nihui
171b9d1bba
use spdx license header, copyright Tencent ( #6152 )
2025-07-08 11:01:29 +08:00
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
2024-10-12 19:02:55 +08:00
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
2024-01-05 14:08:15 +08:00
nihui
fed99fd35b
gemm output transpose, prepack c ( #4479 )
...
* mha is now permute and reshape free
* gemm user defined tile mnk param
2023-01-27 13:03:04 +08:00
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
2022-12-12 19:21:17 +08:00
nihui
fd1ac3c7a0
x86 optimization for gemm unified elempack ( #4387 )
2022-12-10 17:36:50 +08:00
nihui
d42e048b56
pnnx convert torch.addmm ( #3634 )
2022-03-18 12:24:05 +08:00
nihuini
b35b5d7a3c
gemm layer
2020-08-17 20:12:15 +08:00
nihui