Yufeng Li 6f86c4dbe3 Quantize LSTM (#5595) ... Quantize LSTM: 1. dynamically quantizes MatMul inside the LSTM. It doesn't quantize activation function. 2. support per-channel on the input weight and recurrent weight.		2020-11-18 11:21:49 -08:00
..
featurizer_ops	Update data_frame_tool to latest (#3919)	2020-05-18 21:13:56 -07:00
quantization	Quantize LSTM (#5595)	2020-11-18 11:21:49 -08:00
tensorrt/perf	Tensorrt perf tool (#5436)	2020-11-06 12:27:42 -08:00
transformers	Revert saving optimized model as external data (#5690)	2020-11-06 11:54:19 -08:00
__init__.py	Enable running PEP8 on python scripts using flake8 (#3928)	2020-05-15 07:15:06 +10:00
onnxruntime_test.py	Improve handling of symbolic dimensions in the onnxruntime_test.py script. (#3959)	2020-05-18 16:51:09 +10:00
symbolic_shape_infer.py	Some fixes to symbolic shape inference (#5642)	2020-10-30 19:28:47 -07:00