805 Commits (b82e8f007c06d37c6d7c05c066850652bb9ba20f)

Author SHA1 Message Date
  Megvii Engine Team b82e8f007c refactor(gopt): refact the padding channel opt pass 3 years ago
  Megvii Engine Team fa9d719f7e fix(gopt): fix global layout transform fold conv typecvt 3 years ago
  Megvii Engine Team 767fa47480 fix(mgb): add detail error message for trt version diff 3 years ago
  Megvii Engine Team 94e49fae4f fix(serilization): fix elemwise multitype compatibilty in v1.11.0 3 years ago
  Megvii Engine Team f287501eb2 fix(src/core): fix pushdown alloc_result inconsistent when run for many time 3 years ago
  Megvii Engine Team 9e020d23b4 feat(imperative,mgb): add RegionRestrictedConvolution megbrain and imperative opr 3 years ago
  Megvii Engine Team 896b0193d4 fix(mgb): fix zero copy error when model end with memory forward opr 3 years ago
  Megvii Engine Team d3b2b51918 feat(mge/opr): add meshgrid opr 3 years ago
  Megvii Engine Team dc0ab9b64e feat(lite): replace warp when src is discrete input 3 years ago
  Megvii Engine Team 411253f852 feat(mge): implement warp_affine backward 3 years ago
  Megvii Engine Team fb9d73b279 fix(src/tensorrt): trt7 manage all workspace 3 years ago
  Megvii Engine Team dee0228982 fix(serialization): when the dump fbsv2 model is used, the middle_tensor becomes optional 3 years ago
  Megvii Engine Team ab34bac4fc fix(opencl/extern_c_opr): fix cl_mem UAF issue 2/2 3 years ago
  Megvii Engine Team 116781ba9c fix(mgb): fix megtee build errors 3 years ago
  Megvii Engine Team b8c7557b86 fix(mm): fix mm error when use sync 3 years ago
  Megvii Engine Team 73ad06baba fix(mgb): fix fbsv2 model format no dump tensor format 3 years ago
  Megvii Engine Team 399200b3a7 perf(serialization): optimized the memory usage when load new format model 3 years ago
  Megvii Engine Team f31e52d521 feat(mgb): warpperspective support multi src input 3 years ago
  Megvii Engine Team fca6c76a0e fix(lite): fix input invalid bug in lar for fitting mode 3 years ago
  Megvii Engine Team cc21855074 feat(lite): load_and_run support optimize for inference 3 years ago
  Megvii Engine Team 9bbe550032 fix(opencl/extern_c_opr): fix cl_mem UAF issue when 3 years ago
  Megvii Engine Team 1f7bf1ada3 fix(opr): fix the compatilibity of elemwise multitype new mode 3 years ago
  Megvii Engine Team 198ee0686f feat(mgb/trt): update tensorRT toolchain to 8 3 years ago
  Megvii Engine Team 626222c698 fix(test): fix test for brainpp docker env 3 years ago
  Megvii Engine Team fac67e7c2b feat(gopt): support nchw44 global pooling with fuse_grain 3 years ago
  Megvii Engine Team 32b31fd578 fix(mgb): change the check method of cuda sm code 3 years ago
  Megvii Engine Team 5f86368219 Revert "feat(dnn): add elemwise modes" 3 years ago
  Megvii Engine Team d2a1905ad5 Revert "feat(mgb): add cumprod opr" 3 years ago
  Megvii Engine Team 49e14f87b5 feat(mgb): add cumprod opr 3 years ago
  Megvii Engine Team 87aedc2991 feat(dnn): add elemwise modes 3 years ago
  Megvii Engine Team c49d3070ba refactor(imperative/ops): extends DnnOprCaller with template 3 years ago
  Megvii Engine Team 3fbceb3a38 fix(mgb/version): fix nvinfer.h not found 3 years ago
  Megvii Engine Team d60d028a40 feat(mge/device): enable to get cuda/cudnn/tensorrt version 3 years ago
  Megvii Engine Team 6dfd5a4cd4 fix(win7): workaround for hang when progress exit on win7+32bit 3 years ago
  Megvii Engine Team 51397bfc08 feat(mgb): supports value infer and empty input tensor in ElemwiseMultiType 3 years ago
  Megvii Engine Team 247e2f59a4 feat(mgb/dnn): add modes that the output type is bool in elemwise 3 years ago
  Megvii Engine Team cfed86f9af feat(persistentcache): change file persistent cache with append model 3 years ago
  Megvii Engine Team d19fc2c1da fix(imperative): add alloc TensorPtr in imperative 3 years ago
  Megvii Engine Team ac51f7807d feat(mge/distributed): add support for batch send recv op 3 years ago
  Megvii Engine Team 35cf0422f0 fix(ci): relax async timeout 3 years ago
  Megvii Engine Team 5a35513856 fix(mgb): fix profile skip condition 3 years ago
  Megvii Engine Team 5bdc430ec1 fix(mgb/fastrun): fix megbrain fastrun memory overflow bug 3 years ago
  Megvii Engine Team a4f019e79d fix(mgb/atlas): fix issue with profiling on Atlas 3 years ago
  Megvii Engine Team cfc41648a4 fix(mge): fix grad of maximum(x, x) 3 years ago
  Megvii Engine Team ed92b9c125 fix(cmake): fix compilation options for benchmark in cmake 3 years ago
  Megvii Engine Team f0088335bb feat(mgb): upgrade flatbuffer 3 years ago
  Megvii Engine Team 4d22e85b46 feat(ci): add completeness compatibility check 3 years ago
  Megvii Engine Team a32b727720 fix(build): upgrade bazel riscv toolchains 3 years ago
  Megvii Engine Team 1192a9a61b fix(imperative): fix adaptive pool2d 3 years ago
  Megvii Engine Team 24c5c19bf0 fix(imperative): make functional ops support negative axis 3 years ago