57 Commits (ca717806afd36074a94226fd1495aff400e66b99)

Author SHA1 Message Date
  Megvii Engine Team cab46f2a00 fix(dnn): fix relayout format when group conv group=1 5 years ago
  Megvii Engine Team 4afa4b72c3 fix(mgb/oppass): fix fuse conv bias pass when bias is full bias and bias 5 years ago
  Megvii Engine Team 03d0cc0281 feat(gopt): add remove redundant copy pass 5 years ago
  Megvii Engine Team 40e778fbd1 fix(mgb): fix-deconv-io16c32-pass-fail 5 years ago
  Megvii Engine Team ee2e2b3c7b fix(mgb/gopt): fix nchwxx optpass of no handle conv_bias opr which with no bias 5 years ago
  Megvii Engine Team 59a9275c66 fix(mge): fix optimize_for_inference during trace.dump 5 years ago
  Megvii Engine Team 8f44d6ea60 fix(mgb): fix optpass fail at transform NCHW to NCHW4 when input dtype is float 5 years ago
  Megvii Engine Team fade97d4ef fix(mgb/gopt): fix convert batchnorm to elemwise pass issue 5 years ago
  Megvii Engine Team 78d7d400d1 feat(opr): add a constant flavor for SharedDeviceTensor 5 years ago
  Megvii Engine Team c20d4cc6dc feat(dnn): fix opt pass nchw44 can not dump resnet 5 years ago
  Megvii Engine Team 56381f808b fix(dnn/arm): use vcvtq_f32_s32 for all arm code 5 years ago
  Megvii Engine Team 1173205726 fix(gopt): nchw_nchwxx useable and opt pass use nchw_nchwxx_valid 5 years ago
  Megvii Engine Team eb18eba87d fix(gopt): fix nchw44 nchw44_dot gopt test 5 years ago
  Megvii Engine Team eab7ab0530 fix(gopt): gen nchw_nchw44 when kernel is optimized 5 years ago
  Megvii Engine Team 777f3ea970 refactor(gopt): format code 5 years ago
  Megvii Engine Team 80c4705317 perf(mgb): use midout in megbrain to reduce binary size 5 years ago
  Megvii Engine Team 4348960c40 fix(mge/gopt): fix fp16 compute mode 5 years ago
  Megvii Engine Team 9f4060b050 fix(mgb/gopt): add ShuffleShuffleRemovePass assert 5 years ago
  Megvii Engine Team c1fb3c8c1a fix(mgb/gopt): fix ConvertF32ToF16Pass endpoints 5 years ago
  Megvii Engine Team ab3efab066 fix(mgb): add compute capability check 5 years ago
  Megvii Engine Team 8070f40aa1 fix(mgb/gopt): fix gopt nchwxx convert elemwise and reshape 5 years ago
  Megvii Engine Team 486cbdea8b fix(mgb/opt): nchw to nchw4 pass suppport ic less than 4 5 years ago
  Megvii Engine Team 2e70cf1dd0 feat(mgb/opt): add nchw->nchw4 in tensorcore pass 6 years ago
  Megvii Engine Team 1e8337f14a fix(mgb/gopt): remove redundant reshape in nchw->nchw4 pass 6 years ago
  Megvii Engine Team 6d367454cf feat(mge/opr-mm): add param local_grad for collective_comm opr 6 years ago
  Megvii Engine Team 0ccb965c8e fix(mgb/gopt): fix convert format nchw->nchw4 pass 6 years ago
  Megvii Engine Team 4d35397bdf fix(dnn/fallback): fix conv1x1/im2col usable and fuse-conv-bias get fp32xfp32-->qint8 error 6 years ago
  Megvii Engine Team 12dc36a6ab feat(mgb/gopt): add interface to reproducible 6 years ago
  Megvii Engine Team 09d2b7c3fe fix(core): make the semantics of instance id clear and correct 6 years ago
  Megvii Engine Team 273f891b55 fix(mgb/gopt): fix run-time winograd-transform and nchwxx error 6 years ago
  Megvii Engine Team 9ed3882a94 fix(opr/dnn): fix winograd fast run mismatch 6 years ago
  Megvii Engine Team 18be23f328 fix(mbg/gopt): fix nchwxx gopt with no fuse conv_bias and winograd 6 years ago
  Megvii Engine Team 01092feb9b feat(mgb): add PackAllReducePass 6 years ago
  Megvii Engine Team 49fdddef8d fix(gopt): fix reorder arith chain pass 6 years ago
  Megvii Engine Team 50db9b84c2 fix(gopt): fix paramfuse if the endpoint is const 6 years ago
  Megvii Engine Team f56f187f6e fix(mbg/gopt): fix nchw44-dot channel wise trans to nchw44 6 years ago
  Megvii Engine Team f1c86606cb fix(dnn/cuda): fix FuseConvBiasWithZ pass for HSwish activation 6 years ago
  Megvii Engine Team 8f87a3e988 feat(dnn/arm_common): add int8 nchw44 winograd f23_4x4 f23_8x8 compute float32/int16 output int8 6 years ago
  Megvii Engine Team 30b3d3aa3e fix(dnn/gopt): add convolution nchw44-dot format gopt 6 years ago
  Megvii Engine Team c1397792a7 feat(dnn): add winograd-fp32-nchw44 support 6 years ago
  Megvii Engine Team 45e2beead6 feat(mgb/gopt): add nchw4 optpass 6 years ago
  Megvii Engine Team 6d6b42bb77 refactor(gopt): refactor interface of add passes for common optimizations 6 years ago
  Megvii Engine Team 6585514902 fix(gopt): fix convbias replace of cd4 pass 6 years ago
  Megvii Engine Team 36f17dec64 feat(gopt): add layout transform and fuse in load_and_run 6 years ago
  Megvii Engine Team e24fcd00c1 refactor(gopt): use graphcommonoptimizeoptions for graphopt 6 years ago
  Megvii Engine Team e080dd3c8c refactor(gopt): rename nchw2xxx to xxx 6 years ago
  Megvii Engine Team a3560fa10e feat(gopt): add tranform to chwn4 to optimize_for_inference 6 years ago
  Megvii Engine Team 1fb7d34f0b refactor(gopt): refactor layout transform for optimize for inference 6 years ago
  Megvii Engine Team 4f77509ea6 feat(mgb/opr): allow empty ImmutableTensor 6 years ago
  Megvii Engine Team e109ae919c fix(mgb/gopt): fix float32 to float16 opt pass 6 years ago