Commit Graph

15 Commits (8f2656ef5ca4ab16f06d94b8ca9392d3f0f760ae)

Author SHA1 Message Date
cc 8fabb1c32f
Add test attribute in channelwise_quant op, test=develop (#27742)
5 years ago
huangxu96 02606d45ef
Quant op dev (#25932)
5 years ago
cc 3f816bc8b4
[Quantization] Conv2d_transpose and mul support channnelwise quantization (#25639)
5 years ago
cc 42189be67b
[Quant] Remove the output for moving_average_abs_max_scale op (#25697)
5 years ago
Zhen Wang bb45af02ac
add the c++ part of Imperative QAT. test=develop (#25446)
5 years ago
Liufang Sang 915b892a15
Fix div zero in fake quantize op (#22966)
5 years ago
Huihuang Zheng 12542320c5
Replace TemporaryAllocator by CUDADeviceContextAllocator (#18989)
6 years ago
Zhaolong Xing ff7f911b4d
add quant_dequant_moving_avg_max_abs op (#17480)
6 years ago
Zhen Wang a914d9b116
Quant output scale (#17215)
6 years ago
Zhen Wang 8965819fbb rewrite the cuda kernels of channel_wise_quant_op and channe_wise_dequant_op. test=develop
6 years ago
Zhen Wang ec88b6cc5a add channel wise quantization in ir pass.
6 years ago
achao2013 81b4fad8b9 add moving average absmax op and fix bug (#15155)
6 years ago
Zhen Wang 545247d7b4 add channel wise quantize op.
6 years ago
qingqing01 9bd933d3fb
Improve and fix fake_quantize_op (#13092)
7 years ago
achao2013 8e4b225fe4 Add fake_quantize_op. (#11359)
7 years ago