Update onnx master #1
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…t of QLinearSigmoid (#6534) * Init change * Add QlinearSigmoid support * Update tests * Add resize int8 support * Add version check for resize linear uint8 and add scale/zero point check for concat uint8 * Address CR comments * minor fix and add test for uint8 handling * Address CR comments * Fixed an existing bug * Fix the new UT break, due to different rounding of 0.5 in device and emulator
…lDevice on machine without hardware adapters (#6535) * Checkoutpoint 1 * Remove global logruntime error telemetry. This isn't necessary and doesn't contain relevant information * Make macro simpler Co-authored-by: Ryan Lai <[email protected]>
* switch to jdk11 * fix java * Update
* [CoreML EP] Add support of Conv operator * Ignore an corner case setting empty padding * Add handle autopadding * Addressed CR comments
1. Merge Nuget CPU pipeline, Java CPU pipeline, C-API pipeline into a single one. 2. Enable compile warnings for cuda files(*.cu) on Windows. 3. Enable static code analyze for the Windows builds in these jobs. For example, this is our first time scanning the JNI code. 4. Fix some warnings in the training code. 5. Enable code sign for Java. Previously we forgot it. 6. Update TPN.txt to remove Jemalloc.
Update CPU Cast implementation to fix performance regressions. Update Cast unit tests for more coverage.
…supported, so disable those typed kernels.
* Add type reduction support to Slice and Transpose
…ack type usage for. (#6565)
* Enable type reduction in Gather.
…t EP fails (#6580) * Let exccution fall back to CPU EP if compile of a partition fails * Removed debugging logs * Addressed CR comments
* Add warning when GetGradientForOp() silently fails. In some cases, `GetGradientForOp()` can return without creating any nodes, which may lead to an invalid graph being created.
…tions to reduce the size used by function names in ORT_ENFORCE(). (#6624) Move ORT_ENFORCE()'s within MLTypeCallDispatcher to helper class functions to reduce the size of function names in ORT_ENFORCE(). ORT_ENFORCE() captures the containing function's name in the error message. For some usages of MLTypeCallDispatcher (i.e., with numerous types or long type names), the function name is quite long and can contribute significantly to the binary size. Usage in the Cast CPU kernel is a notable example. This change moves the ORT_ENFORCE() checks from a class template member function template with variable length name to a helper function with a fixed length name.
hipFFT is transitioning to a separate repository (away from being included in rocFFT). During this transition, using the hipFFT version of hipfft.h won't produce a deprecation warning.
* Add NNAPI EP option to disable CPU * update comments * Address CR comment * Address CR comments, update code comments * Address CR comments
…Max]Pool (#6625) * [CoreML EP] Add batch norm support * Add reshape support * Add global pooling support * Addressed CR comments
* support skiplayernorm fusion without beta in layernorm * use place holder * review comments
* bert_base_cased: embedlayer fusion * xlm_mlm_en_2048: attention fusion
* skip constant folding dequantizelinear for quant qdq format
Add python 3.8/3.9 support for Windows GPU and Linux ARM64 Delete jemalloc from cgmanifest.json. Add onnx node test to Nuphar pipeline. Change $ANDROID_HOME/ndk-bundle to $ANDROID_NDK_HOME. The later one is more accurate. Delete Java GPU packaging pipeline Remove test data download step in Nuget Mac OS pipeline. Because these machines are out of control and out of our network, it's hard to make it reliable and the data secure. Fix a doc problem in c-api-artifacts-package-and-publish-steps-windows.yml. It shouldn't copy C_API.md, because the file has been moved into a different branch. Delete the CI build docker file for Ubuntu cuda 9.x and Ubuntu x86 32 bits And, due to some internal restrictions, I need to rename some of the agent pools
* Fix broken links to EP docs * Fix another link * Simplify content to link to docs site * Update README.md * Add build pipeline status * Fix openvino pipeline widget
* Move type agnostic code out of UnpackInitializerData Refactor the unpack tensor logic to switch on data size Add test cases * Remove templatization of more parts
Registrations need to either be between a start and end version, or be the current version. Having a macro that uses 3 versions will break or lead to misuse when a 4th version is released.
* Enable type reduction for ConstantOfShape.
…est (macOS only) (#6642)
… similar to V100. (#6611) * Partial updating of ROCM reduction code. * Update reduction_all.cu * Add reduce template parameters. * miopen common * Reuse CUDA's reduction_functions.cc * Reduction ops. * Update remaining reduction ops to use MIOpen. double datatype is not supported, so disable those typed kernels. * Disable a couple more unsupported tests. * Code formatting. * Delete ROCM-specific reduction code that is identical to CUDA reduction code. * Fix scratch buffer early free. * Fix merge conflict. * first attempt nightly amd ci pipeline * try fix bad yaml file * try again with corrected model directory * add convergence test as well * update reference loss for amd mi100 * include mi100 test results csv * update the mi100 convergence test reference values * update batch sizes for mi100 32g * fix gpu sku for run_convergence_test.py * undo unrelated changes to master * pr comments * pr comment Co-authored-by: Jesse Benson <[email protected]>
…arious Audio operators (#6623) * model building * fix build * winml adapter model building api * model building * make build * make build again * add model building with audio op * inplace and inorder fft * add ifft * works! * cleanup * add comments * switch to iterative rather than recursive and use parallelization * batched parallelization * fft->dft * cleanup * window functions * add melweightmatrix op * updates to make spectrogram test work * push latest * add onesided * cleanup * Clean up building apis and fix mel * cleanup * cleanup * naive stft * fix test output * middle c complete * 3 tones * cleanup * signal def new line * Add save functionality * Perf improvements, 10x improvement * cleanup * use bitreverse lookup table for performance * implement constant initializers for tensors * small changes * add matmul tests * merge issues * support add attribute * add tests for double data type windowfunctions and minor cleanup * stft onesided/and not tests * cleanup * cleanup * clean up * cleanup * remove threading attribute * forward declare orttypeinfo * warnings * fwd declare * fix warnings * 1 more warning * remove saving to e drive... * cleanup and fix stft test * add opset picker * small additions * add onnxruntime tests * add signed/unsigned * fix warning * fix warning * finish onnxruntime tests * make windows namespace build succeed * add experimental flag * add experimental api into nuget package * add experimental api build flag and add to windows ai nuget package * turn experimental for tests * add minimum opset version to new experimental domain * api cleanup * disable ms experimental ops test when --ms_experimental is not enabled * add macro behind flag * remove unused x * pr feedback Co-authored-by: Sheil Kumar <[email protected]>
…6663) * Remove support from custom ops from the base minimal build as they contribute too much binary growth to an Android build. Add ability to explicitly enable custom op support in a minimal build. Change one minimal build CI to test adding custom op support (unit tests are run in that build to validate)
1. For previous openmp build, remove --use_openmp, so thread pool will become default; 2. For previous non-openmp build, add --use_openmp and rename the package to indicate the inclusion. 3. Add a mac build with openmp enabled.
…ion (#6654) * Adding changes to enable ov_config_options Enabling a flag to pass OpenVINO Runtime options as an string argument using a command line. * Enabling OpenVINO Runtime options for perftest Enables OpenVINO EP runtime options into onnxruntime_perf_test. Now these options can be passed as an argument to the perf test CPP application using key-value pairs seperated by a space via a command line. Signed-off-by: MaajidKhan <[email protected]> * minor changes added * Corrected Indentation Signed-off-by: MaajidKhan <[email protected]> * corrected Indendation issues Signed-off-by: MaajidKhan <[email protected]> * Making config options generic to all EP's Signed-off-by: MaajidKhan <[email protected]>
…rnelDefConstraintsFromTypeList function. (#6674)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.