Anton Korablin 207c57219a Add support for full ViT optimization (#15289) ... Add support for ViT optimization in optimizer.py As ViT architecture follows BERT rather closely, we can easily reuse BERT fusions for ViT. The only difference is that ViT does not have attention mask, which means there is no Add node in qk paths. Make the necessary changes in onnx_exporter.py to be able to cover optimizations with test.		2023-04-04 14:05:24 -07:00
..
custom_op_wrapper	Custom Op runtime wrapper (#13427)	2023-01-18 09:09:32 -08:00
kernel_explorer	Adopt linrtunner as the linting tool - take 2 (#15085)	2023-03-24 15:29:03 -07:00
microbench	Adopt linrtunner as the linting tool - take 2 (#15085)	2023-03-24 15:29:03 -07:00
profile_explorer	Adopt linrtunner as the linting tool - take 2 (#15085)	2023-03-24 15:29:03 -07:00
quantization	Enable pylint and numpy rules (#15218)	2023-03-27 20:37:53 -07:00
tensorrt/perf	Enable pylint and numpy rules (#15218)	2023-03-27 20:37:53 -07:00
transformers	Add support for full ViT optimization (#15289)	2023-04-04 14:05:24 -07:00
__init__.py	Enable running PEP8 on python scripts using flake8 (#3928)	2020-05-15 07:15:06 +10:00
offline_tuning.py	Adopt linrtunner as the linting tool - take 2 (#15085)	2023-03-24 15:29:03 -07:00
onnx_randomizer.py	Format all python files under onnxruntime with black and isort (#11324)	2022-04-26 09:35:16 -07:00
onnxruntime_test.py	Adopt linrtunner as the linting tool - take 2 (#15085)	2023-03-24 15:29:03 -07:00
pytorch_export_contrib_ops.py	Adopt linrtunner as the linting tool - take 2 (#15085)	2023-03-24 15:29:03 -07:00
symbolic_shape_infer.py	Add tool to support packing mode for BERT model (#15283)	2023-03-31 08:46:47 -07:00