wangwei
/
MegEngine
Not watched
1
0
Fork 0
Code
Releases 31 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
1054 Commits
28 Branches
25 MB
551 Download
Tree: de0742be25
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'de0742be25'
${ noResults }
Commit Graph

321 Commits (de0742be255b7fe228b860d3dc2efec2a2803bf4)

Author SHA1 Message Date
  Megvii Engine Team 3975a54aa4 fix(mge/sublinear): fix divide by zero in sublinear 5 years ago
  Megvii Engine Team 8f7f52ae4d feat(jit): add memfwd in jit executor opr 5 years ago
  Megvii Engine Team dfb2b2ce49 fix(dnn): change pooling window size smaller than padding constraint to log_error 5 years ago
  Megvii Engine Team c49427d15a feat(imperative): add inplace add_update option in optimizer 5 years ago
  Megvii Engine Team aeb7980b29 perf(mgb): outputs of the same opr and same compnode share the same callbackcaller 5 years ago
  Megvii Engine Team 7f3f9a94ae feat(mgb/core): add shape hint for graph optimization 5 years ago
  Megvii Engine Team a85531dd0f feat(mgb/opr): add tqt opr 5 years ago
  Megvii Engine Team a5609f3bbf fix(cambricon): fix cross cn copy for cambricon 5 years ago
  Megvii Engine Team aba0acc797 fix(sdk): add AssertEqual opr, fix dump_with_testcase_mge 5 years ago
  Megvii Engine Team 14d8b709e1 perf(mge/imperative): add mini graph to partially replace proxy graph 5 years ago
  Megvii Engine Team 184e1311fa fix(mgb/opr): move NVOF opr's shape inference to execute part 5 years ago
  Megvii Engine Team 4e9be159f7 feat(mgb/gopt): add opt pass for fusing convolution and reformat 5 years ago
  Megvii Engine Team 61f917fb8e feat(dnn/cuda): add impl for fusing warp perspective and dimshuffle 5 years ago
  Megvii Engine Team 15dd5e1a0f fix(mgb/core): fix memory management release cambricon var issue 5 years ago
  Megvii Engine Team 38ea5f1ba0 fix(mgb/jit): lower FuncOp to GPUFuncOp directly 5 years ago
  Megvii Engine Team 88b402ef62 feat(mge/trace): tracing use id to set priority 5 years ago
  Megvii Engine Team d2910f7ef5 fix(mgb/jit): add bind_shape feature to MLIRCompiler 5 years ago
  Megvii Engine Team 469d0808f5 fix(asan/thread): fix asan issue 5 years ago
  Megvii Engine Team eb826422c4 fix(dnn): forbid pooling window size smaller than padding 5 years ago
  Megvii Engine Team a78c11099b fix(imperative): add param(axis) for GetVarShape 5 years ago
  Megvii Engine Team fc0fcd2f7f chore(winograd): remove winograd transform code 5 years ago
  Megvii Engine Team 368c18607f fix(mgb/jit): find cuda include path correctly 5 years ago
  Megvii Engine Team b04e0466bb feat(megbrain): add alias name to model serialization 5 years ago
  Megvii Engine Team cf53d9e0f8 fix(mgb/tensor): do tensor overlap check only when d2d and h2h 5 years ago
  Megvii Engine Team 69e3e32240 feat(imperative): auto generated opdef header and python binding 5 years ago
  Megvii Engine Team 0398a7867f fix(build/windows/cuda/llvm): fix windows bazel build with cuda 5 years ago
  Megvii Engine Team 3bf73ff16f feat(dnn): add cuda preprocess fusion 5 years ago
  Megvii Engine Team 5f171298aa feat(mgb/gopt): add AxisAddRemove opr support for cd4 opt pass 5 years ago
  Megvii Engine Team dbb64b46d5 feat(debug/android): opt android backtrace 5 years ago
  Megvii Engine Team 3e00e3f697 feat(debug/linux): opt linux backtrace 5 years ago
  Megvii Engine Team 783a612643 feat(debug/macos/windows): imp macos/windows backtrace, fix mem issue 5 years ago
  Megvii Engine Team e92670e820 fix(mgb/atlas): when batchsize more than model max batchsize 5 years ago
  Megvii Engine Team 147dbf8a0c fix(test): fix a race condition in TestCudaMemAlloc 5 years ago
  Megvii Engine Team 7066ad5ba6 feat(dnn): add uint16 support 5 years ago
  Megvii Engine Team a1877ee0fa refactor(dnn): refactor algo interface, use algoinfo instead of global algorithm 5 years ago
  Megvii Engine Team cb59c27835 feat(mlir/ir): add more op definitions 5 years ago
  Megvii Engine Team 9ec8d375f1 feat(externcopr): add config extern c opr dynamic param 5 years ago
  Megvii Engine Team 88e918e261 feat(mgb/jit): add scf.ForOp in MgbToGpuLoweringPass 5 years ago
  Megvii Engine Team 6f5d0febf1 perf(dnn/cuda): enhance performance for pooling forward 5 years ago
  Megvii Engine Team f7731bd437 fix(mgb/jit): fix a pointer bug in mlir executable_cuda 5 years ago
  Megvii Engine Team 2ad8c5e1e9 fix(mge/io_remote): fix remote send/recv gradient at trace 5 years ago
  Megvii Engine Team f470df4f1a fix(mgb/opr): fix convbias with no bias when weight preprocess 5 years ago
  Megvii Engine Team 6b9ac894d3 fix(mgb/topk): fix topk grad 5 years ago
  Megvii Engine Team 61c5c9cf74 chore(cmake): normlize some cmake message level 5 years ago
  Megvii Engine Team 5d0f8da46a feat(mgb/jit): add Dimshuffle and lowering passes in jit mlir backend 5 years ago
  Megvii Engine Team 0007b9e09b build(third_party): update llvm-project 5 years ago
  Megvii Engine Team 404ef808fa feat(mgb/jit): adapt jit mlir backend to new mgb dialect and add typecvt 5 years ago
  Megvii Engine Team 60c6d59fc9 feat(mbg/core): support bias preprocess in conv_bias 5 years ago
  Megvii Engine Team 064c774f05 feat(imperative): impl hashable for SendRecv and add virtual input for Recv 5 years ago
  Megvii Engine Team b60cc8ca3e feat(mgb/opr): add megbrain fake quant opr 5 years ago