3031 Commits (c8662cce5eec3e515fa6041c91ae62610ded1645)
 

Author SHA1 Message Date
  nihui c8662cce5e
arm optimization for convolution int8 gemm unified elempack (#5016) 2 years ago
  nihui 4da33b195e
prevent some old gcc using high registers as kernel values (#5036) 2 years ago
  HuPengsheet 6eb994422a
fix build with new protobuf target for pnnx (#5034) 2 years ago
  Shu Liqiang 83cca26794
pnnx convert torch.mv (#4974) 2 years ago
  dependabot[bot] a22998bbfa
Bump docker/setup-qemu-action from 2 to 3 (#5029) 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
  FhqTreap e14cc272ac
gelu vk op tanh fix (#5008) 2 years ago
  Jiang-Weibo 4a2620d1e2
pnnx add torch.cumprod op (#5002) 2 years ago
  nicochen1118 4923fb955b
pnnx add torch.positive (#4999) 2 years ago
  dependabot[bot] cdcb0d21cf
Bump actions/checkout from 3 to 4 (#5006) 2 years ago
  莫思潋 379dfd2e29
add torch.lgamma to pnnx (#4976) 2 years ago
  FhqTreap cc54b889d5
add gelu vulkan operator (#5001) 2 years ago
  zyt1024 b3fbbccd8b
pnnx convert torch narrow (#4918) 2 years ago
  xiezheng-XD 14b000d2b7
improve codeformat.sh with function (#4993) 2 years ago
  nihui 9ecf6a61be
x86 optimization for convolution int8 gemm unified elempack (#4881) 2 years ago
  lrw04 1a61bcd286
Fix potential overflow in determining the datatype (#4988) 2 years ago
  青菜萝卜冬瓜 0829fa49d3
Add RK3566 and RK3588S benchmark (#4977) 2 years ago
  nihui c003281c53
fix unaryop round build with old glibc (#4963) 2 years ago
  nihui 7c4969ed58
fix convolution winograd43 vulkan on fixed shape hint (#4973) 2 years ago
  nihui b2e94901d2
fix moduleop attribute order, write weight shape as parameter for ncnn module op (#4970) 2 years ago
  nihui 2c587923c0
pnnx fuse moduleop unpack (#4968) 2 years ago
  JeremyRand 77c4421fc2
load_param_mem pybind (#4924) 2 years ago
  nihui cd1c0d6eab
fix build with new protobuf target (#4955) 2 years ago
  daquexian d38871bbfc
load bin in a single pass (#4966) 2 years ago
  nihui cb674ac5ed
fix build with toolchain defined _L _U constants (#4957) 2 years ago
  青菜萝卜冬瓜 6b657a39cb
fix _mm512_i32gather_epi32 and other scatter/gather routines have incorrect signature. (#4959) 2 years ago
  nihui 39721eeb94
require c++17 for building with new protobuf (#4947) 2 years ago
  Zhuo Zhang cbd838f670
[docs] Clean comments and prints when find vulkan (#4948) 2 years ago
  nihui 00da9251b1
update python ci version (#4946) 2 years ago
  nihui 93e395dc4b
pnnx convert torch maximum minimum and torch max min as expression (#4944) 2 years ago
  lrw04 fed3b43c73
Add logxxx to log comp xxx rewriter where xxx = sigmoid or softmax (#4925) 2 years ago
  WXB 070a6d40f2
support torch.t to ncnn (#4940) 2 years ago
  nihui e80fcbca8f
prefer faster and larger device local only memory on amd integrated graphics, heap budget value follows the same strategy as blob allocator (#4936) 2 years ago
  佰阅 75e10c6e61
Support mac platform static library compilation (#4859) 2 years ago
  tpoisonooo a24787b32b
feat(benchmark/benchncnn.cpp): support user defined case (#4782) 2 years ago
  dependabot[bot] ffe1510c2f
Bump pypa/cibuildwheel from 2.13.1 to 2.15.0 (#4926) 2 years ago
  nihui 4abadd2ffb
binaryop implicit broadcast B with 1 dimension rank for outer axis (#4930) 2 years ago
  nihui 285d0793d4
pnnx fuse expression for scalar-like attribute and unbind chain (#4928) 2 years ago
  nihui 60fedae38b
fix pnnx ghost reshape shape expression inputs, fix intmax overflow on fuse/eval expression (#4923) 2 years ago
  JeremyRand 0a8cf31a05
Add POWER8 VSX toolchains (#4853) 2 years ago
  mizu-bai 4c861a0d1a
Add Building with Intel oneAPI (#4920) 2 years ago
  Han Gao 974d1122b2
Add TH1520 gpu benchmark (#4917) 2 years ago
  nihui e02b6e8521
fix pnnx slice copy shape type, inplace op link output (#4914) 2 years ago
  nihui e13fbe2a8a
pnnx add missing Tensor.to pattern (#4908) 2 years ago
  nihui 759d55d555
pnnx convert torch cross and t (#4896) 2 years ago
  Joson c6b191c3df
add RDK X3 Module benchmark (#4895) 2 years ago
  Han Gao 412960c027
Update 3A6000 data (#4894) 2 years ago