19 Commits (fc0fcd2f7f34431770c4fb8197536783112d79f9)

Author SHA1 Message Date
  Megvii Engine Team fc0fcd2f7f chore(winograd): remove winograd transform code 5 years ago
  Megvii Engine Team 3bf73ff16f feat(dnn): add cuda preprocess fusion 5 years ago
  Megvii Engine Team 03d0cc0281 feat(gopt): add remove redundant copy pass 5 years ago
  Megvii Engine Team 2e70cf1dd0 feat(mgb/opt): add nchw->nchw4 in tensorcore pass 5 years ago
  Megvii Engine Team 273f891b55 fix(mgb/gopt): fix run-time winograd-transform and nchwxx error 5 years ago
  Megvii Engine Team 18be23f328 fix(mbg/gopt): fix nchwxx gopt with no fuse conv_bias and winograd 5 years ago
  Megvii Engine Team 50db9b84c2 fix(gopt): fix paramfuse if the endpoint is const 5 years ago
  Megvii Engine Team 30b3d3aa3e fix(dnn/gopt): add convolution nchw44-dot format gopt 5 years ago
  Megvii Engine Team 45e2beead6 feat(mgb/gopt): add nchw4 optpass 5 years ago
  Megvii Engine Team 6d6b42bb77 refactor(gopt): refactor interface of add passes for common optimizations 5 years ago
  Megvii Engine Team 6585514902 fix(gopt): fix convbias replace of cd4 pass 5 years ago
  Megvii Engine Team 36f17dec64 feat(gopt): add layout transform and fuse in load_and_run 5 years ago
  Megvii Engine Team e24fcd00c1 refactor(gopt): use graphcommonoptimizeoptions for graphopt 5 years ago
  Megvii Engine Team e080dd3c8c refactor(gopt): rename nchw2xxx to xxx 5 years ago
  Megvii Engine Team a3560fa10e feat(gopt): add tranform to chwn4 to optimize_for_inference 5 years ago
  Megvii Engine Team 1fb7d34f0b refactor(gopt): refactor layout transform for optimize for inference 5 years ago
  Megvii Engine Team 4f77509ea6 feat(mgb/opr): allow empty ImmutableTensor 5 years ago
  Megvii Engine Team 554ce352c8 feat(mgb/gopt): add nchw44 optpass 5 years ago
  Megvii Engine Team f91881ffdc MegEngine: Initial commit of MegEngine. 6 years ago