nihui
05ad0c52c6
pnnx fuse gelu ( #4702 )
3 years ago
nihui
490816b21b
update ios toolchain, simulator arm64 ci, mac catalyst ci ( #4697 )
3 years ago
Zhang Geng
2b1feaf82b
Update VF2 score ( #4688 )
3 years ago
nihui
a37a83d850
clip gelu mish tanh 4d ( #4695 )
3 years ago
Zhang Geng
9fe7fc8159
Update loongson 3a4000 test score ( #4691 )
3 years ago
Zhang Geng
61a7e7204e
Update FT2000/4 scores ( #4689 )
3 years ago
Zhang Geng
62da373d4b
Added RK3399,RK3588s (op4lts,op5) ( #4687 )
3 years ago
nihui
cd5a6098a2
sigmoid and swish 4d ( #4692 )
3 years ago
Hillwood Yang
d878f0e16d
Fix build by gcc 13 ( #4684 )
3 years ago
nihui
72a3e5141f
fix vulkan validation error, prefer VK_KHR_buffer_device_address over VK_EXT_buffer_device_address ( #4680 )
3 years ago
nihui
c28c8c04a1
multiheadattention attn mask ( #4668 )
3 years ago
zhiliu6
125b9f2baf
reduce double usage ( #4671 )
3 years ago
Zhuo Zhang
737a114242
fix typo in PNNX readme ( #4670 )
3 years ago
Zhuo Zhang
c07ff1ce4f
fix typo in PNNX groupnorm error message ( #4669 )
3 years ago
nihui
b640574b88
rough vulkan gemm and multiheadattention ( #4618 )
3 years ago
Yukie
3a64083756
Fix spelling errors, ncn -> ncnn. ( #4665 )
3 years ago
mizu-bai
ae1e73f14a
Add Intel oneAPI 2023.1.0 Results ( #4664 )
3 years ago
He Yang
f9180330e2
update how-to-build.md and delete obsolete tutorials in docs ( #4660 )
3 years ago
Yoh
bd15e32517
move x86 abs_mathfun to x86_mathfun ( #4659 )
* move x86 abs_mathfun to x86_mathfun
* Improve the implementation of AVX and AVX512F abs.
* Unified naming rules
---------
Co-authored-by: MouriNaruto <Mouri_Naruto@Outlook.com>
3 years ago
Chen Xin
9fe843fa39
fix wrong param id of Squeeze for modelwriter ( #4658 )
3 years ago
lrzlin
8adf3686b8
add benchmark of loongson 2k1000la ( #4656 )
3 years ago
nihui
e006aa8007
fix extension not present error ( #4655 )
3 years ago
dependabot[bot]
8e445bfde8
Bump pypa/cibuildwheel from 2.12.2 to 2.12.3 ( #4651 )
Bumps [pypa/cibuildwheel](https://github.com/pypa/cibuildwheel ) from 2.12.2 to 2.12.3.
- [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/v2.12.2...v2.12.3 )
---
updated-dependencies:
- dependency-name: pypa/cibuildwheel
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>
3 years ago
nihui
f7af84f001
pnnx reset maxpool return_indices if only output found, drop convtransposed output_size arg for static output padding ( #4654 )
3 years ago
nihui
3c6f6e4b2b
update swiftshader ( #4650 )
3 years ago
triple Mu
544adbb051
Fix destory in gpu ( #4653 )
3 years ago
Kenji Mouri
f2a5a81a5d
Add AVX512F implementation of atan2 in x86 targets. ( #4641 )
3 years ago
He Yang
9a5b6ce20e
fix fprintf type mismatch. ( #4647 )
3 years ago
triple Mu
e36dbdfd93
Fix core dump in benchmark ( #4648 )
3 years ago
dependabot[bot]
3462a2675b
Bump pypa/cibuildwheel from 2.12.1 to 2.12.2 ( #4643 )
Bumps [pypa/cibuildwheel](https://github.com/pypa/cibuildwheel ) from 2.12.1 to 2.12.2.
- [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/v2.12.1...v2.12.2 )
---
updated-dependencies:
- dependency-name: pypa/cibuildwheel
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>
3 years ago
nihui
a2106f840f
setup more extension entrypoint ( #4636 )
3 years ago
nihui
91cc508a23
pnnx recognize foldable scalar and fuse it into expression ( #4639 )
3 years ago
Kenji Mouri
d802acd205
Add SSE and AVX implementation of atan2 in x86 targets. ( #4633 )
3 years ago
nihui
5b5e9ea537
fix some pnnx build warnings ( #4634 )
3 years ago
nihui
f8e32aba9c
fix pnnx gru rnn with optional output, fix #4608 ( #4631 )
3 years ago
張小凡
d87e895a1f
Add get_gpu_instance() function and Organized the instance class codes. ( #4630 )
3 years ago
nihui
8066c76bc5
pnnx complex data type and torch.stft family ( #4627 )
3 years ago
Darren Cheng
176f8e12cb
remove platform.h.in aarch64 judgment ( #4628 )
3 years ago
張小凡
772b13a1d1
Add three extension capability support check ( #4626 )
* Add some extension capability for vma
3 years ago
Kenji Mouri
1936142aae
Add AVX and AVX512F implementation of asin, acos and atan in x86 targets. Fix typo for SSE2 implementation of asin in x86 targets. ( #4621 )
3 years ago
caofx0418
643107533a
fix errors while build in Android Open Source Code ( #4622 )
3 years ago
Kenji Mouri
5ca5209cd5
Add FMA optimization for SSE2 implementation of asin, acos and atan in x86 targets. ( #4620 )
3 years ago
AlOa
22e86402f7
Read image from memory buffer for simpleocv ( #4557 )
3 years ago
nihui
db628b1b99
allow overwriting built-in layer with custom layer ( #4616 )
3 years ago
nihui
1133a18ca8
x86 and arm optimization for convolution1d packed unified elempack ( #4615 )
3 years ago
張小凡
868ea52bea
update faq.md about gpu performance ( #4614 )
3 years ago
nihui
85991e2e0e
test custom option, update ci ( #4609 )
* early return for cpu test
* make nvidia driver happy
* fix gemm x86 threading
3 years ago
nihui
f34becf6fc
fix divide by zero in get optimal tile size mnk ( #4610 )
3 years ago
nihui
2ce77ba918
fix mha gemm allocator race ( #4611 )
3 years ago
nihui
804ac3421d
infrastructure and optimization for a53 and a55 ( #4596 )
* new api for detecting arm midr and a53 a55 arch info wrapper
* let a35 be a53 :P
* a53 bf16s
* detect running core
3 years ago