1. 20 10月, 2021 4 次提交
    • S
      Add FasterTokenizer Operator (#34491) · 3f2d6a3f
      Steffy-zxf 提交于
      Add Tokenizer related functionalities for Transformer model in order that the process of training and predicting is consistent.
      
      * support the text string as an input Tensor
      * support the "VOCAB"unordered_map<wstring, int> as an input Tensor to lookup tokens
      * Tokenizer used for BERT. This tokenizer applies an end-to-end, text string to wordpiece tokenization.
      * It first applies basic tokenization, followed by wordpiece tokenization.
      3f2d6a3f
    • W
      add unittest (#36371) · 7325c9fb
      Wilber 提交于
      7325c9fb
    • W
      update for trt convert ut. (#36549) · 06bd348d
      Wilber 提交于
      06bd348d
    • W
      fix (#36557) · 4bd19770
      wenbin 提交于
      * fix
      
      * remove const
      4bd19770
  2. 19 10月, 2021 2 次提交
  3. 18 10月, 2021 2 次提交
  4. 15 10月, 2021 1 次提交
  5. 14 10月, 2021 3 次提交
  6. 13 10月, 2021 2 次提交
    • W
      pool fix (#36388) · 192e08cb
      wenbin 提交于
      * pool fix
      
      * comments
      192e08cb
    • W
      [PaddleInference] Pass: add int8 flag for op (#36042) · d7858c99
      Wangzheee 提交于
      * add_int_pass
      
      * add_int8_flag_pass
      
      * add_int8_flag_pass
      
      * fix CMakeLists.txt
      
      * fix test_trt_fc_fuse_quant_dequant_pass.py
      
      * fix python/paddle/fluid/tests/unittests/ir/inference/test_trt_fc_fuse_quant_dequant_pass.py
      
      * fix test_trt_fc_fuse_quant_dequant_pass.py
      d7858c99
  7. 12 10月, 2021 1 次提交
  8. 11 10月, 2021 3 次提交
  9. 30 9月, 2021 1 次提交
  10. 24 9月, 2021 2 次提交
  11. 23 9月, 2021 2 次提交
  12. 22 9月, 2021 4 次提交
  13. 19 9月, 2021 1 次提交
  14. 18 9月, 2021 1 次提交
  15. 17 9月, 2021 3 次提交
  16. 16 9月, 2021 2 次提交
  17. 15 9月, 2021 6 次提交