OpenI
/
MegEngine
Not watched
1
0
Fork 0
Code
Releases 31 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
987 Commits
28 Branches
25 MB
4689 Download
Tree: a78c11099b
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'a78c11099b'
${ noResults }
Commit Graph

987 Commits (a78c11099b85bf8a992259a398f70ca600bc332d)
 

Author SHA1 Message Date
  Megvii Engine Team a78c11099b fix(imperative): add param(axis) for GetVarShape 4 years ago
  Megvii Engine Team cde9727a4f fix(mge/quantization): fix `qat.conv_bn` parameter issue 4 years ago
  Megvii Engine Team 94796060b6 test(mge/quantization): qat module, quantized op and module 4 years ago
  Megvii Engine Team ab9f44f15c feat(mge/quantization): add support for easyquant 4 years ago
  Megvii Engine Team fc0fcd2f7f chore(winograd): remove winograd transform code 4 years ago
  Megvii Engine Team d1adc9a22f fix(dnn): fix opencl algo search 4 years ago
  Megvii Engine Team 368c18607f fix(mgb/jit): find cuda include path correctly 4 years ago
  Megvii Engine Team b04e0466bb feat(megbrain): add alias name to model serialization 4 years ago
  Megvii Engine Team cf53d9e0f8 fix(mgb/tensor): do tensor overlap check only when d2d and h2h 4 years ago
  Megvii Engine Team 7e2b2dbffc fix(dnn/test): delete large size in ARM_COMMON.FP32_GEVM 4 years ago
  Megvii Engine Team 69e3e32240 feat(imperative): auto generated opdef header and python binding 4 years ago
  Megvii Engine Team 0398a7867f fix(build/windows/cuda/llvm): fix windows bazel build with cuda 4 years ago
  Megvii Engine Team b9c37112a2 refactor(mge/distributed): skip barrier when running with single node 4 years ago
  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