1. 08 9月, 2021 1 次提交
    • S
      Slice bug (#35357) · 28abd5d8
      Shang Zhizhou 提交于
      * update slice plugin
      
      * add test
      
      * fix code style
      
      * fix trt6
      
      * update test
      
      * fix test
      
      * add timeout
      
      * update trt version
      
      * update cmake
      28abd5d8
  2. 11 8月, 2021 1 次提交
  3. 05 8月, 2021 1 次提交
  4. 29 7月, 2021 1 次提交
    • W
      Tile supported (#34388) · cffa15c5
      wenbin 提交于
      * tile op
      
      * more uts
      
      * disable tile if trt6.0
      
      * typo
      
      * fix timeout issue
      
      * opteller
      
      * opteller remove duplicate code
      
      * comments.	test=document_fix
      
      * modify PADDLE_ENFORCE.
      
      * fix reduce_mean issue
      cffa15c5
  5. 21 7月, 2021 1 次提交
    • W
      trt reduce_mean supported. (#34204) · aff14962
      wenbin 提交于
      * reduce_mean supported. test=allcase
      
      * ut. test=allcase
      
      * test=develop
      
      * ut.test=allcase
      
      * correct name. test=allcase
      
      * correct UT. test=allcase
      
      * correct UT.test=develop
      
      * remove op
      
      * UT
      
      * add convert
      
      * fix timeout issue
      
      * more uts
      
      * more ut
      
      * correct ut
      aff14962
  6. 08 7月, 2021 1 次提交
  7. 07 7月, 2021 1 次提交
  8. 05 7月, 2021 1 次提交
  9. 15 6月, 2021 1 次提交
  10. 12 6月, 2021 1 次提交
  11. 08 6月, 2021 1 次提交
    • S
      add dynamic layer_norm plugin (#33293) · 45d1ae21
      Shang Zhizhou 提交于
      * add dynamic layer_norm plugin
      
      * fix bug
      
      * fix numpy.allclose
      
      * fix format
      
      * fix code style
      
      * remove shepe in dynamic shape
      
      * code format
      
      * remove layer norm fp16
      
      * fix format
      45d1ae21
  12. 05 6月, 2021 1 次提交
  13. 01 6月, 2021 1 次提交
  14. 28 5月, 2021 1 次提交
    • W
      强化非trt conv判断 (#33150) · e90f3006
      wenbin 提交于
      * add more conditions
      
      * dynamic shape
      
      * ut
      
      * correct contidions
      
      * commnent
      
      * remove rebandadnt op type
      
      * remove rebandant if
      e90f3006
  15. 25 5月, 2021 1 次提交
  16. 08 5月, 2021 1 次提交
    • W
      [Paddle-TRT]fix trt-converter-fc_op (#32671) · 62d848de
      Wangzheee 提交于
      * [Paddle-TRT]fix fc_op
      
      * [Paddle-TRT]fix fc_op
      
      * [Paddle-TRT]fix fc_op
      
      * test_trt_subgraph_pass.py
      
      * fix elementwise_op
      
      * fix elementwise_op
      
      * fix elementwise_op
      
      * fix elementwise_op.cc
      
      * op_teller.cc
      62d848de
  17. 27 4月, 2021 1 次提交
  18. 25 4月, 2021 1 次提交
  19. 23 4月, 2021 2 次提交
    • C
      ernie int8 support trt6 (#32424) · a01b5109
      ceci3 提交于
      a01b5109
    • W
      move semantic checks to op_teller (#32279) · 7c38114f
      wenbin 提交于
      * move semantic checks to op_teller
      
      * more ops
      
      * more ops
      
      * revert block related change
      
      * part1
      
      * revert activation
      
      * remove if
      
      * remove const_cast
      
      * reslove conflict
      
      * remove const_cast
      
      * delete useless var
      
      * replace vlog(1) with vlog(3), replace assert with PADDLE_ENFORCE
      
      * down to 19 files
      7c38114f
  20. 16 4月, 2021 1 次提交
  21. 13 4月, 2021 1 次提交
  22. 06 4月, 2021 1 次提交
  23. 01 4月, 2021 1 次提交
    • Z
      [Paddle-TRT] add anchor generator op plugin (#31730) · b807e408
      zlsh80826 提交于
      * add anchor generator op plugin
      
      * add anchor generator unit_test
      
      * remove dbg info
      
      * remove redundant line
      
      * replace assertion with paddle enforce
      
      * dynamic plugin replaces assertion with paddle enforce
      
      * anchor generator support dynamic shape on spatial axis
      
      * anchor generator test with fp16, dynamic shape
      
      * add anchor generator test all
      
      * add back main
      
      * reduce test input size to not exceed the timelimit of ci
      
      * change super to InferencePassTest for python2 compatibility
      
      * reuse paddle operator anchor generator
      
      * move creator construct to header with default
      
      * add cuda ifdef
      
      * reduce line
      
      * change super to InferencePassTest for python2 compatibility
      
      * fix anchor generator fp16 serialize setting
      
      * split unittest from test_all
      
      * restrict anchor generator input format before version 7234
      
      * anchor generator only support greater than trt7.1
      
      * change min_graph_size to 2
      
      * min_graph size to 3 if dynamic shape
      
      * reduce dynamic shape size to avoid trt search tactic too long to exceed time limit
      
      * remove anchor from fetch list
      
      * anchor generator support all trt version
      
      * fix memory not allocated but if serialized
      b807e408
  24. 30 3月, 2021 1 次提交
  25. 29 3月, 2021 2 次提交
    • Z
      [Paddle-TRT] roi_align_plugin (#31732) · e3a38d79
      zlsh80826 提交于
      * add roi_align_plugin
      
      * add roi align unit_test
      
      * add roi align serialization
      
      * remove roi align static plugin because of batch dim issue
      
      * refine roi align unittest and add fp16/serialization
      
      * add trt roi align condition to op_teller
      
      * refine error message
      
      * remove unnecessary reshape layer
      e3a38d79
    • Z
      [Paddle-TRT] trt affine channel converter (#31628) · bfb5cf55
      zlsh80826 提交于
      * trt affine channel converter
      
      * add trt affine channel base test
      
      * add trt affine channel NHWC
      
      * remove asterisk for python2 compatibility
      
      * trt affine channel converter
      
      * add trt affine channel base test
      
      * add trt affine channel NHWC
      
      * remove asterisk for python2 compatibility
      
      * fix rebase
      
      * move LodTensor to Tensor
      
      * add dbg info
      
      * affine channel converter only support NCHW
      
      * scale,bias are parameters, use create_parameters api
      
      * reduce test input size to not exceed the timelimit of ci
      
      * refine affine channel unittest and add serialization/dynamic test
      
      * change super to InferencePassTest for python2 compatibility
      
      * change super to InferencePassTest for python2 compatibility
      
      * fix affine channel fp16 serialize setting
      bfb5cf55
  26. 26 3月, 2021 1 次提交
    • Z
      [Paddle-TRT] multiclass nms (#31742) · 01aa2526
      zlsh80826 提交于
      * add multiclass_nms
      
      * add multiclass_nms unittest
      
      * add default enable_tensorrt_oss option
      
      * refine multiclas nms unittest and add serialization/dynamic test
      
      * change super to InferencePassTest for python2 compatibility
      
      * refine multiclass nms unittest
      
      * move out dynamic shape test due to ci timelimit
      01aa2526
  27. 23 3月, 2021 1 次提交
    • S
      fix tensorrt output varible reshape (#31733) · 9d04ef73
      Shang Zhizhou 提交于
      * fix tensorrt output varible reshape
      
      * move padding shape x 1 x 1 in ernie to qkv and fc
      
      * update layer name
      
      * fix softmax when input is dynamic, fc not padding any more
      
      * fix varlen
      
      * move fc x_dim assert to op_teller
      9d04ef73
  28. 22 3月, 2021 1 次提交
    • Z
      [Paddle-TRT] nearest_interp op (#31626) · bfced39e
      zlsh80826 提交于
      * nearest_interp op converter w/ dynamic/static
      
      * fix data_layout include
      
      * add trt nearest unit_test
      
      * add nearest_interp NHWC test
      
      * update trt nearest interp nhwc testcase
      
      * remove asterisk for python2 compatibility
      
      * add empty line to prevent conflict
      
      * nearest_interp op converter w/ dynamic/static
      
      * fix data_layout include
      
      * add trt nearest unit_test
      
      * add nearest_interp NHWC test
      
      * update trt nearest interp nhwc testcase
      
      * remove asterisk for python2 compatibility
      
      * add empty line to prevent conflict
      
      * change the priority of out_h, out_w
      bfced39e
  29. 18 3月, 2021 2 次提交
  30. 03 3月, 2021 1 次提交
  31. 02 3月, 2021 1 次提交
  32. 24 2月, 2021 1 次提交
    • P
      [Paddle-TRT] support group_norm (#31040) · 00b09e86
      Pei Yang 提交于
      * add group norm plugin
      
      * fix compile problems
      
      * move concat axis check to trt op teller
      
      * add nbDims for scale and bias nv dims
      
      * add group norm unit test
      
      * fix unittest
      
      * add trt version restriction for group norm op teller
      
      * fix unittest
      00b09e86
  33. 18 2月, 2021 1 次提交
  34. 04 2月, 2021 1 次提交
  35. 13 1月, 2021 1 次提交
    • A
      Added support for inference using quantization aware trained dygraph (#30288) · 7bbf3ac5
      alncat 提交于
      * added support for inference using qunatization aware trained dygraph
      
      * added support for inference using qunatization aware trained dygraph
      correct boost get usage
      
      * Delete incorrect warning message (#30196)
      
      * fix warning and no grad
      
      * clean redundant API alias in 2.0 - part 2 (#30013)
      
      * delete paddle.nn.functional.assign
      
      * fix dynamic to static error
      
      * just add the op error message for the matmul xpu (#30246)
      
       add the op error message for the matmul xpu
      
      * Add Static Variable Clone (#30208)
      
      Add clone method for static Variable so that this interface will be same as dygraph. It fixed some bugs in dy2stat
      
      * use wget to replace curl to download the lcov file (#30229)
      
      * use wget to replace curl to download the lcov file
      
      * add cache for lcov
      
      * fix test_pool3d_op timeout issue (#30248)
      
      * Fix unittests bugs. (#30250)
      
      * modify error message based on comments (#30189)
      
      * modify error message based on comments
      
      * edit code according to review.
      
      * Correct spelling according to review.
      
      * Fix bug for 'save mutiple method' (#30218)
      
      * Fix bug for 'save mutiple method'
      
      * To pass coverage.
      
      * edit code to pass coverage.
      
      * edit code to pass coverage.
      
      * add unittest for coverage.
      
      * change for coverage.
      
      * edit for coverage.
      
      * added support for inference using qunatization aware trained dygraph
      
      * Alias from  paddle.fluid.layers.auc to paddle.static.auc (#30206)
      
      * add alias from  fluid.layers.auc to static.auc
      
      * Update __init__.py
      
      * added support for inference using qunatization aware trained dygraph
      correct boost get usage
      
      * corrected boost get usage
      
      * corrected naming issues and enforcing zero check
      
      * correct paddle enforce message
      
      * added more error checkings
      
      * corrected error report message and optimized code
      
      * corrected findvar usage
      
      * corrected paddle_enforce in scope
      
      * correct error messages
      
      * correct error reporting format
      Co-authored-by: NLielinJiang <50691816+LielinJiang@users.noreply.github.com>
      Co-authored-by: NXiaoguangHu <46782768+XiaoguangHu01@users.noreply.github.com>
      Co-authored-by: Nwawltor <fangzeyang0904@hotmail.com>
      Co-authored-by: NHuihuang Zheng <zhhsplendid@gmail.com>
      Co-authored-by: NYUNSHEN XIE <1084314248@qq.com>
      Co-authored-by: NBai Yifan <me@ethanbai.com>
      Co-authored-by: Ngongweibao <weibao.gong@gmail.com>
      Co-authored-by: NWeiXin <weixin10@baidu.com>
      Co-authored-by: NJiaqi Liu <liujiaqi06@baidu.com>
      7bbf3ac5
  36. 07 12月, 2020 1 次提交
  37. 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