GitLab

* [MLIR] Adds a runtime switch to trigger MLIR

* Update github action for onnxruntime sync to open autoPR

fallback to msgpack for older msgpack versions

* NMS improvements

resolve half info messages while building 

github action file change

Enable multiple orgs for testing

Add additional documentation to explain the passes.

Creates the select_module operator that selects one of the submodules passed to it to run based on the submodule parameters.  The submodule is selected by having the exact same static shapes for the arguments to select_module as the parameters in the submodule

* Add a Changelog to the repository

Enable python 3.10 bindings

Avoids double global loads.  Strided loops are unrolled which lets store results in array which compiler will use registers for since the index access is constant.   Updated to handle large reductions so which results with a better stable diffusion result

* deprecate HCC

* Add driver flag "--exhaustive-tune" to enable tuning, add support for the same in C/C++ and python API

Add dynamic shape support to slice operator.

First draft of this feature doesn't support ops slicing non-fixed, dynamic axes. Resulting shape in such cases is not guaranteed.* Also, onnx parsing doesn't support any arguments other than "axes".

Use requirements-dev.txt instead of the other instances

Currently, we default to device 0 when loading programs. Updating this to use hipGetDevice to set the device for the loaded program.

Expands on the documentation and corrects default option documentation error.

* Add serialization of tuples and optional types

Using add_instruction for the neg op was causing issues on replace_instruction. Changed to use insert_instruction.  Tests and added a new one that is failing without the change.

* add dynamic shape support to concat operator.  Includes new op_shape_test and ref_ops_test cases

dyn shape support for Where operator.  Includes shape test, ref_ops test, onx_test. 

Change download location for onnx model from AWS ONNX to download.onnxruntime.ai

* Fuse layernorm with different patterns
* Only match when using the last axis
Co-authored-by: kahmed10 <15948690+kahmed10@users.noreply.github.com>
Co-authored-by: kahmed10 <15948690+kahmed10@users.noreply.github.com>

Switch default ROCm version to 5.4.2 and default calculation algorithm to defined threshold

Refactors memory coloring to only handle allocation instructions. It also handles allocations for tuple shapes.

* Implement dynamic shapes for scatterND operators.

Dynamic shape support for gathernd op.

[Experimental] Update accuracy checker for tf support and map input dims (custom input shape) (#1514)

* update file reading function to fix external data loading

Allows migraphx to inline the IF operator when we run into an IF that can be evaluated at compile time, thus avoiding us injecting IF and just inserting the instructions directly.