nihui
db035d602d
update ncnnoptimize layers, lightmode=false keeps original weight ( #5414 )
2 years ago
nihui
556b79ce4d
create layer decoupled ( #5258 )
* create layer decoupled
* no more virtual public
* allow build test with shared library
* decouple cpu vulkan
* drop old scripts
2 years ago
nihui
dba87f8cad
fix build with msvc arm64 asimdhp ( #5176 )
2 years ago
nihui
1133a18ca8
x86 and arm optimization for convolution1d packed unified elempack ( #4615 )
3 years ago
nihui
c471826da1
fix arm bfloat2float float2bfloat oops ( #4439 )
3 years ago
nihui
dd86cebab8
armv8.6 ci and coverage ( #4025 )
* asimdfhm in fc
* move neon bf16 conversion function to arm_usability header
* fix cmake option
* fix build with newer gcc
* arm84 coverage
* arm asimdfhm optimization for innerproduct gemm fp16s
3 years ago
nihui
7886e90c65
split arm82 source for smaller binary and memory footprint ( #3877 )
* split arm82 source, wip
* check compiler arm82 only for arm 64bit target
* drop arm82 registery
* strict check compiler support arm82
4 years ago
nihui
3f2799d706
always build tightly packed weight, fix #3545 ( #3547 )
4 years ago
nihui
c0a94cd9ca
fix armv7 without neon ( #3514 )
4 years ago
nihui
999e640d43
dynamic convolution weight ( #3408 )
4 years ago
nihui
426e564b6e
general simd optimization for convolution1d ( #3404 )
4 years ago