You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

arlesniak d31a174f51 added fusing matmul-transpose-reshape pass (#23866)		6 years ago
..
__init__.py	separated QAT1 and QAT2 (#23284)	6 years ago
mkldnn_post_training_strategy.py	clean up intel labeled TODOs (#19476)	7 years ago
post_training_quantization.py	Weight quantization support channel_wise_abs_max method to achieve higher accuracy (#23629)	6 years ago
qat2_int8_mkldnn_pass.py	added fusing matmul-transpose-reshape pass (#23866)	6 years ago
qat_int8_mkldnn_pass.py	separated QAT1 and QAT2 (#23284)	6 years ago
quantization_pass.py	Collect output scale for quantized op and fused op (#23369)	6 years ago
quantization_strategy.py	fix fuse_reduce_op quantization bug (#20306)	7 years ago