wangwei
/
MegEngine
Not watched
1
0
Fork 0
Code
Releases 31 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
2127 Commits
28 Branches
25 MB
520 Download
Tree: 396412e790
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '396412e790'
${ noResults }
Commit Graph

640 Commits (396412e7907bae599f3197b2b7f7ce9ffb8da2e5)

Author SHA1 Message Date
  Megvii Engine Team 396412e790 test(mgb/cambricon): add testcase for magicmind runtime opr 4 years ago
  Megvii Engine Team b5284796f9 feat(mgb/cambricon): add magicmind runtime opr 4 years ago
  Megvii Engine Team 623477fdeb refactor(megbrain): combine mc40 and mc20 compnode and change mc20 to ax 4 years ago
  Megvii Engine Team 11556cba13 feat(megbrain): add mc20 bazel 4 years ago
  Megvii Engine Team b8f810ee31 feat(megbrain): add mc20 runtime opr 4 years ago
  Megvii Engine Team 67e4e83419 fix(lite): fix the force_output_use_user_specified_memory when out var not supported 4 years ago
  Megvii Engine Team accb2d8d47 fix(mgb/serialize): fix flatbuffer compatibility issues 4 years ago
  Megvii Engine Team 5b1383e06c fix(mgb/plugin): fix io dump for qint4, quint4 and bool type tensors 4 years ago
  Megvii Engine Team 24f12df95b chore(release): bump version 4 years ago
  Megvii Engine Team 605836a70f fix(mgb): fix trt5.1 test can not create FlattenConcatPlugin 4 years ago
  Megvii Engine Team 11d75fecb5 feat(dnn/check_non_finite): add batch check_non_finite 4 years ago
  Megvii Engine Team 30976c239f fix(mgb/gopt): fix global layout transform 4 years ago
  Megvii Engine Team b6c0e8d093 fix(mgb/gopt): update profiler cache of global layout transform test 4 years ago
  Megvii Engine Team f2db7b0ded feat(mgb/gopt): global layout transform support cuda fp16 4 years ago
  Megvii Engine Team ca7cec7a5d fix(mgb/gopt): minor fixes for global layout transform 4 years ago
  Megvii Engine Team 93152dfa14 fix(mgb/gopt): fix global layout transform 4 years ago
  Megvii Engine Team fe93013a6e feat(mgb/gopt): global layout transform support nchw_nchwxx hybrid mode 4 years ago
  Megvii Engine Team 3d45d35241 feat(mgb/gopt): profiler support checking algo availability 4 years ago
  Megvii Engine Team 5f15f75984 test(mgb/gopt): add a testcase for SubGraphExtractor with multiple outputs 4 years ago
  Megvii Engine Team a6230ba95a feat(mgb/gopt): global layout transform support arm 4 years ago
  Megvii Engine Team 0be6ca8899 fix(src/core): fix record change ptr bug on comp node copy 4 years ago
  Megvii Engine Team 84baf3df1b feat(mgb): add tensorrt plugin support 4 years ago
  Megvii Engine Team b59e8ccf24 fix(mgb): fix cambricon bangc copybara 4 years ago
  Megvii Engine Team fe6299c52d Revert "feat(mgb): allow output tensor's ptr change when record" 4 years ago
  Megvii Engine Team d90cb7763c feat(src/core): record support change ptr basic 4 years ago
  Megvii Engine Team 68cdabd288 feat(opr): indexing_multi_axis_vec support nd index 4 years ago
  Megvii Engine Team 0a56a5b110 feat(cuda/comp_node): gets (maximum) GPU memory allocated/reserved 4 years ago
  Megvii Engine Team 13c7c572df fix(mgb): fix shape infer's condition in lite 4 years ago
  Megvii Engine Team 0ddabb06cc fix(imperative/astype): fix astype when target dtype is int4 4 years ago
  Megvii Engine Team 34773ba37b fix(mgb/gopt): tensorcore pass replace BatchConvBias inputs to nchw4 4 years ago
  Megvii Engine Team 481007812e fix(mgb): support rc version 4 years ago
  Megvii Engine Team f00741dad5 feat(build): bazel build support flatbuffer serialization 4 years ago
  Megvii Engine Team 8b7649345a feat(lite): lite support output var no copy option 4 years ago
  Megvii Engine Team 7642f66df7 feat(core): support output var no copy 4 years ago
  Megvii Engine Team 7fa5f6f4e2 fix(mgb): correct version of fbs serialization 4 years ago
  Megvii Engine Team 25ec2530ba feat(whl/api/lar): enable megengine dll on Windows 4 years ago
  Megvii Engine Team c17d603847 feat(mgb): allow output tensor's ptr change when record 4 years ago
  Megvii Engine Team d9a9d9d49e fix(imperative/fastrun): set workspace limit for imperative rt 4 years ago
  Megvii Engine Team a09a2b730d fix(mgb/opr): fix fastrun workspace limit for imperative rt 4 years ago
  Megvii Engine Team 5207154e5c Revert "fix(mgb): fix fastrun no_profiling_on_shape_change" 4 years ago
  Megvii Engine Team bd42cb06cf refactor(mgb/lite): refactor lite InfilePersistentCache with core impl 4 years ago
  Megvii Engine Team d898838e18 fix(src/gopt/test): remove device info in the cache_data 4 years ago
  Megvii Engine Team a4ac5e7e8f fix(mgb/gopt): fix profiler cache when build without opr type info name 4 years ago
  Megvii Engine Team 012de7695d feat(mgb/gopt): add profiler cache 4 years ago
  Megvii Engine Team b33ec46e54 fix(mgb/gopt): fix layout gtrans when graph partition has opr with different format 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 565466c25f feat(lite): auto deduce output tensor shape before model forward 4 years ago
  Megvii Engine Team a29f1c8c02 fix(cmake/midout): fix cmake midout 4 years ago
  Megvii Engine Team 369c2ccc5a style(all): reformat c++ code 4 years ago
  Megvii Engine Team bfb30dcb81 chore(format): fix compile bugs after code format 4 years ago