nihui
171b9d1bba
use spdx license header, copyright Tencent ( #6152 )
10 months ago
nihui
1c7af00499
gemm int8 quantization ( #5706 )
* quantize gemm
* write gemm quantize scales
* update doc
* less openmp args
* x86 riscv fallback
* skip gemm vulkan int8
* fix noint8 test, fix arm bf16 test
* enable vfpv4 on neon build only
* fix gemm vulkan without C
* fp16 pack8 output
* enable elempack=8 only for asimdhp+
* tiled gemm int8 test
* opt arm64 tiles, fix asimdhp dispatch
1 year 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
fed99fd35b
gemm output transpose, prepack c ( #4479 )
* mha is now permute and reshape free
* gemm user defined tile mnk param
3 years ago
nihui
c5640a16c3
gemm x86 multiply alpha beta in post gemm stage, enable one_blob_only ( #4407 )
* gemm x86 multiply alpha beta in post gemm stage, enable one_blob_only
* relax mnk multiple restrictions
* make square tiles in each thread
* sanitize num_threads changes
3 years ago
nihui
fd1ac3c7a0
x86 optimization for gemm unified elempack ( #4387 )
3 years ago
nihui
d42e048b56
pnnx convert torch.addmm ( #3634 )
4 years ago
nihuini
b35b5d7a3c
gemm layer
5 years ago