* [UPDATE] update ci to rocm5.2 + torch1.11
* [Revert] disable ort module test
* [DELETE] delete Rocm5.1.1 ci test result
* [UPDATE] update the comments
Add a graph optimization that convert u8s8 matrix multiplication to u8u8 if needed
In x86/64 platforms, specifically SSE4.1, AVX2 and AVX512 CPUs provide better performance computing u8s8 matrix multiplications. Unfortunately, the higher performance comes with value overflow problems, as described in:
https://www.intel.com/content/www/us/en/develop/documentation/onednn-developer-guide-and-reference/top/advanced-topics/nuances-of-int8-computations.html
In this change we added a session option "session.x64quantprecision" (default off). For operators that calls u8s8 matrix multiplications, e.g. QAttention, we convert them to u8u8 when the following conditions are all satisfied:
1. Current CPU is SSE4.1, AVX2 or AVX512 with no VNNI support
2. Session option "session.x64quantprecision" is on.
3. Constant weight tensor contains values outside of [-64, 63] range
Note that when weight tensor is not constant, QDQS8ToU8Transformer should already convert it to u8.
* add description of build ORT+TVM EP on Windows
* fix cmake error related to symlink creation on Windows
* add llvm config path to build flags for correct build on Windows
* update TVM_EP.md for llvm_config build arg
* fix warnings skipping during build on Windows
* fix using string or wstring for model path to correct build on Windows (MSVC error)
* fix error in custom logger for correct build on Windows
* implement glob algorithm for Windows
* additional build fixes
* update TVM with export of VM symbols for dll
* description of nasm issue and workaround
* update TVM with export of Executable from VM symbols for dll
* description of installation of ipp-crypto dependencies on Windows
* cmake key for ipp-crypto build
* fix wstring for TVMso EP
* fix ipp-crypto build
* cmake key onnxruntime_TVM_USE_HASH switch off not specific methods, but full hash functionality
* fix absolute path to compiled lib
* update TVM_EP.md, fix lint warnings
* update TVM_EP.md
* small fixes after review
* switch on handshake functionality for Linux workflow
Co-authored-by: Valery Chernov <valery.chernov@deelvin.com>
Co-authored-by: KJlaccHoeUM9l <wotpricol@mail.ru>
* Fix GH issue 12151.
Need to use inverse perms for updating that axis to what is used for transposing the input. This only applies if the DQ node is doing per-axis dequantization.
**Description**: This fixes error handling in the JNI code in OnnxMap, OnnxSequence, OnnxRuntime, RunOptions. SessionOptions and OrtEnvironment are correct as is.
The bulk of the work will be in rewriting OnnxTensor, OnnxSparseTensor (after the merge of #10653) and OrtSession, along with the helper methods in OrtJniUtil. I plan to tackle those in separate PRs to reduce the amount of code to review.
**Motivation and Context**
- Why is this change required? What problem does it solve? The current native interop code doesn't return control to Java immediately on throwing an exception from an ORT error code, which can cause incorrect interactions with native ORT, and issues with exception propagation on the Java side.
- If it fixes an open issue, please link to the issue here. Partial work towards solving #11451.
* test case for masked_select
* isolate variables per onnx_op, include line numbers for ORT errors
* format errors
* correct masked_select impl, broadcast test
* node attrs naming fixed
* Add tests for all uniary aten ops supported in eager mode
* fixing the PR draft
* fixing the merge
* changing eval to be at compile time
* adding requirements for eager
* 1.adding function to {ops}_out
2.cleaning the code
and adding comments
* editing the code according to code review
Co-authored-by: root <root@AHA-LIRONKESE-1>
Description: In the PR 12018 a few fixable python and cpp warning were introduced that this PR cleans up. Also adding a comment on the intent of test_mul_bool and out testing on test_ones.
Motivation and Context
When iterating in Python, use a list instead of a set and don't use reserved words
Fix long line in cpp
Clarify test_mul_bool intent for future developers.
fill_ implements torch.ones under the covers but in previous pr verification on the out param was not added so adding it here.
* First attempt for half2 vectorized memory access in SkipLayerNorm
* Add some functions for debugging
* Clean up the code
* Clean up the code
* Generalize the vectorized kernels with aligned_vector and remove cudaDeviceProp
* Add a unit test for a larger input size
* Fix some Lint C++ warnings
* Use ILP = 4 for the vectorized kernels
* Rewrite the vectorized kernel and templatize ComputeSkipLayerNorm
* Use conditional operator for input_v
* Refactor LaunchSkipLayerNormKernel and replace the original SkipLayerNormKernelSmall with the vectorized kernel
* Clean some comments and rename the layernorm function
* Use ComputeSkipLayerNorm to replace LaunchSkipLayerNormKernel
* Resolve a Lint C++ warning
* Fix SkipLayerNormBatch1_Float16_vec output data
* Add hipified code of bert SkipLayerNorm for ROCmEP
* Resolve some Lint C++ warnings
* Resolve some Lint C++ warnings
* Resolve some Lint C++ warnings
* Resolve Python formatting issue
* First attempt for half2 vectorized memory access in SkipLayerNorm
* Add some functions for debugging
* Clean up the code
* Clean up the code
* Generalize the vectorized kernels with aligned_vector and remove cudaDeviceProp
* Add a unit test for a larger input size
* Fix some Lint C++ warnings
* Use ILP = 4 for the vectorized kernels
* Rewrite the vectorized kernel and templatize ComputeSkipLayerNorm
* Use conditional operator for input_v
* Refactor LaunchSkipLayerNormKernel and replace the original SkipLayerNormKernelSmall with the vectorized kernel
* Clean some comments and rename the layernorm function
* Use ComputeSkipLayerNorm to replace LaunchSkipLayerNormKernel
* Resolve a Lint C++ warning
* Fix SkipLayerNormBatch1_Float16_vec output data
The generated bindings causes C# build errors that require workaround code. Disabling generation should avoid the need for any workarounds.
As the user has the C# ORT package with the C# to C bindings there's no need for binding generation that calls the ORT Java API (which is C# -> Java ->C).
* Add op tuning functionality and example for vector add.
* Add namespace.
* Various improvements.
* use unique pointer
* fix lint errors
* Check return error.
* Add utility methods for resize_output
* Eager mode: implement abs.out
This is an initial hand written implementation of an out= operator to
demonstrate how to structure out= methods using resize_out helper
methods.
This is meant to be used as a reference when we update the code
generator to generate implementations for out= operations.
