* consume onnx test data from github
* ensure tests
* update script and allow opset specification
* fix python format
* fix python format
* consume new filter format
* fix linting error
* use 3D grid to avoid the upper limit of grid dimension
* enrich tests
* Revert "use 3D grid to avoid the upper limit of grid dimension"
This reverts commit 2d5badf2fe8cd985f3f29ee2cb18fff13d07c2ab.
* change to a fix: switch the 1st and 2nd dim
This change updates the implementation or te argmax_out operator to 1)
set the output tensor correctly and 2) remove the unnecessary use of a
temporary tensor to store intermediate result of onnx ArgMax operation.
Previously, the argmax_out operator did not correctly update the out
tensor - it replaced the OrtValue instead of the memory backing the
OrtValue . To properly update the output tensor, we need to calculate
the expected shape of the out tensor.
We add the helper function calculate_reduction_shape to calculate the
shape of the reduced tensor from the input tensor, dimension to reduce,
and option to keep the reduced dimension or not. This is based on the
utility functions in aten/src/ATen/native/ReduceOpsUtils.h in the
PyTorch repository, but is tailored to be a bit more specific to our
current needs.
Notes:
We considered just directly leveraging PyTorch's utility functions (e.g.
get_reduction_shape) to calculate the shape of the reduced tensor from
aten/src/ATen/native/ReduceOpsUtils.h in the PyTorch repository, but
including this header file resulted in warnings around unused functions
that we need to handle. As we only need a limited functionality at the
moment, we instead implemented our own utility function to calculate the
reduction shape for our specific current needs. If we need a utility
function to more generally calculate the reduction shape, we could
consider switching to leveraging the utility methods in PyTorch.
* refactor test for model with undefined shapes
* add test for TVMso EP
* update build script for TVM EP tests
* fix pylint
* disable test for Windows
* fix black
* fix python format
* fix pylint
* fix python format
* replace Path.resolve with os.path.join
* fix python path issue
Co-authored-by: Valery Chernov <valery.chernov@deelvin.com>
* add scripts
* update docker scripts
* update build script
* create run script
* add test script
* add log 3 flags
* use the right build function
* build navi
* add clean script
* add pytorch like soln
* only build gfx 1030
* use HOST side var
* ignore logs
* update scripts
* GPU_WARP_SIZE_HOST
* update scripts
* remove scripts/amd
* match main
* add GPU_WARP_SIZE_HOST on cuda side
* match main
* correct gfx1030
* remove print
* move gfx add to rocm5.0
* remove inline
* make constexpr on cuda side
Fix bug where onnxruntime_USE_NCCL flag would default to ON, causing ORT to not build properly. New functionality: flag is ON when training is enabled and NCCL is not disabled. Flag is OFF otherwise
* Add file mapping for windows platform.
* Add unit test for file mapping for windows. Also add an error message for mis-aligned offset
* Add unit test for file mapping for windows. Also add an error message for mis-aligned offset
* Update data type to avoid warnings
* Compitable data type to avoid warnings. Update CreatFileMapping2 condition for winml compiling.
* Add type conversion to avoid warnings for X86 release build.
Co-authored-by: Ting Cao <ticao@microsoft.com>
* [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>
