nihui
|
e9b5bbcd2d
|
fix armv7 roundmode (#3176)
|
4 years ago |
yaobyPerfxlab
|
ec561736a5
|
Riscv64 c906 d1 (#3159)
* Use RVV spec 0.7.1 for C906.
* Fix code style issue.
* Update convolution_sgemm_packn_fp16s.h
RVV_SPEC_0_7 update
* apply code-format changes
Co-authored-by: Zhang Xianyi <xianyi@perfxlab.com>
Co-authored-by: yaobyPerfxlab <yaobyPerfxlab@users.noreply.github.com>
|
4 years ago |
Liuyufanlyf
|
b0f8290657
|
Update RK3328 CPU benchmark (#3164)
|
4 years ago |
nihui
|
d7c8d0d9a2
|
fix coverage glslang (#3158)
|
4 years ago |
nihui
|
51652a2280
|
NCNN_MALLOC_OVERREAD for potential kernel reading data out of allocation size (#3155)
|
4 years ago |
nihuini
|
a99cc13611
|
ncnnoptimize generate proper weight for int8 scales, fix non-neon innerproduct int8, fix #3157
|
4 years ago |
BowShotDS
|
a6667ee6c4
|
Update RK3568 CPU benchmark (#3145)
|
4 years ago |
nihui
|
c6cda8d07c
|
arm neon optimization for requantize leakyrelu (#3144)
* arm neon optimization for requantize leakyrelu
* add missing changes
* Update test_requantize.cpp
* more test coverage
|
4 years ago |
nihui
|
224040e65c
|
Create README.md
|
4 years ago |
nihuini
|
169614f732
|
fix build with NCNN_STDIO off
|
4 years ago |
ncnnnnn
|
b61d4cbd60
|
Update FAQ-ncnn-vulkan.md (#3134)
|
4 years ago |
nihui
|
c1bde160cc
|
recognize xtensa
|
4 years ago |
nihui
|
da7b64b833
|
fix build on c906
|
4 years ago |
nihuini
|
11794675f3
|
apple a11 and a12 do not support armv8.2 dotprod, restore the fp16-only optimized path
|
4 years ago |
nihuini
|
b9460c6e8f
|
fix armv7 requantize relu, fix #3122
|
4 years ago |
Feng Wang
|
ba8e814539
|
chore(examples): add YOLOX to ncnn examples (#3110)
* chore(examples): add YOLOX to ncnn examples
* fix(example): make C++98 happy
* apply code-format changes
* fix(example): fix #287 in yolox
* fix(example): make C++98 happy again
* apply code-format changes
Co-authored-by: FateScript <FateScript@users.noreply.github.com>
|
4 years ago |
Xavier Hsinyuan
|
2a5c672787
|
Add unittest and RVV optimized for SELU (#3114)
|
4 years ago |
Xavier Hsinyuan
|
d78add2acd
|
RVV optimized PReLU, with fp16 support (#3113)
|
4 years ago |
teng
|
413ff2b33b
|
fix typo (#3125)
* Update README.md
* Update how-to-build.md
|
4 years ago |
源源✨
|
e6294455ed
|
add YoloX (#3124)
* Update README.md
* Update README.md
|
4 years ago |
dependabot[bot]
|
dd52ae4a78
|
Bump styfle/cancel-workflow-action from 0.9.0 to 0.9.1 (#3121)
Bumps [styfle/cancel-workflow-action](https://github.com/styfle/cancel-workflow-action) from 0.9.0 to 0.9.1.
- [Release notes](https://github.com/styfle/cancel-workflow-action/releases)
- [Commits](https://github.com/styfle/cancel-workflow-action/compare/0.9.0...0.9.1)
---
updated-dependencies:
- dependency-name: styfle/cancel-workflow-action
dependency-type: direct:production
update-type: version-update:semver-patch
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
|
4 years ago |
nihui
|
f9a16ea1ec
|
fix build on c906
|
4 years ago |
German Novikov
|
21d3ad54cd
|
Added Khadas VIM3 Amlogic A311D benchmark (#3111)
|
4 years ago |
nihuini
|
c5d003001c
|
preserve lstm hidden output
|
4 years ago |
nihuini
|
9afbfdd9dd
|
ncnnoptimize fuse rsub rdiv with scalar
|
4 years ago |
nihuini
|
618f0f70ac
|
fuse 1x1xc broadcasting add into convolution
|
4 years ago |
dependabot[bot]
|
a08707d98d
|
Bump codecov/codecov-action from 2.0.1 to 2.0.2 (#3109)
Bumps [codecov/codecov-action](https://github.com/codecov/codecov-action) from 2.0.1 to 2.0.2.
- [Release notes](https://github.com/codecov/codecov-action/releases)
- [Changelog](https://github.com/codecov/codecov-action/blob/master/CHANGELOG.md)
- [Commits](https://github.com/codecov/codecov-action/compare/v2.0.1...v2.0.2)
---
updated-dependencies:
- dependency-name: codecov/codecov-action
dependency-type: direct:production
update-type: version-update:semver-patch
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
|
4 years ago |
nihui
|
8b0f5e6f8a
|
exclude build cache for test coverage
|
4 years ago |
Xavier Hsinyuan
|
9933cc776a
|
RVV optimized HardSwish and HardSigmoid (#3108)
* RVV optimized HardSwish, with fp16 support
* RVV optimized HardSigmoid, with fp16 support
* apply code-format changes
Co-authored-by: thelastlin <thelastlin@users.noreply.github.com>
|
4 years ago |
Zhiqiang Wang
|
225e0fed44
|
Update openmp installation methods and M1 benchmarks (#3107)
* Update M1 benchmark
* Update openmp installation and use method
* Fixing typo
* And more info about Xcode
|
4 years ago |
nihui
|
d91cccfb55
|
apply code-format changes
|
4 years ago |
Xavier Hsinyuan
|
99440e67f7
|
RVV optimized binaryop, with fp16 support (#3097)
|
4 years ago |
nihuini
|
0f296ee9bf
|
update build tutorial for d1 and ls2k
|
4 years ago |
nihuini
|
29ab8afc0d
|
fix mips32 test coverage
|
5 years ago |
nihuini
|
b62fda6e7c
|
disable runtime cpu for test coverage
|
5 years ago |
nihui
|
2c4ae09604
|
fix #2961 (#3095)
|
5 years ago |
dependabot[bot]
|
1ed6c30940
|
Bump codecov/codecov-action from 1.5.2 to 2.0.1 (#3096)
Bumps [codecov/codecov-action](https://github.com/codecov/codecov-action) from 1.5.2 to 2.0.1.
- [Release notes](https://github.com/codecov/codecov-action/releases)
- [Changelog](https://github.com/codecov/codecov-action/blob/master/CHANGELOG.md)
- [Commits](https://github.com/codecov/codecov-action/compare/v1.5.2...v2.0.1)
---
updated-dependencies:
- dependency-name: codecov/codecov-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>
|
5 years ago |
tsuibin
|
1699aaaca6
|
added support for loongarch64 (#3094)
Co-authored-by: tsuibin <tsuibin@loongson.cn>
|
5 years ago |
nihuini
|
f1533667ff
|
fix test_c_api net instance destroyed earlier than blob destruction
|
5 years ago |
nihuini
|
d7772379d6
|
disable NCNN_AVX for sse2 only build
|
5 years ago |
nihuini
|
affbefe311
|
some space cleanup, blob clone from allocator
|
5 years ago |
neos
|
63664771cf
|
Update jetson agx benmark (#3093)
|
5 years ago |
lsdustc
|
61af40cfbd
|
Fix Innerproduct gemm forgot to add an offset of w in int8 forward (#3084)
|
5 years ago |
nihui
|
dba7348f17
|
add loongson 2k1000 benchmark
|
5 years ago |
zhiliu6
|
190207a173
|
fix AVX2 compiled as AVX problem (#3090)
|
5 years ago |
nihui
|
052b2a1653
|
apply code-format changes
|
5 years ago |
chenxiemin
|
9bd8a50b96
|
fix vulkan memory leak issue (#3088)
|
5 years ago |
zhiliu6
|
c6bb70622b
|
fix convolution padding when pad=0 (#3087)
|
5 years ago |
nihui
|
a2844bbf6c
|
Update build-minimal-library.md
|
5 years ago |
nihui
|
cdf45a6512
|
cmake option NCNN_BF16 (#3068)
|
5 years ago |