GitLab

comment cleanup, some test fixes, minor refactoring of parse_resize.  onnx_test still fails; needs to be updated with new instructions.

 Add tracing to benchmark to show which kernels are running and the time of every kernel

Adds workarounds to avoid passing capture ops and scalar literals from quantization as arguments to ck_gemm.

Bumps [urllib3](https://github.com/urllib3/urllib3) from 1.26.15 to 1.26.18.

* Update onnxruntime main 635d3faa3b3908d2806d009dc6872152cfcfcdda
* Update script for build_and_test_onnxrt.sh

* Disable -Wunsafe-buffer-usage when compiling gpu code

This will enable MLIR by default for these cases:

Any convolution fusion
Any int8 gemm fusion
All Navi3 standalone convolutions
With a flag(ie MIGRAPHX_ENABLE_MLIR) to enable MLIR for floating-point gemm fusions
Except:

3x3 winnograd convolutions fusions (except on Navi)
K > 2048 on gemm (as CK)
Also there is MIGRAPHX_DISABLE_MLIR to disable MLIR completely.

Add support for the QLinearMatMul onnx operator

This sets up the virtual environments for running python onnx tests.
ctest's fixtures are used to ensure that the virtual environment is
set up before the tests are run.

Currently, we see MLIR partition candidates recieving non-standard shape due to not fusing in squeeze, flatten and unsqueeze ops. These ops could be canonicalized to reshape without introducing additional ops as long as MLIR backend is concerned.