Resize is spec'd to ignore the "roi" tensor in certain modes. For some reason, converters are specifying an arbitrary value for this tensor, even though it's optional.
This makes the graph partitioner skip a check for empty shape dimensions for tensors such as this, which the DML kernel registers as consuming as CPU inputs. Otherwise, the node is not included in DML graph partitions, because the DML graph doesn't handle empty dimensions.
Related work items: #32221164
A model from one of our partners regressed with a failure to evaluate due to the addition of strided 64-bit emulation in the DML EP for the Cast operator. Specifically, the model uses a Cast from int32 to int64 to produce the input shape to a Reshape node. When supplied with a shape dimension of -1 (int32 0xffffffff), the strided emulation in Cast ends up producing an int64 result of 0x00000000ffffffff. This is then fed into the Reshape operator, where it produces an incorrect tensor shape and a failure during evaluation.
Generally speaking we assume that using strided 64-bit emulation is safe if a node's inputs came from the DML EP itself. This isn't true in the general case for Cast, however - casting negative signed values can and will produce incorrect outputs with strided emulation.
After this change, Cast nodes with 64-bit types will fall back to CPU unless running on a GPU that native supports 64-bit datatypes.
Related work items: #31768166
* Include ORT format model conversion scripts and infrastructure in ORT python package.
- tweak existing script setup so it can be easily run directly and from the ORT python package
Add config file and readme for Android minimal build package
Update ORT Mobile doco
Disable warning if 'all' optimizations are enabled but NCHWc transformer is excluded (device specific optimizations don't apply in this scenario so the warning is moot).
* Address PR comments
fix crash when DeQuantizeLinear's output is graph output
propagate only when scale and zp are scalar.
fix bug for is_modified= is_modified || TryCancelOutDQQPair(graph, dq_node, q_node); in which TryCancelOutDQQPair wouldn't be invoked if is_modified is true
* check in early stop search as separate type
* rename to beam search configurations
* update do sample configuration flag help
* rename to configurable search step
* add option groups
* add more unit tests
Co-authored-by: Xiaoyu Liu <xiaoyu@xiaoyu-VM.z4vh1dzj5eoevgybsksdpz2izh.jx.internal.cloudapp.net>
This patch helps to set architecture as power, when processor
check output matches ppc64le*.
Co-authored-by: Rajalakshmi Srinivasaraghavan <rajis@linux.ibm.com>
**Description**:
- Fix SequenceInsert with last position, which is equal to the current sequence length.
- Implement Identity to support sequence input for opset 14.
**Motivation and Context**
- Required to export Huggingface/transformers T5 with beam search.
* Update symbolic_shape_infer.py
don't rely on static code infer in _infer_Squeeze_
* checking if dorpped axes might be =! 1
* Checking opset. Logging assumption that symbolic dimensions are unequal to 1.
* more checks
* LayerNorm function body v1
* LayerNorm function body
* layernorm function test
* Minor fixes
* Fix signed unsigned comparison
* Move contrib ops test
* Handle optional output parameters
* Add test case for optional outputs
* Handle float16 random generation
* Address PR feedback
Implement various improvements related to reordering a tensor for use by NCHWc operations:
Relax the requirement that the input channel count must be a multiple of the NCHWc block size (either 8 or 16 depending on ISA). The requirement now is that the channel count must be a multiple of 4. The implementation of MlasReorderInputNchw would need further work to support relaxing this further, but I don't have any models where I've observed this to be necessary yet.
Support fusing a Transpose(NHWC->NCHW) into a following ReorderInput. ReorderInput now has a channels_last attribute as was done in the past for ReorderOutput. This helps with models converted from TF where the converter is unable to remove all Transpose operations.
Add threading support to ReorderInput to accelerate performance (ReorderOutput will come later).
* wait for dispatch done in RunParallelSection
* pass worker_fn by value
* cancel move
* only move work_fn when it is lastly referred
Co-authored-by: Randy Shuai <rashuai@microsoft.com>
* Implement qlinear concat and unit test.
Add quantization tools for QLinearConcat and it quantization tests.
* Add kernel def hash for QLinearConcat.
* Change according to PR. Add qdq transformer support for QLinearConcat.
* Add QDQ Transformer unittest. Fix typo on domain.
* remove dup logic of no use.
* fix x86 build error.
* Update operator docs.
