1. 08 7月, 2022 1 次提交
  2. 29 6月, 2022 1 次提交
  3. 24 6月, 2022 1 次提交
  4. 05 6月, 2022 1 次提交
  5. 02 6月, 2022 1 次提交
  6. 30 5月, 2022 1 次提交
  7. 14 4月, 2022 1 次提交
  8. 31 3月, 2022 1 次提交
  9. 17 3月, 2022 1 次提交
  10. 22 2月, 2022 1 次提交
  11. 11 2月, 2022 1 次提交
  12. 13 1月, 2022 1 次提交
  13. 27 10月, 2021 1 次提交
  14. 22 10月, 2021 1 次提交
  15. 14 10月, 2021 1 次提交
  16. 22 9月, 2021 1 次提交
  17. 14 9月, 2021 1 次提交
  18. 30 4月, 2021 1 次提交
  19. 25 4月, 2021 2 次提交
    • W
      update lite subgraph api. (#32513) · 92dc9b2b
      Wilber 提交于
      92dc9b2b
    • D
      Nne integration (#32255) · feb2e476
      denglin-github 提交于
      * Add dlnne engine runtime
      
      * Fix log
      
      * Remove <const_cast> and remove unrelated modify with dlnne, +clang-format
      
      * Fix CMakeList format error
      
      * Add copyright message
      
      * Fix dlnne CMakeList.txt
      
      * Add some paddlepaddle_pass to support more networks
      
      * Fix some format bug
      feb2e476
  20. 02 3月, 2021 1 次提交
    • S
      support trt serialize when load model from memory (#31342) · 6404c438
      Shang Zhizhou 提交于
      * support trt serialize when load model from memory
      
      * delete conv_bn_fuse_pass before tensorrt, with which trt serialize engine id is not stable
      
      * Revert "delete conv_bn_fuse_pass before tensorrt, with which trt serialize engine id is not stable"
      
      performance degradation, fix in the future
      
      This reverts commit fa6cd17e60b15df351efda379ddd00e9e9c1fea9.
      
      * add delete conv_bn
      
      * delete path when delete_cache_files
      6404c438
  21. 18 2月, 2021 1 次提交
  22. 25 1月, 2021 1 次提交
  23. 06 1月, 2021 1 次提交
  24. 06 11月, 2020 1 次提交
  25. 03 11月, 2020 1 次提交
    • S
      TensorRT中ernie模型推理性能优化,支持变长输入 (#28367) · ea851796
      Shang Zhizhou 提交于
      * fp16 result ok
      
      * change -DWITH_NVINFER_PLUGIN toconfig.EnableTensorRtOSS
      
      * auto detect special slice op converter for ernie with trt oss
      
      * ernie oss only support fp16
      
      * fix special_slice_plugin serialize bug
      
      * matmul in tensorrt ok
      
      * ernie unittest ok
      
      * add matmul tensorrt unittest
      
      * remove demo code
      ea851796
  26. 16 9月, 2020 1 次提交
  27. 11 9月, 2020 1 次提交
  28. 22 7月, 2020 1 次提交
    • supports xpu runtime, test=develop (#25554) · 72064172
      石晓伟 提交于
      * update ResetHolder, test=develop
      
      * add TensorShare for lite engine, test=develop
      
      * tensor data changed from copying to sharing, test=develop
      
      * supports xpu runtime, test=develop
      
      * fix code styles, test=develop
      72064172
  29. 09 4月, 2020 1 次提交
    • M
      Remove: NGraph engine from PDPD repository (#23545) · 3baaee9a
      mozga-intel 提交于
      * Remove the NGraph engine from PDPD repository
      1. Each operator was removed from the operator's directory
      2. Each test was removed from the unittest directory
      3. The parallel executor support was removed from the PDPD
      4. The CMake file was removed from the PDPD
      5. The NG flags were removed from the repository
      test=develop
      
      * Remove ngraph from:
      1. Cmake file
      2. Python file
      test=develop
      3baaee9a
  30. 26 3月, 2020 1 次提交
    • Z
      [Paddle-TRT]: Ernie Dynamic shape support. (#23138) · 430b0099
      Zhaolong Xing 提交于
      * add dynamic plugin support.
      test=develop
      
      * change emb eltwise layernorm to math function
      test=develop
      
      * add emb eltwise layernorm
      test=develop
      
      * can run dynamic shape ernie
      test=develop
      
      * fix ci
      test=develop
      
      * add ut for trt ernie dynamic
      
      test=develop
      
      * refine dynamic shape c++ interface.
      test=develop
      
      * fix comments
      test=develop
      
      * fix comments
      test=develop
      430b0099
  31. 09 3月, 2020 1 次提交
  32. 24 2月, 2020 1 次提交
  33. 04 2月, 2020 1 次提交
  34. 09 1月, 2020 1 次提交
  35. 07 1月, 2020 1 次提交
  36. 03 1月, 2020 1 次提交
  37. 04 12月, 2019 1 次提交
  38. 26 11月, 2019 1 次提交
    • G
      Add fc padding to improve mkl GEMM's performance when N and K are multiple of 128. (#20972) · 234060f8
      GaoWei8 提交于
      * Add fc padding to solve mkl performance
      test=develop
      
      * fix gpu pass and error information
      test=develop
      
      * fix fc_fuse_pass_test
      test=develop
      
      * fix error information
      test=develop
      
      * fix error information
      test=develop
      
      * fix name and add fc op padding test
      test=develop
      
      * fix attributes
      test=develop
      
      * optimize fc padding
      test=develop
      
      * fix test
      test=develop
      234060f8
  39. 03 9月, 2019 1 次提交
    • Y
      A a pass to enable the use of cudnn (#19346) · c5548178
      Yiqun Liu 提交于
      * Add a interface to enable cudnn for inference.
      
      * Add cudnn_placement_pass.
      test=develop
      
      * Set the default value of cudnn_enabled_op_types to null.
      test=develop
      
      * Write the common basic class, placement_pass_base, to refine the codes.
      test=develop
      
      * Call EnableCUDNN in unittest.
      test=develop
      
      * Refine cudnn_placement_pass tester.
      
      * Enable the testing of cudnn_placement_pass in inference's unittest.
      test=develop
      
      * Add the check of op kernels.
      test=develop
      c5548178