1. 28 1月, 2019 6 次提交
  2. 27 1月, 2019 4 次提交
  3. 26 1月, 2019 6 次提交
  4. 25 1月, 2019 22 次提交
  5. 24 1月, 2019 2 次提交
    • X
      support multi grad ops · 4d9feb35
      Xin Pan 提交于
      test=develop
      4d9feb35
    • 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