2918 Commits (05ad0c52c6cfe91bf550adcd4ed3467beffbd0df)
 

Author SHA1 Message Date
  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) 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) 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) 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) 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) 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) 3 years ago