2769 Commits (057b5bb515d551fa64decdb7350422c19feba447)
 

Author SHA1 Message Date
  nihui 057b5bb515
split tests (#4354) 3 years ago
  nihui aed05aa851
pnnx fuse more function to module (#4351) 3 years ago
  nihui ec1b07c9fe
pnnx fp16 option for ncnn and onnx weight type (#4350) 3 years ago
  nihui 6967baaccc
pnnx convert torch bitwise left_shift right_shift (#4349) 3 years ago
  nihui eceac35a7f
implement MultiheadAttention kdim vdim (#4347) 3 years ago
  nihui 498ca7341b
squeeze and expanddims 4d (#4346) 3 years ago
  Lry89757 6a47f8d15c
gridsample op support (#4288) 3 years ago
  nihui 6019f47f08
ci loongarch64 lsx (#4344) 3 years ago
  junchao-loongson 279222c2c9
add vector optimization for loongarch64 (#4242) 3 years ago
  nihui a2af6369d9
match inplace slice copy pattern, rewrite copy uses (#4338) 3 years ago
  nihui a7e3c62a1b
save foldable constants in file for reducing memory usage (#4337) 3 years ago
  nihui cb88e16fdf
pnnx save onnx zero (#4077) 3 years ago
  WuJinxuan abb28435d6
fix:pnnx-softmax (#4333) 3 years ago
  nihui 92da26be79
pnnx load gpu torchscript and reset device (#4330) 3 years ago
  nihui 5b28c1730e
implement ncnn fold and unfold (#4326) 3 years ago
  shaoshengsong d522e78af1
support yolov5 6.2 (#4328) 3 years ago
  nihui a12c24d328
pnnx convert fold unfold (#4325) 3 years ago
  nihui b8d40a960f
pnnx convert nn.Softmax2d (#4324) 3 years ago
  nihui bcf06bd1c0
fold new_full and full_like (#4323) 3 years ago
  nihui 2ef57a6204
fix ci pnnx build 3 years ago
  Xavier Hsinyuan d1ac1de7ab
RVV: InstanceNorm with fp16s(a) support (#4078) 3 years ago
  Xavier Hsinyuan 31602bd2dc
RVV: BatchNorm with fp16s(a) support (#4075) 3 years ago
  nihui a91411ea14
tencent ci test-coverage pnnx (#4305) 3 years ago
  nihui 0f9a3bb9dc
fix slice end index, fix fp16 model weight alignment (#4317) 3 years ago
  nihui 6e49fa30dc
groupnorm 1d/2d/4d (#4312) 3 years ago
  nihui b853b3d132
get_physical_cpu_count api family (#4302) 3 years ago
  nihui 9c6f1107d2
fix #4315 (#4316) 3 years ago
  nihui fdf129fcd7
pnnx pytorch 1.13 (#4314) 3 years ago
  dependabot[bot] b17c9eb84f
Bump pypa/cibuildwheel from 2.11.1 to 2.11.2 (#4308) 3 years ago
  nihui 5ee276cdf7
x86 unified fc fp32/fp16s (#4303) 3 years ago
  nihui 512e584a6a
general cpu feature detection on macos/ios, enable bf16 and i8mm on a15 a16 and m2 (#4300) 3 years ago
  bestpower a116e005b8
Fix linux build error(#4265) (#4294) 3 years ago
  nihui 8edc03c515
pnnx skip dynamic size evaluation (#4291) 3 years ago
  nihui 8eab5ea0ea
x86 sse2/avx2 optimization for convolution sgemm/winograd int8 family (#4286) 3 years ago
  Caize Wu c33cbc924a
1. Fix typo in readme (#4287) 3 years ago
  nihui f770987267
pnnx glu batchindex aware conversion (#4285) 3 years ago
  nihui 777e4ef0a0
fix pnnx softmax/normalize/slice negative axis conversion to ncnn (#4284) 3 years ago
  dependabot[bot] 549152ca73
Bump pypa/cibuildwheel from 2.10.2 to 2.11.1 (#4271) 3 years ago
  Fangjun Kuang 5281d51535
implement GLU and pnnx conversion (#4283) 3 years ago
  nihui c62d2563ac
fix tencent ci (#4277) 3 years ago
  Yoh bb660d09b8
add elu vulkan operator (#4280) 3 years ago
  nihui 0b591b0d1f
implement layer feature disabled bit (#4278) 3 years ago
  nihui 270d6b2ae6 linux-x64-cpu-gcc on tencent ci 3 years ago
  li mengyang 0df463a77e
add benchmark for rk3588 on rock5b (#4275) 3 years ago
  Eahow Chen f80c2743e7
fix compile warning with gcc 9.1.0 including simplestl.h file (#4274) 3 years ago
  miemie2013 b13c2a16ce
Optimize x86 DeformableConv2D (#4128) 3 years ago
  nihui 77eda4c19f
implement lstm proj_size (#4263) 3 years ago
  陸 言 0f38cb2cd8
Add TH1520 (4*C910V) toolchain support. (#4267) 3 years ago
  LiuYi-Up 902954d737
modified the param axes of expanddims in modelwriter (#4259) 3 years ago
  nihui 3e2b3fa04d
more stricter armv7 fp16 and armv84 bf16 compiler check, fix #4147 fix #4222 (#4247) 3 years ago