* fix the build for mobile packaging
* update the cmake file as well
* more fixing on dlib related ops
* release the iOS cmake version constraint
* upgrade cmake in Linux CUDA build
* Update Dockerfile.ubuntu_cuda11_8_tensorrt8_6 for typo
* Update ios_packaging.yml for Azure Pipelines
* update the dlib versoin
* update all cases of cmake version
* update the comment for dlb cmake
* Unify the image operations in extensions library
* fix the build configuration issue
* More build fixings
* Fix the native image codec
* fix encode_image
* Add bgr/rgb conversion for encoding image
* parity check
* build break
* update PNG encoding parameters
* build break on Linux
* using MSE to compare images
* fix the discrependency between Linux and Windows
* final code refinement
* one more change
* fix the C++ warnings
---------
Co-authored-by: Sayan Shaw <52221015+sayanshaw24@users.noreply.github.com>
This added support for native image decoding on Windows & Apple platforms.
This helps us remove libpng & libjpeg completely on these platforms, and
in the meantime support more image formats thanks to OS vendors,
* initial commit
* Ugm vocab loaded is good
* test passed
* fixes unit test on win32
* finish the parity check
* code refinement
* code refinement for review
* Remove OpenCV dependency from C_API model
* fix build on Windows
* switch ci build flag
* try to fix the macOS build issue
* more fixing
* fix the macOS build issue
* list jpeg source
* verified on MacOS
* update the pp_api too
* avoid the codecs library conflicts
* Add the unit tests
* move the codec test
* add the missing dl lib for extensions test
* refine the code
* a smaller fixing for Windows Python
* support tokenizer build only in C API mode
* fix the python build.
* fix the selectedops build
---------
Co-authored-by: Sayan Shaw <52221015+sayanshaw24@users.noreply.github.com>
* reimplement resize cpu kernel for image processing
* accuracy fixing and code refinement
* fix the build issues
* fix Linux build issue
* more fixings
* Fix the pipeline issue
* fix the ci script
* try to fix CUDA machine pool
* switch cmake cmp0169 flag to new
* the missing spm code.
* more refinement on cmake build targets
* Update ci.yml
* Update ci.yml
* update the jpg files after using libjpeg instead of libjpeg-turbo
* exclude cutlass too
* upgrade the protobuf library to be consistent with ORT
* update the protoc generated files
* use the right patch name
* Update cutlass.cmake
* dd "-allow-unsupported-compiler" flags to Windows CUDA flags
inspired by this PR: https://github.com/microsoft/onnxruntime/pull/21004
* switch to cmake command line
* handle the issues caused by the latest MSVC release
* correct the typo
* correct the parameter
* try one dash again
* use the installed cmake
* use cmake standalone installation firstly
* use the standalone cmake in win32 python too
* fix it more
* one more try
* fix the MacOS pipeline issue
* fix the pip command line
- update protobuf version being used by sentencepiece and the java tests
- ignore unused language bindings from protobuf and triton
- specify the CG config file with ignored directories where required
Fix cgmanifest.json
- 'git' entries require a commit hash not version
- use 'other' for opencv third party code that is included directly in the opencv repo
- the path isn't a valid repositoryUrl value to be provided as a 'git' entry
- update version numbers/commit hashes to match the latest code
Co-authored-by: Sayan Shaw <52221015+sayanshaw24@users.noreply.github.com>
* only keep the image decoder from opencv
* initial build
* refine the code
* Add clear functions
* Update CMakeLists.txt
* Update opencv.cmake
* change the output type to float
* get the result
* align image-process with original Python
* move the LoadRawImages into library
* fix the calculation error
* fix the pipeline build issue
* fix the build breaks in ci pipeline
* support json configuration file and refactor the code.
* initial checkins
* fix the selectedops build failures
* add the tokenization implementation
* update the windows DEF file for c abi in cmake file
* fix the build on linux
* fix some warnings and remove the unused code
* initial import of unit tests from tfmtok
* add streaming API support
* fix the merges loading issues
* complete export from tfmtok - needs input id fixing
* fix the unit test failures.
* fix all unit test failure
* refactor streaming code
* remove the unused code
---------
Co-authored-by: Sayan Shaw <sayanshaw@microsoft.com>
* refactor the header file in include folder
* fix the basic-token eager unit test case
* a more flexible way to handle string tensor shape.
* fix the unit test path issue
* remove the multi-inherits to avoid issue during pointer casting
* add api cmake build support
* undo some temporary changes
* code refinement
* fix variadic arg
* only expose the context for ort version >= 17
* fix a shape bug
* fix the cuda build issue
* change ifdef condition of GetAllocator
* finalize the ort c abi wrapper file name
* fix the iOS build break
* align gtest version with triton
* Update ext_apple_framework.cmake for iOS header files
---------
Co-authored-by: Cheng Tang <chenta@a100.crj0ad2y1kku1j4yxl4sj10o4e.gx.internal.cloudapp.net>
* update ort version to 1.17.1
* revert python versions
* change python range to 3.8-3.12 and skip requirements install and python test for WindowsPython
* add conditions for WindowsPython for Python 3.12
* typo
---------
Co-authored-by: Sayan Shaw <sayanshaw@microsoft.com>
* build first cuda kernel
* redirect to gpu pkg
* setup resource enum and version
* recover cuh
---------
Co-authored-by: Randy Shuai <rashuai@microsoft.com>
* the cuda kernel first example
* Update test_ortops.cc
* revert some unneccesary changes
* unix-like os build failure
* refactor header files
* fix python dll exporting error.
* Initial checkins for returnable ORT ABIs
* fix for linux build
* more fixes on Python, test...
* remove the statusmsg
* native unit tests fixing
* Python unit tests fixing
* last unit test fixing
* Use in-memory certs for curl on Android
- could not get curl+openssl to be able to use the system ones
* Use static build for curl and openssl
- smaller binary size
* Cache the x509 certificate store so we don't need to re-create for every request.
* Read certs from node attribute for now.
---------
Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com>
* doc ops (#529)
* Try and make CIs pass with Azure ops enabled by default.
Misc. other cleanups
* Fix some CI issues.
Cleanups some bits and pieces.
* Fix a couple of issues.
* Fix arg to build.bat
* Increase warning in triton client build to make binskim happy (hopefully).
* Try patching the warning level in the triton grpc branch as well. Shouldn't matter but...
* Run triton patch command for windows as well.
* Add patch.exe directly so windows builds work.
* override auth gen for AOAI
* fix build
* switch to windows-static
* update model for azure chat
* document triton invoker
* doc chat endpoint
* document triton invoker
* format
* format
* format
---------
Co-authored-by: Scott McKay <Scott.McKay@microsoft.com>
Co-authored-by: Randy Shuai <rashuai@microsoft.com>
* address comments
* move doc sect
* typo
* typo
---------
Co-authored-by: Scott McKay <Scott.McKay@microsoft.com>
Co-authored-by: Randy Shuai <rashuai@microsoft.com>
* Build fixes
- zlib needs to come from vcpkg if azures ops are being built and opencv isn't enabled
- set the IR version to 8 for some of the azure ops test models so they can be tested when ORT 1.14 is used
- pass through new ort version value so that a consistent version is used to a) pull the ORT package for the c++ unit tests and b) disable azure ops if ORT version is too old.
* Update to automatically chain package to avoid build errors during the install if cmake runs commands in parallel
* Define simplified ORT_FILE for older ORT versions
* - Ensure we log an error message before throwing on Android
- message in exception will be lost due to how the shared libraries are built (both onnxruntime and extensions use static libc++ so there are no shared exception types between them)
- support static or dynamic build of curl/openssl on android
- TBD which we want to use.
- add infra for anything deriving from BaseKernel to log messages using the ORT logger
- ensures messages from custom kernels end up in the same place as messages from ORT
* Fix LNK4098 warning from sentencepiece forcibly changing the build flags.
> LINK : warning LNK4098: defaultlib 'LIBCMT' conflicts with use of other libs; use /NODEFAULTLIB:library
* Use CMAKE_MSVC_RUNTIME_LIBRARY to determine whether /MT should be used.
* Add TrieTokenizer for RWKV-like LLM models
* add more tests
* fix the windows build
* downloading file instead of check in the vocab file
* a small bug fixing
* Refactor setup for Azure ops to try and make common things more re-usable, and for the actual ops to simply layer in the specific input/output constraints for that type of request.
Currently builds on Linux, Windows (x64 only) and Android
Android requires a manual pre-build of openssl and curl.
Linux requires a manual pre-install of openssl.
Windows currently only works for x64. Other targets need the triplet adjusted.
* Address PR comments
* Fix could of android build warnings.
* Update .gitignore to remove old path
* Fix build break from merge
Wenbing Li
Rony Fadel
Chester Liu
Scott McKay
cao lei
Rachel Guo
Sayan Shaw
Yi Zhang
RandySheriffH
Edward Chen