1. 20 3月, 2019 1 次提交
  2. 18 3月, 2019 1 次提交
  3. 08 3月, 2019 1 次提交
  4. 29 1月, 2019 2 次提交
  5. 18 12月, 2018 1 次提交
  6. 07 12月, 2018 1 次提交
  7. 27 11月, 2018 1 次提交
  8. 18 11月, 2018 1 次提交
  9. 16 11月, 2018 1 次提交
    • J
      Squashing MKL based softmax for inference · 513bb6c1
      Jacek Czaja 提交于
      test=develop
      
      - Added profiling to softmax functors
      
      - MKL based softmax inference op
      
      - Fix to softmax compuation via MKL
      
      - cleaning
      
      - Cosmetic fixes to softmax MKL
      
      - Fix to ON_INFER lack of propagation
      513bb6c1
  10. 14 11月, 2018 2 次提交
  11. 09 11月, 2018 2 次提交
  12. 07 4月, 2018 1 次提交
  13. 12 2月, 2018 1 次提交
  14. 10 2月, 2018 2 次提交
  15. 12 12月, 2017 1 次提交
    • Q
      Refine device context (#6433) · 61ec0b95
      QI JUN 提交于
      There are mainly following fixes:
      
      - take `DeviceContext` as the template parameter of math functors and OpKernel instead of `Place`
      - remove `eigen_device` interface in base class  `DeviceContext`
      - remove `GetEigenDevice` interface in `ExecutionContext` and base class `DeviceContext`
      - remove unused `platform::EigenDeviceConverter`
      - rename `REGISTER_OP_GPU_KERNEL` to `REGISTER_OP_CUDA_KERNEL`
      - rename `USE_GPU_ONLY_OP` to `USE_CUDA_ONLY_OP`
      61ec0b95
  16. 13 11月, 2017 1 次提交