2865 Commits (254eb8d0d4b505ff81fa782aae33893e23b08f0a)
 

Author SHA1 Message Date
  nihui 254eb8d0d4
blacklist fp16a on old adreno driver (#4587) 3 years ago
  nihui 06b97d7e69
fix exynos 9810 isa detection (#4585) 3 years ago
  nihui 5ac17df797
arm optimization for packed convolution unified elempack (#4590) 3 years ago
  nihui 8049623d31
pnnx convert torch.mm (#4589) 3 years ago
  inisis 37042b2174
update build doc for Centos users (#4583) 3 years ago
  dependabot[bot] 2f193ebe8f
Bump pypa/cibuildwheel from 2.12.0 to 2.12.1 (#4568) 3 years ago
  nihui 010d6772d6
softmax arm unified elempack and bf16/fp16 optimization (#4582) 3 years ago
  nihui c777bf09dc
arm convolution sgemm unified elempack (#4572) 3 years ago
  nihui 6987efd950
fix scale avx512 (#4580) 3 years ago
  nihui 693535afc1
pnnx torch 2.0 (#4579) 3 years ago
  Kenji Mouri 47879ea7ea
Add SSE2 implementation of atan in x86 targets. (#4575) 3 years ago
  Kenji Mouri b314b3543d
Add SSE2 implementation of acos in x86 targets. (#4573) 3 years ago
  Kenji Mouri 328d2ca2c4
Add SSE2 implementation of asin in x86 targets. (#4570) 3 years ago
  Yoh 7573faae52
move floor and ceil sse_function from unaryOp to sse_mathfun (#4566) 3 years ago
  wzyforgit 6109669583
Update benchmark of 3A5000 (#4563) 3 years ago
  nihui dabc4c065f
arm convolution winograd unified elempack (#4556) 3 years ago
  nihui 6f08ec7397
use full date for macos pypi package (#4552) 3 years ago
  nihui ae4f630467
pnnx fuse multiheadattention (#4544) 3 years ago
  dependabot[bot] 626aa7cb31
Bump actions/checkout from 2 to 3 (#4550) 3 years ago
  nihui c68266efd0
pnnx eliminate reshape shape expression for only one dynamic dimsize (#4548) 3 years ago
  WuJinxuan ff80ac2955
[ARM] Multiheadattention (#4463) 3 years ago
  nihui bbc770079e
silence fopen error on sysfs cache files 3 years ago
  nihui 6f661f9bc4
Update FAQ-ncnn-throw-error.md 3 years ago
  tpoisonooo 0676684f13
Create CITATION.cff (#4526) 3 years ago
  nihui afc9310c62
update new operators for modelwriter (#4540) 3 years ago
  nihui 3e09196237
ci create release (#4539) 3 years ago
  nihui 47ea2877ed
stb and emsdk update (#4536) 3 years ago
  nihui d0c2738043
update riscv winograd f43 coeffs and fix some warnings (#4537) 3 years ago
  WuJinxuan 6572da3533
[x86] GroupNorm (#4471) 3 years ago
  nihui 833f6ed8e4
c api for getting output indexes and names (#4534) 3 years ago
  nihui 4fc977d7fd
fold scalar constant, write scalar attribute correctly (#4533) 3 years ago
  tuduweb ae45d2860a
Correct README links about build and Add compatibility introduction (#4530) 3 years ago
  nihui 1832da8292
concat 4d (#4528) 3 years ago
  nihui fb9cf7982d
eltwise 4d (#4529) 3 years ago
  nihui 32e2de015e
slice 4d (#4525) 3 years ago
  nihui fc6ce4a641
copyto operator (#4522) 3 years ago
  nihui 242e775d21
pnnx convert torch log10, pow 2 as square (#4518) 3 years ago
  nihui 246e71c526
implement atan2 (#4516) 3 years ago
  Fangjun Kuang 92e75105c9
Support torch.cumsum (#4505) 3 years ago
  nihui ab4cfbf5b0
enrich ncnn binary broadcast rules (#4513) 3 years ago
  Yoh 529c83b8a5
Fuse pixel unshuffle (#4504) 3 years ago
  nihui 6869c81ed3
find cpu cache size from sysfs (#4502) 3 years ago
  nihui 17197b3c45
ci build with musl libc (#4499) 3 years ago
  nihui ce6b80a16b
pnnx flatten input tuple list (#4498) 3 years ago
  向阳 6af0f3777f
Remove redundant include (#4497) 3 years ago
  nihui 3b36656bc8
reduce vulkan winograd f43 transform shader register pressure (#4496) 3 years ago
  nihui dfbcd3e69b
improve vulkan winograd f43 fp16 numerical stability (#4492) 3 years ago
  weirdseed 503a8b921f
fix uninitialized gpu bug_buffer_image_load_zero value (#4493) 3 years ago
  nihui d2d012dce5
x86 bfloat16 cast functions (#4491) 3 years ago
  dependabot[bot] f046181766
Bump pypa/cibuildwheel from 2.11.4 to 2.12.0 (#4477) 3 years ago