Paddle

Author	SHA1	Message	Date
Yiqun Liu	3008fa1261	Add the CUDA kernel for beam_search op (#15020 ) * 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	7 years ago
Tao Luo	e0d4e04bdd	fix some compiler warning test=develop	7 years ago
minqiyang	9725db0d40	Fix copy wrong pos bug test=develop	7 years ago
minqiyang	14ebc424d6	Add gpu support for unittest	7 years ago
minqiyang	bd5a82e193	Polish unit test code	7 years ago
minqiyang	047fa2f9aa	Add unit-test for sequence_pooling functor	7 years ago