivia Jain
a0c9408f0d
Make TRT Version Configurable (#8864) 
* copy changes from trt_and_mem

* second edits

* Update linux-gpu-tensorrt-ci-perf-pipeline.yml for Azure Pipelines

* Update linux-gpu-tensorrt-ci-perf-pipeline.yml for Azure Pipelines

* Update linux-gpu-tensorrt-ci-perf-pipeline.yml for Azure Pipelines

* change to cuda 11.4

* build with cuda 11.4

* Update Dockerfile.ubuntu_cuda11_1_tensorrt7_2

* add cmake extra defines

* cmake architectures

* fix cmake arch

* Delete ubuntu-18.04.Dockerfile

* Rename Dockerfile.ubuntu_cuda11_1_tensorrt7_2 to Dockerfile.ubuntu_cuda11_4_tensorrt7_2

* Update linux-gpu-tensorrt-ci-perf-pipeline.yml

* Update linux-gpu-tensorrt-ci-perf-pipeline.yml for Azure Pipelines

* removing previous ort args

* rename to cuda 11.4

* remove cuda 10_2

* delete trt 7.1

* remove 7.1

* Passing in cuda architecture to reduce build time

* always add submodule sync due to recursive cloning

* fix run command

* add and

* take away unused arms and share python installation script

* Update linux-gpu-tensorrt-ci-perf-pipeline.yml

* Update Dockerfile.tensorrt

* cleanup file

* install python directly on dockerfile - move to scripts in future

* Update Dockerfile.custom-trt-perf

* adding cuda 11.1 for missing Libnvrtc.so.11.1

* Delete install_python.sh
 2021-09-03 13:32:27 -07:00
Chi Lo
1f576e1766
Detect necessary files inside GPU packages (#8955) 
* Rename files

* Update YAML files

* Update validation script and YAML
 2021-09-03 13:28:28 -07:00
liqun Fu
a7f5bd226b
retarget torch181 to torch182 (#8947) 
Co-authored-by: liqun <liqun@OrtTrainingDev4.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net>
 2021-09-03 09:44:42 -07:00
Changming Sun
1a34775fe9
Fix the benchmark code (#8926) 2021-09-02 10:36:24 -07:00
Changming Sun
fbb6f0f599 Fix an error in Nuget pipeline caused by merge conflict 2021-09-02 09:26:25 -07:00
Sunghoon
332c2ba4f4
[js/web] Integrate ONNX Runtime Web CI with BrowserStack (#8859) 
* Integrate ONNX Runtime Web CI with BrowserStack

* Rename a pipeline from browserstack to multi-platform
 2021-09-01 17:25:57 -07:00
liqun Fu
f126a12699
decouple pytorch from onnxruntime training build (#8815) 2021-09-01 16:31:53 -07:00
Changming Sun
6299a60bf8
Nuget: splitting PDB files to a separated package (#8903) 2021-09-01 09:07:24 -07:00
Suffian Khan
00b0a9c127
Add hugging-face models loss curve and performance guards to ROCm CI pipeline. (#8915) 
* test running hf bert-large

* try again

* try again

* include other models

* correct names

* disable deberta-v2-xxlarge

* avoid torch.distributed

* add compare json loss and perf for bert-large to test

* fix sed expression

* remove pytest

* add more models

* move unit tests u

* display samples/sec
 2021-09-01 09:03:10 -07:00
Changming Sun
a9a0d3f6fa Update min supported macOS version to 10.14 2021-08-31 16:09:48 -07:00
Changming Sun
129722db37
Add android binary size monitor back (#8904) 2021-08-31 14:13:55 -07:00
Olivia Jain
33c0b3e94b
Perf test fixes (#8863) 
* fix anubis wheel upload and symbolic shape infer location

* Update linux-gpu-tensorrt-ci-perf-pipeline.yml for Azure Pipelines

* Update linux-gpu-tensorrt-ci-perf-pipeline.yml for Azure Pipelines

* Update linux-gpu-tensorrt-ci-perf-pipeline.yml for Azure Pipelines

* fix symbolic path

* use master and call mem_test after build

* Update linux-gpu-tensorrt-ci-perf-pipeline.yml

* use installed symbolic shape infer TODO: check upon error

* catch symbolic shape errors
 2021-08-31 10:03:47 -07:00
Changming Sun
c6d9426ef2
Add binary size reporting back (#8883) 2021-08-30 19:48:38 -07:00
Abhishek Jindal
868c8af9ac
Abjindal/eager mode pipeline (#8870) 
* Adding pipeline file for eager mode

* adding the build eager mode flag

* adding torch wheel files for installation

* Changing pytorch version for change in wheel files

* updating requirements file path

* Removing Java and NodeJS from the build

* removing import torch for testing build of eager mode

* changing the build command

* import torch

* building eager mode separately

* removing Java tests

* python path issues

* changing python path location

* changing the build path file loc

* installing torch before build

* setting environment for building eager mode

* Copying the build file and getting rid of flags

* changing python path

* adding missing packages

* moving build eager mode code

* changing python path to python3

* adding amd_hipify

* adding logger file

* install torch before build

* change requirements file location

* install torch before build eager

* modifying eager mode build

* modifying build location

* adding new docker image

* handling gradle move issue

* Typo fix

* changing deps file

* adding java and nodejs

* changing repo name for docker image

* removing pybind

* building only eager mode

* changing the image name

* removing install wheel package

* build complete onnxruntime with eager mode

* building wheel

* enabling pybind

* adding build eager mode flag in unit tests

* removing build java nodejs

* adding build command

* removing java tests

* moving Debug tests before Release

* building Debug only case

* changing debug test code

* running the build eager mode with tests

* adding build dir

* adding build dir path

* changing build dir path

* changing build command for eager mode

* building eager mode and running tests simultaneously

* adding more flags to the pipeline

* chaning flag

* adding Debug and Release

* changing torch to nightly build

* changing torch version for nightly build

* chaning torch version

* move to Ubuntu image

* adding pool

* adding dockerfile for eager mode

* adding python deps file for eager

* modifying python deps file for eager

* changing deps file

* changing deps file statements

* changing python path

* REMOVING ECHO line

* going to original docker file

* changing docker file

* changing to eager requirements file

* changing python deps file

* changing paths

* changing cmake path

* changing build script

* changing python installation

* running debug mode only

* changing pipeline file

* test name

* test name

* test name2

* changing requirements file

* final flags for eager mode

* previous pipeline

* moving to ubuntu image and including some deps

* adding cmake path

* returning to manylinux image

* removing unncecessary files for pipeline
 2021-08-30 18:24:39 -07:00
Changming Sun
6df4e293ff Remove unused code in tools/ci_build/github/azure-pipelines/nuget/templates/gpu.yml 2021-08-30 15:37:40 -07:00