* change BeamSearch op to support encoder decoder model
* check model_type and decoder attribute
* fix
* update comments
* warn shape inference issue with onnx v1.11 or T5
* skip parity test when tempature != 1.0
* fix build
* Changes to fuse embed layer for gpt2, kernal changes pending
* verified add output and regular add match
* Test added for additional output embedlayernorm, working on CUDA
* Test passing on CPU
* updated convert_to_onnx toll to check parity correctly
* removed some debugs
* couple of TODO left as in optimizer.py
* removed changes to optimizer.py
* fixing build
* fixing build
* updated order of initilization
* added a test case for float16
* updating the docs
* updating tests failing due to embed layer fusion
* update unit tests
* updating CUDA documentation in operatorkernels.md
* addressing comments
* OperatorKernels.md updated with CUDA
* adding TODO to qembed_layer
* minor edit
* updated docs
* addressing comments
* adding position ids to embed layer gpt2
* updating fused gpt2 model
* added extra test
* remove comments
* addressing comments
* contrib_defs.cc updated
* all tests passing
* fixing a typo
* minor edit
* trigger build
* qembedlayernorm checkinputs updated
* fixing build error
* fixing build error
* fixing build error
```
Component for aggressive decoding. Find the bifurcation index of predicted tokens, between source tokens,
starting from previous suffix match index, and predicted tokens.
Concat predicted tokens, starting from bifurcation index, to the back
of current tokens. This forms the output tokens.
Detect suffix match index in source tokens, between source tokens and output tokens.
Detection is based on finding the appearances of last n-gram in output tokens
in source tokens.
A match is considered found if source tokens contain a single matching n-gram.
Return the index of the start of the n-gram in source tokens.
No matching if found if src tokens contain multiple or zero matching n-grams. Return -1.
```
* bias dropout improvement
* add transform case for same shape case
* combine kernel
* merge with vectorized kernel
* use "has_same_shape_bias"
* minor: a "N % 4 != 0" case
* add op UT for has_same_shape_bias
* address comments; add param case for 1d bias;
add param case tests for 1d and same-shape bias
* rewrite logic condition
Co-authored-by: Peng Wang <pengwa@microsoft.com>
QGemm takes in quantized A, B, C, and quantization parameters of output Y, in which C and quantization parameters of Y are optional. Its output can be quantized or full precision, which depends on whether quantization parameters of Y exists or not. If quant params of Y are provided, the output will be requantized or is full precision.
Comparing with QLinearMatMul and MatMulInteger, QGemm supports transpose, apha and beta attribute.
The formula for quantized GEMM is:
Y = alpha * scale_a * scale_b * ((A_int8 - zp_a) * (B_int8 - zp_b) + C_int32), in which,
C_int32 is quantized with formula: C_int32 = (beta * C) / (alpha * scale_a * scale_b)
SparseTensor support
Implement Builder pattern
Fix support for 1-D and 2-D COO indices
Implement and test CSR support.
Handle shape inference for SparseTensors
Implement conversion for COO, CSR and tests.
Address the case where constant sparse initializer is the output.
Implement test infra for SparseTensors
Implement SparseDenseMatMul for Csr and COO and tested it.
Add hash for SparseToDenseMatMul
Finish shared provider refactor
Refactor GetOrCreate to Create
Working on py interface
Expose OrtDevice and use it in allocate_numpy
Adjust Sparse interfaces, add support for string SparseTensor. Add tests.
Add and test to_cuda()
Add accessors to format specific indices
Test values and indices views, read-only flag, after GC access
Add sparse related methods to OrtValue
Re-work SparseTensor wrapper, add OrtValue methods
Rework numpy_array_to_cuda/to_cpu
Add run_with_ort_values
Add models and test sparse_mat_mul with run_with_ort_values
Refactor sparse tensor to use a single buffer
Ifdef x86 Eigen CSR sparse matmul implementation
Exclude broken test, check for string type when copying cross device
Split pybind schema, regenerate docs, add exclusion
Conditionally exclude schema module
Update docs fix cuda build
Add test to a filter and renerate JS docs
Add conversion and test string support for sparse tensors
Exclude conversion utils from minimal build
Add CUDA Memcpy and adjust provider interfaces
* add Gridsampler contrib op
* fix gridsampler_paddingmode_border test
* disable the tests until the kernel added
* fix CI failure
* change GridSampler to GridSample
* changes working to convert akv nodes
* changes to replace nodes
* changes to accomodate qkv hidden sizes as attributes
* kernel to accept qkv_hidden_size attributes
* Working till compute for varied dimension, todo applyattention()
* changes to make all regression tests work
* inference running successfully without prepack
* success inference with pre-pack weights
* add test for diff sizes
* bias shape need not be a mul of 3
* get the output_hidden_size from input
* infer output shape from input
* merge with master
* cleaning up files that got merged wrong
* accurancy at accepted level
* added unit test case for different dimensions
* all unit tests passing
* packed weights working for attention
* prepacked weights working
* added test case for newly added extra qk input
* updated unit test to test only extra add qk
* fixing build error
* removing few debugs
* reverting test changes
* all python test passing
* cleaning up
* new unit test added, major clean up of code
* removed extra code
* minor
* minor fix to tests
* prepack weights code cleaned up
* compacted compute() in attention.cc
* reformat compute()
* making a parameter T
* adding 3 q,k,v buffers in all cases
* fixing build
* running tests only on cpu
* Updating docs
* trigger ci builds
* Addressing comments in PR
* addressing some more comments
* get add_qk_str from add_qk node directly
* updating docs, added extra check to verify attn inputs
* Optimized the extra add by parallelizing
* added attention_shape to symbolic_shape_infer.py
* minor refactoring to address comments
**Description**:
Enforce no repetition of n-grams. Scores are set to `-inf` for tokens that form a repeated n-gram if added to the back of the input_ids.
**Motivation and Context**
Needed by transformer models in sequence generation algorithms (greedy search and beam search). This module has heavy impact on performance, and can be highly parallelized.
* Update the operator documentation generation
- Make layout a little nicer
- Update to latest supported operators including training
- Fix some links that are broken when the docs content is copied to github-pages
- Fix incorrect usage of 'onnx.ai.ml' as the default domain
- ML ops are now separated from the real default domain of 'onnx.ai'
- Include CPU, CUDA and training kernels
- exclude DNNL as it's not an EP we own
* There are separate paths for CUDA and CUDNN as they are not guaranteed to be in the same location on a Windows machine. Use the CUDNN path when looking for the CUDNN library.
* Enable validation of both contrib ops and operator kernels in build
Filter generation so it's deterministic
Add ability for CI to publish the md files as build artifacts if they differ so a developer can download and add to their PR to resolve any diffs.
Remove workarounds for github-pages as that will now link to the github docs which display correctly
* checkin
* add 4dmask support in attention cuda op
* trim
* add comments
* fix build/test error
* review comments and add tests
* sync doc
* review comments
* minor change
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).
* 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.
* Intial commit
* Rename DynamicPad to Pad
* More changes
* Add Unique operator
* Revert accidental check-in
* Fix CUDA Pad to align with changes
* More changes
* Fix more CUDA pad source files
* More fixes
* More changes
* More changes
* Avoid vector copy
* Update vector validation logic
* Fix build failures
* Fix build
* Fix build failure
* Fix tensorrt build
* add --gen_doc to ci_build
* make gen-doc conditional to build/test step
* some fix in the git diff check
* some more trick on doc diff
* updated for input/output
* updated the contrib operator doc
* fix on missing input output descriptions
* fixed the problem of missing doc string, due to protobuf optimization
* fix
* revert last change
* moved gen_doc.py to /tools/python
* fixed typo
* added tools for doc gen, added doc
* doc updated
* some fixes
* hooked up with build.py
* hooked up with build.py and fail on nonupdated doc
* update
