Skip to content

MegEngine
MegEngine

MegEngine 天元 / MegEngine
1 年多 前同步成功

通知 404
Star 4705
Fork 582
MegEngine
MegEngine
切换分支/标签
  1. 11 8月, 2022 1 次提交
  3. 04 8月, 2022 1 次提交
  5. 20 5月, 2022 1 次提交
  7. 03 4月, 2022 1 次提交
  9. 01 4月, 2022 1 次提交
  11. 04 3月, 2022 1 次提交
  13. 07 1月, 2022 1 次提交
  15. 27 12月, 2021 1 次提交
  17. 16 12月, 2021 2 次提交
  19. 14 12月, 2021 2 次提交
  21. 26 11月, 2021 2 次提交
  23. 17 11月, 2021 1 次提交
  25. 15 11月, 2021 2 次提交
  27. 05 11月, 2021 1 次提交
  29. 15 9月, 2021 1 次提交
  31. 11 9月, 2021 1 次提交
  33. 06 9月, 2021 1 次提交
    • M
      fix(cmake/llvm): fix llvm build if env install llvm-12-dev · 28c066ee
      由 Megvii Engine Team 提交于 
      now, we do not depends LLVM_ENABLE_BINDINGS and LLVM_INCLUDE_DOCS module
so disable it! if later depends on this module, need upgrade
third_party/llvm-project/ to 12 to compat build env which install
llvm-12-dev

GitOrigin-RevId: 62164c0e7f0b3bb296c4b76a2a3eadd31c266421
      28c066ee
  35. 07 8月, 2021 2 次提交
    • M
      feat(cmake/windows/xp/sp2/inference): implement inference on windows xp · ce2f620e
      由 Megvii Engine Team 提交于 
      (os vesion >= sp2) build with cmake

* cmake build support(xp sp2):
(dbg)EXTRA_CMAKE_ARGS="-DMGE_DEPLOY_INFERENCE_ON_WINDOWS_XP_SP2=ON"
./scripts/cmake-build/host_build.sh -m -d

(opt)EXTRA_CMAKE_ARGS="-DMGE_DEPLOY_INFERENCE_ON_WINDOWS_XP_SP2=ON"
./scripts/cmake-build/host_build.sh -m

* cmake build support(xp sp3):
(dbg)EXTRA_CMAKE_ARGS="-DMGE_DEPLOY_INFERENCE_ON_WINDOWS_XP=ON"
./scripts/cmake-build/host_build.sh -m -d

(opt)EXTRA_CMAKE_ARGS="-DMGE_DEPLOY_INFERENCE_ON_WINDOWS_XP=ON"
./scripts/cmake-build/host_build.sh -m

* internal behavior:
will define MGB_HAVE_THREAD=0 when enable
-DMGE_DEPLOY_INFERENCE_ON_WINDOWS_XP_SP2=ON

* refer to
https://docs.microsoft.com/en-us/cpp/build/configuring-programs-for-windows-xp?view=msvc-160
xp sp2(x86) do not support vc runtime fully, casused by KERNEL32.dll do not
implement some base apis for c++ std function, for example,
std::mutex/std::thread/std::condition_variable as a workround, we will
disable some MegEngine features on xp sp2 env, for exampe, multi-thread etc!

* about DNN_MUTEX/MGB_MUTEX/LITE_MUTEX, if your code will build in inference
code (even CPU backends), please replace std::mutex to DNN_MUTEX/MGB_MUTEX,

* about multi-thread, if you code need multi-thread support, please
enable it when MGB_HAVE_THREAD=1

* about test build env status
1: Visual Studio 2019(MSVC version <= 14.26.28801)---- pass
2: Visual Studio 2019(MSVC version > 14.26.28801) ---- failed
   caused by this 'new' version will put VCR depends on win7
   KERNEL32.DLL, this may be fixed at Visual Studio 2019 later version
   but we do not test at this MR merge point
3: Visual Studio 2017   ---------- pass
4: Visual Studio 2014   ---------- pass
GitOrigin-RevId: ea6e1f8b4fea9aa03594e3af8d59708b4cdf7bdc
      ce2f620e
    • M
      feat(imperative): add support for quantized conv transpose2d · 3eb0505f
      由 Megvii Engine Team 提交于 
      GitOrigin-RevId: ffd6431299b2ae008fbdd1eed6458437e6b6a45f
      3eb0505f
  37. 03 6月, 2021 2 次提交
  39. 25 5月, 2021 2 次提交
  41. 22 3月, 2021 2 次提交
    • M
      feat(cmake/arm/cuda): support cmake arm with cuda, · 914af286
      由 Megvii Engine Team 提交于 
      * support arm-host and x86-cross-arm
* fix trt myelib cmake build issue at 'trt copy env'(about 'copy env', Please refs cb92123f)

about x86-cross-arm CUDA env:
1: run ./scripts/cmake-build/create_cuda_build_libs.py to prepare
   cuda/cudnn/trt env(download deb package info, Please refs create_cuda_build_libs.py)
2: export TRT_ROOT_DIR=xxxxx which may create by step 1
3: export CUDNN_ROOT_DIR=xxxx which may create by step 1
4: export PATH=xxxx:$PATH  xxxx need create by step 1, which nvcc have
   relative path dir: ../targets/sbsa-linux/
GitOrigin-RevId: 440c76052aabe5b07a4b64d126e759f919c257a8
      914af286
    • M
      build(cuda): support cu111 build · 0e3a6329
      由 Megvii Engine Team 提交于 
      GitOrigin-RevId: b3067ba4d5f1225048838e4b2460d858c475b75e
      0e3a6329
  43. 02 2月, 2021 1 次提交
    • M
      fix(cmake/cuda): fix build at cuda `copy` env caused by b278a69e1 · 329306b0
      由 Megvii Engine Team 提交于 
      `copy` env vs `normal` env:
case a:`normal` env install CUDNN/TRT by package tool, eg, apt/yum, which
will put include file(cudnn.h/NvInfer.h) to /usr/include etc.

case b: self copy env after export CPATH with cudnn/trt include dir

case c: just copy libs, not export CPATH, only export
TRT_ROOT_DIR/CUDNN_ROOT_DIR

at case a and case b, BUILD system can find cudnn/trt headers, but
at case c, can not find. `FIX` it!

what`s more, recommend install CUDA env by case a and case c, NOT
recommend install by case b, which caused by CUDA SDK CPATH not
friendly to split c env, for example Android AOSP build env

GitOrigin-RevId: cb92123f9e58d730893fff45602d3e487b38d32c
      329306b0
  45. 04 12月, 2020 1 次提交
  47. 27 11月, 2020 1 次提交
  49. 13 11月, 2020 1 次提交
  51. 05 11月, 2020 2 次提交
  53. 26 10月, 2020 1 次提交
  55. 17 9月, 2020 3 次提交
  57. 16 9月, 2020 1 次提交