1. 08 3月, 2019 1 次提交
  2. 07 3月, 2019 1 次提交
  3. 06 3月, 2019 1 次提交
    • C
      Fix reshape bug (#16069) · c67afb0f
      chengduo 提交于
      * In some case, the input may have one than one negative value.
      test=develop
      
      * fix matmul bug
      test=develop
      c67afb0f
  4. 04 3月, 2019 4 次提交
  5. 01 3月, 2019 1 次提交
  6. 26 2月, 2019 1 次提交
  7. 24 2月, 2019 5 次提交
  8. 23 2月, 2019 1 次提交
  9. 22 2月, 2019 2 次提交
  10. 19 2月, 2019 4 次提交
  11. 18 2月, 2019 1 次提交
  12. 17 2月, 2019 1 次提交
  13. 15 2月, 2019 1 次提交
  14. 13 2月, 2019 1 次提交
  15. 12 2月, 2019 3 次提交
  16. 03 2月, 2019 1 次提交
  17. 31 1月, 2019 3 次提交
  18. 30 1月, 2019 4 次提交
  19. 28 1月, 2019 1 次提交
  20. 25 1月, 2019 1 次提交
  21. 24 1月, 2019 2 次提交
    • Y
      Add the CUDA kernel for beam_search op (#15020) · 3008fa12
      Yiqun Liu 提交于
      * Refine the beam_search op and test.
      
      * A basic CUDA implementation of beam_search for small batch_size.
      
      * Implement CUDA kernel for beam_search_op.
      
      * Use multiple CUDA threads in the same block to select the top beam.
      
      * Update the python api of beam_search op.
      
      * Enable extend function in CPU kernel of beam_search op.
      
      * Unify the CUDA codes.
      test=develop
      
      * Unify the CPU kernel of beam_search op.
      
      * Ensure the seletced items of beam_search_op's CPU kernel sorted by scores.
      
      * Update the description of beam_search in API.spec.
      
      * Enable the use of CUDA kernel in beam_search op.
      
      * Exclude the beam_search's CUDA unittest when there is no CUDA gpu, and delete some debuging statements.
      test=develop
      
      * Follow comments.
      test=develop
      
      * Call the CPU kernel for beam_search op when batch_size > 4.
      test=develop
      
      * Remove the except of is_empty op in PrepareData.
      test=develop
      3008fa12
    • T
      modified some comments · 78145c7d
      tink2123 提交于
      test=develop
      78145c7d