Commit Graph

202 Commits (a8c0fb4e866d58b176c7367242bd307e0d07b023)

Author SHA1 Message Date
nhzlx 9cc6249cd6 2. TRTEngine using stream only when execute.
6 years ago
nhzlx 034ba1c291 add static model load for trt
6 years ago
Yan Chunwei 655179089f
AnalysisConfig remove contrib namespace (#15540)
6 years ago
nhzlx 027d24c831 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_int8_ultimate_version
6 years ago
nhzlx ec213730bc fix trt stream bug.
6 years ago
nhzlx 8817841c73 fix unit test bug
7 years ago
nhzlx b938324381 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_int8_ultimate_version
7 years ago
nhzlx 312fe0ece1 add trt int8 calibration support
7 years ago
Zhaolong Xing 98e85f3735 add_transpose_flatten_concat_fuse (#15121)
7 years ago
nhzlx c1264e99f3 fix win error
7 years ago
nhzlx 4e3522e5b4 add trt int8 support
7 years ago
Yan Chunwei 6ccf8685f7
refactor tensorrt node teller (#15181)
7 years ago
nhzlx 96216052d5 1. fix trt multi thread bug
7 years ago
Zhaolong Xing bc6d0a3427
Merge pull request #14762 from NHZlX/fix_bug_of_trt_pool
7 years ago
nhzlx 019e8bbed2 fix comments test=develop
7 years ago
nhzlx 722b0a805f fix bug of trt pool
7 years ago
nhzlx f75815b78c add prelu gpu inference
7 years ago
minqiyang 53433d7f2e Revert the changes of VLOG
7 years ago
hjchen2 1adda8e06c Add more unit tests for split plugin
7 years ago
hjchen2 6eba5bd276 Fix direct copy and refine split ut
7 years ago
hjchen2 5857fb3014 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop
7 years ago
hjchen2 3e3599f3d9 Refine split tensorrt plugin
7 years ago
nhzlx e62872df8b fix conflicts
7 years ago
Houjiang Chen 33c65517fd Update CMakeLists.txt test=develop
7 years ago
Houjiang Chen 01bda73116
Update CMakeLists.txt
7 years ago
hjchen2 2c2a192eb1 Resolve merge conflicts
7 years ago
Yiqun Liu 8bc1c5d2ab
Implement the Tensorrt plugin for elementwise op (#14487)
7 years ago
hjchen2 1622cb9937 Fix alpha tensor key
7 years ago
hjchen2 a8c077df7c Implement leaky relu tensorRT converter
7 years ago
hjchen2 2825685f2a Fix tensorrt plugin cmake dependency, test=develop
7 years ago
Wu Yi a2d9b34417
Refine operator cmake (#14413)
7 years ago
nhzlx 8f9a8c455a delete unused test code.
7 years ago
nhzlx 83f8c403a7 Merge branch 'develop' of https://github.com/paddlepaddle/paddle into fix_avg_pool_trt_bug
7 years ago
nhzlx b969116988 fxi avg pool trt bug and fix cpplint
7 years ago
hjchen2 6a7b995737 Refine commit message to enable ci, test=develop
7 years ago
hjchen2 413f5948b2 Fix code style
7 years ago
hjchen2 21f33b4274 Complete PRelu plugin and Conv2d transpose op converter
7 years ago
nhzlx 15bdb7ef14 delete error uploaded files
7 years ago
nhzlx ddb120357c Merge branch 'develop' of https://github.com/paddlepaddle/paddle into add_trt_plugin
7 years ago
Yan Chunwei 9f252e0032
Combine Inference Analysis with IR (#13914)
7 years ago
nhzlx 0b96268057 fix comments
7 years ago
nhzlx e5bf8616f0 Merge branch 'develop' of https://github.com/paddlepaddle/paddle into add_trt_plugin
7 years ago
nhzlx d38fd6a0fc add plugin support and offer an simple split sample
7 years ago
nhzlx 2d7134bc37 add initial code for plugin
7 years ago
nhzlx d6ff006903 add serial to trt test and do not print log for unused trt logs
7 years ago
Qiyang Min 698698f2fa
Merge branch 'develop' into fix_vlog
7 years ago
qingqing01 abe209234f
Exhaustive search for cuDNN conv. (#14286)
7 years ago
minqiyang 0c3227a523 Change the origin VLOG level to 10 times
7 years ago
nhzlx 5700fafd0f Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_googlenet_bug_with_rule
7 years ago
nhzlx 86b99ac953 fix comments and fix bug
7 years ago
nhzlx 2b5edfbc37 Add ceil model pooling for trt (ocr attention)
7 years ago
nhzlx 9d98ca0424 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_googlenet_bug_with_rule
7 years ago
nhzlx 849a6874ad fix googlenet bug with relu
7 years ago
nhzlx 0cb88c34be add op converter
7 years ago
nhzlx d40402f9b7 add dropout and sigmoid op converter
7 years ago
nhzlx 0092ad3285 delete unused log
7 years ago
nhzlx 49bafc05bf fix comments and set name for trt layer and ITensor
7 years ago
nhzlx 3de4556659 concat op && map cnn model support
7 years ago
nhzlx ff052c0e6f merge develop
7 years ago
nhzlx c6a5c4b0c0 add comments for execute in ut_helper
7 years ago
luotao1 808e5b1748 fix tensorrt compiler bug
7 years ago
nhzlx 1bf9d9e90c fix comments
7 years ago
nhzlx 144b20c160 add batch norm op converter
7 years ago
nhzlx 14311bb094 merge develop
7 years ago
Zhaolong Xing e5674f6dde
Merge pull request #12753 from NHZlX/add_benchmark
7 years ago
nhzlx 1e92baf746 fix comments
7 years ago
nhzlx ce7f361a80 fix comments
7 years ago
nhzlx df9cbabcee add pool2d test for global_pooling true
7 years ago
nhzlx 133ec69625 add batch norm trt converter
7 years ago
nhzlx 2bdd20be22 add support for global pooling for trt
7 years ago
nhzlx 1600ba86f6 1. change tensorrt op from cpu to gpu
7 years ago
nhzlx 641f32da8c add softmax op converter
7 years ago
nhzlx 32a9e050bc mapping the variable name inside the subgraph
7 years ago
nhzlx d50f776b27 merge develop
7 years ago
nhzlx 64a08f840f increase the test batch
7 years ago
nhzlx c7e6a11bc1 merge develop
7 years ago
nhzlx 0015df1b12 modify op converter for conv2d
7 years ago
gongweibao 819ac3df0a
Modify style (#12465)
7 years ago
nhzlx 5fcdd81da7 tiny modify
7 years ago
nhzlx f05c7fb8ae Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_tensorrt_conv2d_converter
7 years ago
nhzlx 6f6d552790 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_tensorrt_conv2d_converter
7 years ago
Luo Tao 062556f938 Merge branch 'develop' into unify
7 years ago
nhzlx 98948b975e wrong added file
7 years ago
nhzlx 830aa12c1a add elementwise init code
7 years ago
nhzlx 4f71a3b12b fix a bug
7 years ago
nhzlx c8adfb3451 add paddle_enforce
7 years ago
nhzlx 5533400720 fix comments
7 years ago
Luo Tao 5ba4337698 unify libpaddle_inference_api into libpaddle_fluid
7 years ago
nhzlx 01566fb61b 1. support mutil batch utest 2. support pool op
7 years ago
nhzlx 990741aa85 add weight's dim assert
7 years ago
nhzlx 21890ca0cf Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_tensorrt_pooling_converter
7 years ago
nhzlx fc41eb40b1 add conv2d trt converter
7 years ago
nhzlx 4d49e61ab8 fix comments
7 years ago
nhzlx bcd67bdd71 add assert for GetOutput
7 years ago
nhzlx 7382f98600 1. set ut batch > 1 2. readd the mul op(utest will be added later)
7 years ago
nhzlx bd64979fe9 the argument should not be a const one
7 years ago
nhzlx f42ea48996 deal with conflict
7 years ago
nhzlx 82527696e7 1. we delelte mul op, 2.modify fc and action op 3. modify the test inferface
7 years ago
nhzlx 2372daff1d there is no batchsize concept in tensorrt's tensor
7 years ago
Yan Chunwei b42ced8eda
bugfix/tensorrt analysis fix subgraph trigger (#12266)
7 years ago