OpenI
/
MegEngine
Not watched
1
0
Fork 0
Code
Releases 31 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
1074 Commits
28 Branches
25 MB
3777 Download
Tree: e0fffa5286
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'e0fffa5286'
${ noResults }
Commit Graph

1074 Commits (e0fffa5286da293601b8220f330872931d075cf5)
 

Author SHA1 Message Date
  Megvii Engine Team 3bf73ff16f feat(dnn): add cuda preprocess fusion 4 years ago
  Megvii Engine Team 86cf7490ec feat(dnn/aarch64): add quantizeds4 matmul int4x4x16_k8x8x8 4 years ago
  Megvii Engine Team bff0fc6172 fix(mge/interpreter): fix outputs check on async level0 4 years ago
  Megvii Engine Team 142f31a875 perf(dnn/cuda): change conv_bias heu, prefer dnn chanwise impl, dislike dnn batch gemm conv1x1 4 years ago
  Megvii Engine Team f214e14695 refactor(mgb/cuda): use single implementation of get_device_prop from utils 4 years ago
  Megvii Engine Team 54e79dd1d9 perf(mgb/cuda): do not call cudaGetDeviceProperties to avoid io traffic 4 years ago
  Megvii Engine Team 5f171298aa feat(mgb/gopt): add AxisAddRemove opr support for cd4 opt pass 4 years ago
  Megvii Engine Team 93f4977c78 feat(mge/imperative): add thread name 4 years ago
  Megvii Engine Team 98a74e4a7b refactor(dnn): refactor opr proxy in test 4 years ago
  Megvii Engine Team 57546b4c3d test(mge/distributed): fix test skip condition error 4 years ago
  Megvii Engine Team 90e7cb005c feat(externcopr/lar): imp lar run extern c opr with dynamic param 4 years ago
  Megvii Engine Team dbb64b46d5 feat(debug/android): opt android backtrace 4 years ago
  Megvii Engine Team 3e00e3f697 feat(debug/linux): opt linux backtrace 4 years ago
  Megvii Engine Team 783a612643 feat(debug/macos/windows): imp macos/windows backtrace, fix mem issue 4 years ago
  Megvii Engine Team e92670e820 fix(mgb/atlas): when batchsize more than model max batchsize 4 years ago
  Megvii Engine Team 147dbf8a0c fix(test): fix a race condition in TestCudaMemAlloc 4 years ago
  Megvii Engine Team 7066ad5ba6 feat(dnn): add uint16 support 4 years ago
  Megvii Engine Team a1877ee0fa refactor(dnn): refactor algo interface, use algoinfo instead of global algorithm 4 years ago
  Megvii Engine Team cb59c27835 feat(mlir/ir): add more op definitions 4 years ago
  Megvii Engine Team 9ec8d375f1 feat(externcopr): add config extern c opr dynamic param 4 years ago
  Megvii Engine Team ee4ea7fdc8 test(distributed/test): make distributed test more stronger 4 years ago
  Megvii Engine Team 3ecded74ea refactor(distributed/server): use port 0 to get available port 4 years ago
  Megvii Engine Team 88e918e261 feat(mgb/jit): add scf.ForOp in MgbToGpuLoweringPass 4 years ago
  Megvii Engine Team 7aa54b0ec6 feat(mge): enable memory swap and drop/recomputation 4 years ago
  Megvii Engine Team 6f5d0febf1 perf(dnn/cuda): enhance performance for pooling forward 4 years ago
  Megvii Engine Team 0560a218af chore(dnn/test): refactor megdnn arm_common test 4 years ago
  Megvii Engine Team f7731bd437 fix(mgb/jit): fix a pointer bug in mlir executable_cuda 4 years ago
  Megvii Engine Team 810d8cbaf8 fix(mgb/jit): add cmake target MLIRTosa for latest llvm-project 4 years ago
  Megvii Engine Team 2ad8c5e1e9 fix(mge/io_remote): fix remote send/recv gradient at trace 4 years ago
  Megvii Engine Team f470df4f1a fix(mgb/opr): fix convbias with no bias when weight preprocess 4 years ago
  Megvii Engine Team 6c4841e807 fix(mge/quantization): `disable_fake_quant` does not work correctly 4 years ago
  Megvii Engine Team aa953c3bd6 fix(mge/module): fix missing import 4 years ago
  Megvii Engine Team 5a01de7851 fix(mge): fix scalar transpose 4 years ago
  Megvii Engine Team 6b9ac894d3 fix(mgb/topk): fix topk grad 4 years ago
  Megvii Engine Team 6856ce9ce2 feat(dnn): support conv bias activation for nchw4 input tensor format and nchw output tensor format 4 years ago
  Megvii Engine Team 8536864351 chore(version): fix dev version to a large number 4 years ago
  Megvii Engine Team 61c5c9cf74 chore(cmake): normlize some cmake message level 4 years ago
  Megvii Engine Team 2e87420865 fix(module): fix docs in normalization 4 years ago
  Megvii Engine Team 638ab52fdc feat(mge/imperative): simulates scalar 4 years ago
  Megvii Engine Team 7167fdbd49 feat(mge/module): add normalization module includes group_norm, instance_norm and layer_norm 4 years ago
  Megvii Engine Team 94dba16ff4 perf(mge/imperative): misc optimizations 4 years ago
  Megvii Engine Team 9f139562b4 test(mge): fix requires-test.txt for doctest 4 years ago
  Megvii Engine Team 442058aead feat(mge/quantize): add batch matmul activation module for inference 4 years ago
  Megvii Engine Team 81e0dae4ac docs(mge): update GradManger docs 4 years ago
  Megvii Engine Team 6667100638 feat(mge): use weakref for GradManger.attach 4 years ago
  Megvii Engine Team 75ca5bfe65 feat(mge): remove GradManager.detach until it is ready 4 years ago
  Megvii Engine Team 544b798374 revert: feat(mge/grad_manager): add `clear_grad` method for GradManager 4 years ago
  Megvii Engine Team 176268d20c test(mge): disable gc in leak check 4 years ago
  Megvii Engine Team 5d0f8da46a feat(mgb/jit): add Dimshuffle and lowering passes in jit mlir backend 4 years ago
  Megvii Engine Team 0007b9e09b build(third_party): update llvm-project 4 years ago