* Add ability to generate ios static framework
* Fix typos
* Add pod cache clean, update some comments of previous commit
* Fix CI failure with newly added cpuinfo library
* Update test model (CoreML requires node has a name)
* Addressed CR comments
Fix bug that shows up when running tests (in particular, GraphTransformationTests.ConcatSliceEliminationTest) with more verbose logging level.
There is a log statement that doesn't get evaluated at the default test logging level (warning). It was accessing the first element of an empty vector. This change moves that log statement before the point where that vector is cleared.
Updates to the iOS packaging pipeline:
- Make it harder to overwrite package archives accidentally when uploading (fails if the archive already exists)
- Only upload package archives for release builds
- Some clean up
* [ROCm] clear last status if hipErrorNotReady
* use hipEventDisableTiming in rocm_fence.cc
* fix syntax errors
* destroy event before handle becomes invalid
* Add memory check for TRT perf
* Revise test app
* Add memory check for TRT perf
* Revise test app
* add test cases
* Modify script and add pipeline YAML
* remove redundant code
* temporarily change
* Change YAML
* revise test app
* fix minor bug
* code refactor
* small fix
* temporarily change for test
* prepare result log
* rm container when it exits
* code refactor
* unregister registered python functions upon normal interpreter termination
* atexit.register(unregister_python_functions) should be called by __init__.py
* minor fix
* Update submodule onnxruntime-extensions to latest.
* Add document for onnxruntime-extensions.
* Update cgmanifest.json for onnxruntime-extensions.
* Add example in JavaScript.
Co-authored-by: Zuwei Zhao <zuzhao@microsoft.com>
Pytorch cpuinfo library allows us to query current cpu features, micro-architecture and cache size, etc. These information is needed for targeted performance optimizations.
Unfortunately it does not work under Windows/ARM. We need to develop our own later
This PR purely extracts each kernel to a standalone file. No functionality change. It includes specifically:
leave the MlasGemm function and thread handling in the qgemm.cc
put dispatcher functions and the template functions (interfaces) that are required to implement a kernel into qgemm.h
put each kernel implementation in a separate file, which implements/specialize template functions: MlasGemmU8X8FixupZeroPointB, MlasGemmU8X8CopyPackA, MlasGemmU8X8CopyPackB, MlasGemmU8X8Kernel
determine the files to be compiled in cmake file
1. Add support for sequence ops: ConcatFromSequence, SequenceAt, SequenceInsert. There are other sequence ops supported by onnx that worked well after adding these ops, so no need to add all of them in symbolic_shape_infer
2. For If node, the two branches output might have different shapes. In that case, for sequence output, use None in dimension; For tensor output, create a new symbolic dimension.
3. Fix a bug in Tile, where input for repeats might be of unknown value
4. Topological sort of nodes in graph need to consider implicit input in subgraphs for If/Loop/Scan ops
5. Generate unique prefix for new dimensions inside subgraph
* Add metadata_props to ORT model
* Minor update
* Update python binding, and increase the minimal pipeline size threshold
* Fixed a small bug in serializing ir_version
* Remove temp ort.py.fbs and add it to .gitignore
* handle unsqueeze change in opset13
* fix the node arguments index check for square case (x * x)
* Revert "fix the node arguments index check for square case (x * x)"
This reverts commit c66344f0a82c35d8c24d31f2264cf7e9b235ce22.
* handle the square case (x * x) for node argument search
Co-authored-by: Cheng Tang <chenta@microsoft.com>
* Add new transformer that can split node selection from node modification to allow just the modifications to be applied at runtime in a minimal build. This is the first step of a few to enable a QDQ model to be optimized for the NNAPI EP and/or the CPU EP at runtime in a mobile scenario.
Add generic and QDQ specific helpers for selection and modification.
Replace existing QDQ optimizers with optimizer based on new approach.
* first attempt share docker image across python and torch versons
* set dependency between jobs
* fix yaml grammer
* remove python version from first stage
* clean deepspeed directroy
* split into two images according torch version
* fix yaml syntax
* invalidate cache
* remove DS to prevent torch 1.9.0 upgrade
