nihui
|
c3adbcf9f3
|
mips optimization for convolution sgemm (#3853)
* mips optimization for convolution sgemm
* mips optimization for general convolution int8 gemm
* mips optmization for convolution winograd pack1
* preload magic
|
4 years ago |
nihui
|
a5bcc8895f
|
armv5 optimization for convolution sgemm (#3852)
|
4 years ago |
nihui
|
50d04dee30
|
optimize sgemm and winograd remain size register layout (#3851)
|
4 years ago |
nihui
|
0a4f50dbf4
|
arm neon assembly optimization for innerproduct unroll outch 4 (#3848)
|
4 years ago |
nihui
|
569ee37c52
|
arm neon optimization for pooling bf16s, fix some bf16s packing issue, relax winograd transform intrinsic order (#3847)
|
4 years ago |
dependabot[bot]
|
781145f15b
|
Bump pypa/cibuildwheel from 2.5.0 to 2.6.0 (#3844)
Bumps [pypa/cibuildwheel](https://github.com/pypa/cibuildwheel) from 2.5.0 to 2.6.0.
- [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/2.5.0...2.6.0)
---
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>
|
4 years ago |
nihui
|
e49f0226e1
|
multi-threading rnn/lstm/gru with openmp (#3834)
|
4 years ago |
FeiGeChuanShu
|
02107e0fbf
|
fix yolox input shape w!=h (#3839)
|
4 years ago |
nihui
|
e7a664c6e5
|
convert pnnx torch.index_select and torch.scatter_add (#3842)
|
4 years ago |
nihui
|
02a7e64e18
|
optimize x86 winograd input transform transpose (#3818)
* optimize x86 winograd input transform transpose
* x86 sse2/avx optimization for convolution winograd23/43 pack1
|
4 years ago |
Yoh
|
2a05c69cdd
|
fix x86 unaryop bug on gcc-4.4 (#3838)
|
4 years ago |
nihui
|
4c7965781f
|
add pnnx ncnn pass for chain dict output (#3836)
* chain dict output
* recognize sub_
|
4 years ago |
nihui
|
f48d45209b
|
binaryop type specialization (#3830)
|
4 years ago |
nihui
|
026a04f220
|
convert torch.norm to ncnn, fix F.normalize vector (#3828)
|
4 years ago |
tripleMu
|
6f4b444fe5
|
Fix .gitignore (#3824)
|
4 years ago |
nihui
|
bf64d8f1ec
|
fix winograd function name (#3820)
|
4 years ago |
陸 言
|
2161ab2a0c
|
Edit _bias128 in scale_x86.cpp for useless if (#3821)
|
4 years ago |
nihui
|
c16cac2678
|
update glslang, fix system glslang include path (#3819)
|
4 years ago |
nihui
|
9e11dac7d1
|
simpleomp with libgomp abi (#3816)
|
4 years ago |
BUG1989
|
c2fb93b6ff
|
Add the benchmark of AX620A (#3813)
|
4 years ago |
nihui
|
f79073c182
|
update how-to-build doc for raspberrypi and d1
|
4 years ago |
FeiGeChuanShu
|
617d23f6ce
|
Add RK3588 benchmark (#3808)
|
4 years ago |
nihui
|
3a827434a9
|
optimize arm sgemm convolution condition (#3806)
|
4 years ago |
nihui
|
0daad605e0
|
fix make slice expression with dynamic parameters
|
4 years ago |
wzyforgit
|
46a6d9b422
|
Add Loongson and Sunway benchmark data (#3802)
|
4 years ago |
nihui
|
5cdb7f6617
|
make compiler optimization happy with loop (#3799)
|
4 years ago |
tpoisonooo
|
6fd801b6d7
|
feat(src/layer): add vision_transformer benchmark (#3730)
* feat(src/layer): add vision_transformer benchmark and relative layer
* refactor(testutil.h): add para for RandomMat
|
4 years ago |
nihui
|
817bd1fdc4
|
fix vs2022 ci (#3792)
|
4 years ago |
Xavier Hsinyuan
|
29b6a32ac0
|
RVV: follow intrinsic doc, replace vfredsum_* with vfredusum_* (#3790)
* RVV: follow intrinsic doc, vfredusum -> vfredsum
* C906: change toolchains for vfredusum
* RVV: test compiler for vfredusum_vs_*
|
4 years ago |
nihui
|
2dc1ae45fe
|
pnnx bitwise and compare op (#3791)
* bitwise and compare op
* masked_fill and gather test
|
4 years ago |
nihui
|
d476191ff1
|
pnnx export_onnx function (#3784)
|
4 years ago |
nihui
|
0aba8af1d3
|
pnnx swin transformer (#3783)
|
4 years ago |
村长大人
|
c697e988b0
|
fixbug: linux-arm-hisiv500 load mem "Bus error" (#3779)
|
4 years ago |
Zhiqiang Wang
|
a7aa0fe70d
|
Update README.md (#3778)
|
4 years ago |
Zhuo Zhang
|
3dfc10647c
|
docs: update QQ group info (#3777)
|
4 years ago |
NaLan ZeYu
|
5388f9f312
|
test: fix printf arguments mismatch (#3774)
|
4 years ago |
jasonZhang
|
663b42e0d2
|
add tanh avx512 optimize (#3770)
|
4 years ago |
nihui
|
f9c1787de9
|
implement einsum layer and pnnx conversion (#3768)
|
4 years ago |
jasonZhang
|
c34e305902
|
Add SSE&AVX optimized for tan (#3765)
|
4 years ago |
nihui
|
ee6402553c
|
layernorm for vector and mat along w, pnnx convnext end2end test (#3764)
|
4 years ago |
nihui
|
318dc4f5f5
|
convert Tensor.select to ncnn, fuse multiheadattention unpack, add vit_b_32 end2end test (#3763)
|
4 years ago |
nihui
|
b516485528
|
update ci qemu (#3756)
* update ci qemu
* update rvv qemu args
* fix bus error on armv7
* apply downstream qemu patches
|
4 years ago |
dependabot[bot]
|
2f2e678cce
|
Bump docker/setup-qemu-action from 1 to 2 (#3761)
Bumps [docker/setup-qemu-action](https://github.com/docker/setup-qemu-action) from 1 to 2.
- [Release notes](https://github.com/docker/setup-qemu-action/releases)
- [Commits](https://github.com/docker/setup-qemu-action/compare/v1...v2)
---
updated-dependencies:
- dependency-name: docker/setup-qemu-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>
|
4 years ago |
nihui
|
a2b25c88b0
|
pnnx convert torch.einsum (#3744)
* normalize einsum equation
* replace dot pair with alphabet word
* shorten permute equation
|
4 years ago |
841973620
|
a2e25d3fd3
|
fix Multiplication result may overflow 'int' before it is converted to 'size_t'. (#3757)
|
4 years ago |
jasonZhang
|
e62d674e5d
|
Add unittest and SSE&AVX optimized for BNLL (#3759)
|
4 years ago |
nathannaveen
|
d7cc08b54a
|
chore: Set permissions for GitHub actions (#3758)
Restrict the GitHub token permissions only to the required ones; this way, even if the attackers will succeed in compromising your workflow, they won’t be able to do much.
- Included permissions for the action. https://github.com/ossf/scorecard/blob/main/docs/checks.md#token-permissions
https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#permissions
https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs
[Keeping your GitHub Actions and workflows secure Part 1: Preventing pwn requests](https://securitylab.github.com/research/github-actions-preventing-pwn-requests/)
Signed-off-by: nathannaveen <42319948+nathannaveen@users.noreply.github.com>
|
4 years ago |
dependabot[bot]
|
1634de33df
|
Bump pypa/cibuildwheel from 2.4.0 to 2.5.0 (#3755)
Bumps [pypa/cibuildwheel](https://github.com/pypa/cibuildwheel) from 2.4.0 to 2.5.0.
- [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/v2.4.0...2.5.0)
---
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>
|
4 years ago |
nihui
|
615d63e6a1
|
use single thread in ci swiftshader (#3754)
|
4 years ago |
nihui
|
40c50f198b
|
move linux gpu ci to cvm2 (#3750)
|
4 years ago |