ningjiang233
b2f12fdd67
delete useless setences ( #5139 )
2 years ago
nihui
31e315981a
watchos and tvos ci ( #5124 )
2 years ago
nihui
39bc71c941
support big endian platform, add powerpc ci ( #5121 )
2 years ago
nihui
4494aadd74
deconvolution dynamic weight ( #5119 )
2 years ago
mizu-bai
c96bc08307
Add OneCloud Amlogic S805 ( #5120 )
2 years ago
Justin Fung
009f5eae97
Add description of build for Nintendo 3DS homebrew launcher ( #5116 )
2 years ago
nihui
6c6c40edb3
fix deconvolution x86 unaligned bias load ( #5112 )
2 years ago
teng
16524ca937
pnnx fix indent errors ( #5113 )
2 years ago
nihui
37a108c4c4
pnnx run test_inference by default ( #5110 )
2 years ago
nihuini
c2ccbf851d
pnnx fix filename base
2 years ago
nihui
3116e028d2
pnnx drop sdap scale=None for compatiblity with old torch ( #5107 )
2 years ago
nihui
14e14a9ae8
slice with indices ( #5103 )
2 years ago
nihui
3eb2969db9
fix build with ohos toolchain ( #5105 )
2 years ago
nihui
9dda7e385a
fix gridsample x86 warnings ( #5096 )
2 years ago
nihui
7afdbfa680
simplify vulkan conv1d ( #5095 )
2 years ago
nihui
efcfe95a42
pnnx do not sanitize directory part ( #5099 )
2 years ago
nihui
0c2a4a29de
pnnx convert batchnorm function ( #5097 )
2 years ago
nihui
54ab8051e3
fix warnings ( #5094 )
2 years ago
邓实诚
a1e3ebf8e5
implement simplemath ( #4905 )
* complete abs, fmod and sin function in simplemath.h
* remove some unused variables in simplemath.cpp
* modify test-coverage.yml and add some functions to simplemath.cpp
* modify erf.cpp which included math.h
* include platform.h for NCNN_SIMPLEMATH definition
* move utility constants and functions in simplemath.h to simplemath.cpp
* guard simplemath functions with extern "C"
* add NCNN_EXPORT macro in simplemath.h
* include plateform.h and guard all declarations with NCNN_SIMPLEMATH
* clean unused code in test_unaryop.cpp
* guard #include <vector> with NCNN_SIMPLEMATH in benchncnn.cpp
* add 'static' to guard functions that not declarated in header file
* modify sin and cos with better implementation
---------
Co-authored-by: HonestDeng <HonestDeng@users.noreply.github.com>
2 years ago
Zhenyu ZHAO
a6decad15d
Python ncnn with vulkan ( #5020 )
* add option for enabling vulkan in setup.py
* load winograd type options for pybind.
* enable the usage of humbletim/install-vulkan-sdk in ci
* vulkan-loader with release build
* python setup.py install --vulkan=on
* moltenVK for x86_64 macos
* remove universal2 temporarily
2 years ago
nihui
80b3b9c6f0
arm optimization for convolution int8 winograd unified elempack ( #5087 )
* enable out elempack 8 for winograd and sgemm
2 years ago
Yoh
3f437d3f3d
Grid sample op ( #4373 )
* pnnx support grid_sample op
* complete the permute and gridsample operator fusion
* spilt calculation into two stages and support permute fusion
2 years ago
FhqTreap
dc25128195
Vulkan conv1d ( #5060 )
2 years ago
張小凡
84aaedbe96
Added 5 devices(AMD*2, Intel*2, NVIDIA*1) benchmark result. ( #5085 )
2 years ago
Xinyu302
b82d395753
Add riscv float32 gemm ( #4903 )
Co-authored-by: Xinyu302 <Xinyu302@users.noreply.github.com>
2 years ago
佰阅
bcdc276ffe
add torch.view_as_real and torch.view_as_complex ( #5083 )
2 years ago
nihui
3f79c4ff10
Update labeler.yml
2 years ago
nihui
2f1f2e9770
fix labeler
2 years ago
nihui
97ffd1e661
add labeler ( #5078 )
2 years ago
nihui
7b02425246
x86 optimization for convolution int8 winograd unified elempack ( #5054 )
2 years ago
青菜萝卜冬瓜
d1289fb12d
benchmark: add RTX A3000 6G benchmark ( #5070 )
2 years ago
nihui
bedbe599ff
pnnx support torch-2.1 ( #5074 )
2 years ago
張小凡
b4f8fa6d38
Fixed _mm256_set_m128 is only availble on gcc8+. issue#5072 ( #5075 )
2 years ago
dependabot[bot]
c8f92b9f38
Bump stefanzweifel/git-auto-commit-action from 4 to 5 ( #5073 )
Bumps [stefanzweifel/git-auto-commit-action](https://github.com/stefanzweifel/git-auto-commit-action ) from 4 to 5.
- [Release notes](https://github.com/stefanzweifel/git-auto-commit-action/releases )
- [Changelog](https://github.com/stefanzweifel/git-auto-commit-action/blob/master/CHANGELOG.md )
- [Commits](https://github.com/stefanzweifel/git-auto-commit-action/compare/v4...v5 )
---
updated-dependencies:
- dependency-name: stefanzweifel/git-auto-commit-action
dependency-type: direct:production
update-type: version-update:semver-major
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2 years ago
dependabot[bot]
54a9a563e9
Bump pypa/cibuildwheel from 2.15.0 to 2.16.2 ( #5064 )
Bumps [pypa/cibuildwheel](https://github.com/pypa/cibuildwheel ) from 2.15.0 to 2.16.2.
- [Release notes](https://github.com/pypa/cibuildwheel/releases )
- [Changelog](https://github.com/pypa/cibuildwheel/blob/main/docs/changelog.md )
- [Commits](https://github.com/pypa/cibuildwheel/compare/v2.15.0...v2.16.2 )
---
updated-dependencies:
- dependency-name: pypa/cibuildwheel
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2 years ago
daquexian
75ad1cc749
support tag in memorydata layer ( #5061 )
Signed-off-by: daquexian <daquexian566@gmail.com>
2 years ago
Baozhu Zuo
f38fc95e0c
benchmark: add raspberry pi 5 8G benchmark ( #5058 )
2 years ago
Marsyule
69d6051850
add F_pairwise_distance to pnnx and ncnn ( #4942 )
2 years ago
FhqTreap
1d7720efe8
fix test conv1d ( #5049 )
2 years ago
nihui
26a70c9b05
fix build with vanilla c906 toolchain ( #5048 )
2 years ago
nihui
78aca88d67
elu 4d and selu 4d ( #5047 )
2 years ago
nihui
b8d5a5dbec
pnnx fuse conv3d-bn and deconv3d-bn ( #5045 )
2 years ago
Beq Jal
019176c6b2
selu and shufflechannel on x86 ( #5017 )
2 years ago
nihui
fdf2c482dc
fuse adaptive pool dynamic output size, implement ncnn adaptive pooling dynamic outsize ( #5043 )
2 years ago
Amir Ramezani
7e5fa3ade3
shrink operator ( #5022 )
2 years ago
柚木 鉉
0ddc34f522
[benchmark] Add Allwinner T527 benchmark ( #5040 )
2 years ago
FhqTreap
a12a14f3a6
Gelu afp fix ( #5039 )
2 years ago
Shu Liqiang
a2103be55d
support ReplicationPad3d to ncnn ( #4919 )
2 years ago
nihui
f412b7f5c4
fix issue 5025
improve reflect replicated pad pattern
2 years ago
nihui
c8662cce5e
arm optimization for convolution int8 gemm unified elempack ( #5016 )
2 years ago