318 Commits (b2f12fdd67220a37895e8f03f22c8e76bb84dddd)

Author SHA1 Message Date
  nihui 4494aadd74
deconvolution dynamic weight (#5119) 2 years ago
  nihui 14e14a9ae8
slice with indices (#5103) 2 years ago
  邓实诚 a1e3ebf8e5
implement simplemath (#4905) 2 years ago
  Yoh 3f437d3f3d
Grid sample op (#4373) 2 years ago
  nihui 7b02425246
x86 optimization for convolution int8 winograd unified elempack (#5054) 2 years ago
  FhqTreap 1d7720efe8
fix test conv1d (#5049) 2 years ago
  nihui 78aca88d67
elu 4d and selu 4d (#5047) 2 years ago
  Beq Jal 019176c6b2
selu and shufflechannel on x86 (#5017) 2 years ago
  Amir Ramezani 7e5fa3ade3
shrink operator (#5022) 2 years ago
  nihui c8662cce5e
arm optimization for convolution int8 gemm unified elempack (#5016) 2 years ago
  Amir Ramezani 0ea587b8c7
celu activation vulkan and onnx conversion (#5018) 2 years ago
  Beq Jal bcfec1da33
Celu layer and export to ncnn (#5019) 2 years ago
  Beq Jal c851231832
add diag layer and its converter (#4935) 2 years ago
  Amir Ramezani 695f770eab
erf implementation (#5012) 2 years ago
  nihui 4abadd2ffb
binaryop implicit broadcast B with 1 dimension rank for outer axis (#4930) 2 years ago
  nihui c45c01c7c1
enable VK_KHR_cooperative_matrix (#4823) 2 years ago
  nihui 55709708e9
x86 optimization for convolution int8 packed unified elempack (#4861) 2 years ago
  nihui 1283a19305
pnnx convert torch round trunc (#4813) 2 years ago
  nihui 9022b7162a
implement all explicit binaryop broadcast types (#4809) 2 years ago
  nihui 903ec7c2c9
fix overwrite builtin layer destruction (#4732) 3 years ago
  nihui f893d2440d
innerproduct allow 1 height gemm (#4730) 3 years ago
  nihui 249b264336
workaround moltenvk error on spec const composite op (#4714) 3 years ago
  nihui a37a83d850
clip gelu mish tanh 4d (#4695) 3 years ago
  nihui cd5a6098a2
sigmoid and swish 4d (#4692) 3 years ago
  nihui c28c8c04a1
multiheadattention attn mask (#4668) 3 years ago
  nihui b640574b88
rough vulkan gemm and multiheadattention (#4618) 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
  nihui 85991e2e0e
test custom option, update ci (#4609) 3 years ago
  nihui 6987efd950
fix scale avx512 (#4580) 3 years ago
  nihui dabc4c065f
arm convolution winograd unified elempack (#4556) 3 years ago
  WuJinxuan ff80ac2955
[ARM] Multiheadattention (#4463) 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 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
  nihui dfbcd3e69b
improve vulkan winograd f43 fp16 numerical stability (#4492) 3 years ago
  nihui fed99fd35b
gemm output transpose, prepack c (#4479) 3 years ago
  nihui 2e3e680d77
x86 optimization for packed convolution unified elempack (#4469) 3 years ago
  nihui 88274827da
x86 optimization for winograd unified elempack (#4456) 3 years ago
  nihui 15761fc1a6
arm vfpv4 asimdhp asimdfhm optimization for gemm (#4432) 3 years ago
  nihui c5640a16c3
gemm x86 multiply alpha beta in post gemm stage, enable one_blob_only (#4407) 3 years ago
  nihui fd1ac3c7a0
x86 optimization for gemm unified elempack (#4387) 3 years ago
  nihui 0736c5b658
Fix c api allocator (#4360) 3 years ago