1. 25 5月, 2020 1 次提交
  2. 08 3月, 2019 2 次提交
  3. 30 1月, 2019 1 次提交
    • Y
      Return parent_idx in beam_search op (#15520) · 16d54f7f
      Yiqun Liu 提交于
      * Refine beam_search_op to output an extra parent_idx tensor.
      test=develop
      
      * Fix the unittest test_beam_search_op.
      test=develop
      
      * Fix the merging mistake.
      test=develop
      16d54f7f
  4. 24 1月, 2019 1 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
  5. 07 6月, 2018 1 次提交
  6. 06 6月, 2018 1 次提交
  7. 21 5月, 2018 1 次提交
  8. 28 4月, 2018 1 次提交
  9. 27 4月, 2018 1 次提交
  10. 23 4月, 2018 2 次提交
  11. 20 4月, 2018 1 次提交
  12. 19 4月, 2018 3 次提交
  13. 18 4月, 2018 2 次提交
  14. 12 2月, 2018 1 次提交
  15. 10 2月, 2018 2 次提交
  16. 09 2月, 2018 1 次提交
  17. 23 1月, 2018 1 次提交
    • Q
      Nmt model (#7340) · e7d44a20
      Qiao Longfei 提交于
      neural machine translation model support beam search with while op
      e7d44a20
  18. 18 1月, 2018 1 次提交
  19. 24 12月, 2017 1 次提交
    • D
      Feature/operator run place (#6783) · 735eba29
      dzhwinter 提交于
      * "change operator interface"
      
      * "move devicepool to device_context"
      
      * "fix operator test"
      
      * "fix op_registry Run interface"
      
      * "net op passed. Need to fix nccl multi-Context"
      
      * "add nccl group function"
      
      * "add nccl group function"
      
      * "fix gpu count exceed 32 error"
      
      * "fix recurrent op, nccl op"
      
      * "change the other operators interface with Place"
      
      * "fix typo"
      
      * "fix pybind"
      
      * "fix device in python side"
      
      * "fix pybind failed"
      
      * "add init for test"
      
      * "fix CI"
      735eba29
  20. 15 11月, 2017 1 次提交