1. 24 3月, 2021 1 次提交
  2. 07 12月, 2020 1 次提交
    • S
      cherry-pick PR #27933 (#29377) · 9a6ecb03
      Shang Zhizhou 提交于
      * cherry-pick PR #27933
      
      * fix: cuda version is in varibale CUDA_VERSION in 1.8 cuda.cmake
      
      * close unittest failed temporarily
      
      * cherry-pick PR #27544, fix layer_norm and softmax bug in tensorRT
      9a6ecb03
  3. 10 2月, 2020 1 次提交
  4. 25 5月, 2019 1 次提交
    • Z
      TRT: Support set dynamic range in int8 mode. (#17524) · 61221ebc
      Zhaolong Xing 提交于
      * fluid int8 train and trt int8 predict align.
      trt int8 predict init
      op converter
      
      * 2. align fluid int8 train and trt int8 inference.
      enhance quant dequant fuse pass
      enhance op converter, trt engine, trt engine op, trt subgraph pass.
      
      * 3. add delete_quant_dequant_pass for trt
      
      test=develop
      
      * 4. add the missing file
      test=develop
      
      * 5. i modify the c++ interface, but forget to modify the pybind code
      fix the IS_TRT_VERSION_GE bug, and fix elementwise op converter
      test=develop
      61221ebc
  5. 12 11月, 2018 1 次提交
  6. 08 11月, 2018 1 次提交
  7. 09 8月, 2018 1 次提交
  8. 25 7月, 2018 1 次提交
  9. 24 7月, 2018 2 次提交
  10. 07 6月, 2018 2 次提交
  11. 06 6月, 2018 1 次提交
  12. 01 6月, 2018 1 次提交
  13. 14 5月, 2018 1 次提交
  14. 03 5月, 2018 1 次提交
  15. 27 4月, 2018 1 次提交
  16. 25 4月, 2018 2 次提交
  17. 23 4月, 2018 1 次提交
  18. 26 2月, 2018 2 次提交
  19. 12 2月, 2018 1 次提交
  20. 10 2月, 2018 2 次提交
  21. 09 1月, 2018 1 次提交
    • Y
      Port WarpCTC Operator (#5107) · b5fda272
      Yiqun Liu 提交于
      * Add Seq2BatchFunctor, which will be used in WarpCTCOp.
      
      * Implement WrapCTCFunctor and WrapCTCKernel.
      
      * Add unittest of warpctc_op.
      
      * Modify the check_output inferface in python unittest framework to allow check a subset of outputs.
      
      * Use absolute offset lod in warpctc_op and related functors.
      
      * Refine the comments of warpctc_op.
      
      * The new python unittest supports checking a subset of the outputs, so revoke the previous change.
      
      * Rename the transform from LoDTensor to Tensor with shape [max_sequence_length, num_sequences, sequence_width] to PaddingSequenceFunctor.
      
      * Update to the newest codes.
      
      * Rename the PaddingSequenceFunctor to PaddingLoDTensorFunctor and remove the computation of dimensions out of the functos.
      b5fda272
  22. 04 8月, 2017 1 次提交
  23. 11 7月, 2017 1 次提交