wangwei
/
MegEngine
Not watched
1
0
Fork 0
Code
Releases 31 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
2527 Commits
28 Branches
25 MB
520 Download
Tree: 5f0e7ffb64
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '5f0e7ffb64'
${ noResults }
Commit Graph

166 Commits (5f0e7ffb64238e4b52f80ce73ec2a99bd1fbe4bf)

Author SHA1 Message Date
  Megvii Engine Team c2e9860feb chore(license): remove all license in file header 3 years ago
  Megvii Engine Team 70209667e8 fix(dnn/test): fix some bug when force_deduce_layout is off 3 years ago
  Megvii Engine Team 7dc347697a feat(dnn/cuda): add typecvt uint16 3 years ago
  Megvii Engine Team 4c0bff1dba refactor(megdnn): refactor TEGRA_X1/X2 macro 3 years ago
  Megvii Engine Team 758549b936 feat(megengine): support tx2 3 years ago
  Megvii Engine Team b6ad457269 feat(cuda): support int1 simplewq conv 3 years ago
  Megvii Engine Team fd6f8e58b0 feat(mgb/dtype): add dtype qint1 3 years ago
  Megvii Engine Team 87de704a46 feat(gopt): fuse conv h_swish 3 years ago
  Megvii Engine Team d7b0994a3e feat(cuda): add fp16 compute 16 kernel 3 years ago
  Megvii Engine Team 8a2e92bd6c refactor(cuda): depthwish large kernel 3 years ago
  Megvii Engine Team 6b8a69d5b6 feat(cuda): float16 depthwise large kernel conv compute fp32 3 years ago
  Megvii Engine Team bc385b5374 feat(cuda): support float16 depthwise large kernel conv 4 years ago
  Megvii Engine Team 7d2063e35a perf(cuda): speedup conv backward data with small feature map and large filter size 4 years ago
  Megvii Engine Team 72403e8929 perf(cuda): speedup chanwise conv with small feature map and large filter size 4 years ago
  Megvii Engine Team ab6d12caff feat(mge): add conv padding mode 4 years ago
  Megvii Engine Team 47fe766310 feat(dnn/cuda): add implicit bmm kernels for large kernel depthwise convolution backward filter opr 3 years ago
  Megvii Engine Team 6cefabe734 fix(dnn/cuda): fix ci 4 years ago
  Megvii Engine Team 888f4e46ae feat(dnn/cuda): add implicit bmm large kernel dwconv2d dgrad kernels 4 years ago
  Megvii Engine Team 08d8635ff5 feat(dnn/cuda): add implicit bmm large kernel dwconv2d fprop impl 4 years ago
  Megvii Engine Team 95ac055538 feat(dnn,mgb,imperative): add diag opr implement 4 years ago
  Megvii Engine Team cbbca5fb10 feat(mge): add softmax op use cudnn api 4 years ago
  Megvii Engine Team 82be0aaced test(dnn): fix compute capability requirement for NCHWX test 4 years ago
  Megvii Engine Team 1999307015 feat(mgb/opr): add dropout kernel 4 years ago
  Megvii Engine Team a93741815b feat(mgb/opr): add layernorm forward and backward kernel 4 years ago
  Megvii Engine Team 2696e4efaa feat(dnn): add float16 for remap backward 4 years ago
  Megvii Engine Team 11d75fecb5 feat(dnn/check_non_finite): add batch check_non_finite 4 years ago
  Megvii Engine Team ba2f0c2e48 fix(dnn/cuda): fix cudnn_conv algo of conv_bias opr for fp16 add z cases 4 years ago
  Megvii Engine Team c85631aa77 feat(dnn): use ref ptr interface for all backends 4 years ago
  Megvii Engine Team 89186edc5d fix(dnn): correct reduce/argmxx/fakequant calculation with nan 4 years ago
  Megvii Engine Team 68cdabd288 feat(opr): indexing_multi_axis_vec support nd index 4 years ago
  Megvii Engine Team 9b4cd92ba3 fix(mgb/dnn): fix cudnnConvBiasActivation crash on nchw32 int8 with oc > 256 4 years ago
  Megvii Engine Team 10af44abba fix(dnn/cuda): fix cudnn conv impl for nchw4_nchw hybrid layout 4 years ago
  Megvii Engine Team 5885b137fa feat(dnn/arm): support layout like NHWC channel like broadcast on arm 4 years ago
  Megvii Engine Team 369c2ccc5a style(all): reformat c++ code 4 years ago
  Megvii Engine Team f5cb21ed3a fix(mgb/opr): add non finite check 4 years ago
  Megvii Engine Team bde5cf3564 feat(dnn): add resize linear for arm 4 years ago
  Megvii Engine Team 3d3666b6e0 test(dnn/bn): add compatible configs for NHWC BN 4 years ago
  Megvii Engine Team 3977b7aa0b feat(mgb/shuffle): add shuffle opr 4 years ago
  Megvii Engine Team 17371e79b9 fix(dnn/reduce): fix reduce_mean o16c32 is incorrect for large tensor 4 years ago
  Megvii Engine Team 8b40f57738 feat(mgb/dnn): add conv1x1 algo for matrix mul 4 years ago
  Megvii Engine Team d69b59035d feat(dnn): add an get_all_algorithms_safe interface 4 years ago
  Megvii Engine Team 8b94f49328 fix(dnn/cuda): fix elemwise and relayout int4 bug when last shape is 1 4 years ago
  Megvii Engine Team 722aecd437 feat(mgb): support fp16 nhwc backward 4 years ago
  Megvii Engine Team 0708bc780c fix(dnn/cuda): disallow implicit dtype conversion in cublaslt matmul algos 4 years ago
  Megvii Engine Team 4c13bc7e1b feat(dnn/cuda): add nhwc int8 deconv 4 years ago
  Megvii Engine Team 11f022ff7c feat(dnn/cuda): add nhwc int8 imma conv and conv fuse typecvt 4 years ago
  Megvii Engine Team 67575d582c feat(mge/opr): add interpolate bilinear mode 4 years ago
  Megvii Engine Team 0558b2123d feat(mge/opr): add interpolate nearest mode 4 years ago
  Megvii Engine Team c25125e3d2 perf(dnn/cuda): sass int8 epilogue remove shared load 4 years ago
  Megvii Engine Team ff0e6be7b9 fix(dnn/cuda): fix cutlass tensorop kernels 4 years ago