Conv perlayer int8 quantization (#471)

* Add conv2d requant example

* Fix bash error

* Rename example

* 1. Rename gemm quantization
2. shares the requantization lambda function with conv

* Refine declare type

* Add conv bias relu quantization exmaple

* clang format

* Fix compile error due to merge develop

* Fix CI error

* Extract quantization post operation into another file

* Support quantization for non piecewise linear function

* Add instance for conv quantization

* Add convolution quantization factory

* Add convolution quantization client example

* Add more instances with different template parameters

* clang format

* Sync the naming with the develop
This commit is contained in:
rocking5566
2022-11-03 03:56:26 +08:00
committed by GitHub
parent 8ee36118be
commit 226bc02b73
20 changed files with 1553 additions and 35 deletions

View File

@@ -0,0 +1,5 @@
add_executable(client_conv2d_fwd_bias_relu_perlayer_quantization conv2d_fwd_bias_relu_perlayer_quantization.cpp)
target_link_libraries(client_conv2d_fwd_bias_relu_perlayer_quantization PRIVATE composable_kernel::device_operations)
add_executable(client_conv2d_fwd_perlayer_quantization conv2d_fwd_perlayer_quantization.cpp)
target_link_libraries(client_conv2d_fwd_perlayer_quantization PRIVATE composable_kernel::device_operations)