Commit Graph

163 Commits (febc07f047bfa2596de644675fa0a71de324c18d)

Author SHA1 Message Date
Zhaolong Xing 61221ebc28
TRT: Support set dynamic range in int8 mode. (#17524)
6 years ago
Zhaolong Xing 38da103034 fix trt ci bug temporary. (#17565)
6 years ago
Tao Luo 3d19f44a89
remove unused SERIAL compiler option (#17500)
6 years ago
nhzlx bc6b0ca1f4 fix trt anakin subgraph compile rely
6 years ago
nhzlx 084310f536 paddle-anakin: concat, split, pool2d converter#16003
6 years ago
Yan Chunwei d0ce6a9044 fix anakin converter registry (#15993)
6 years ago
nhzlx 06a088a199 fix comments and fix cpplint
6 years ago
nhzlx 0ed63b2108 6. delete useless predictor id
6 years ago
nhzlx 1d5ef7c9ee 5. add static trt load model
6 years ago
nhzlx 2070fb246d 4. do the trt_engine optim during init.
6 years ago
nhzlx ecc12fb430 3. when runing in trt mode, do not allocate memory for parameters in fluid.
6 years ago
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
6 years ago
nhzlx b938324381 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_int8_ultimate_version
6 years ago
nhzlx 312fe0ece1 add trt int8 calibration support
6 years ago
Zhaolong Xing 98e85f3735 add_transpose_flatten_concat_fuse (#15121)
6 years ago
nhzlx c1264e99f3 fix win error
6 years ago
nhzlx 4e3522e5b4 add trt int8 support
6 years ago
Yan Chunwei 6ccf8685f7
refactor tensorrt node teller (#15181)
6 years ago
nhzlx 96216052d5 1. fix trt multi thread bug
6 years ago
Zhaolong Xing bc6d0a3427
Merge pull request #14762 from NHZlX/fix_bug_of_trt_pool
6 years ago
nhzlx 019e8bbed2 fix comments test=develop
6 years ago
nhzlx 722b0a805f fix bug of trt pool
6 years ago
nhzlx f75815b78c add prelu gpu inference
6 years ago
minqiyang 53433d7f2e Revert the changes of VLOG
6 years ago
hjchen2 1adda8e06c Add more unit tests for split plugin
6 years ago
hjchen2 6eba5bd276 Fix direct copy and refine split ut
6 years ago
hjchen2 5857fb3014 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop
6 years ago
hjchen2 3e3599f3d9 Refine split tensorrt plugin
6 years ago
nhzlx e62872df8b fix conflicts
6 years ago
Houjiang Chen 33c65517fd Update CMakeLists.txt test=develop
6 years ago
Houjiang Chen 01bda73116
Update CMakeLists.txt
6 years ago
hjchen2 2c2a192eb1 Resolve merge conflicts
6 years ago
Yiqun Liu 8bc1c5d2ab
Implement the Tensorrt plugin for elementwise op (#14487)
6 years ago
hjchen2 1622cb9937 Fix alpha tensor key
6 years ago
hjchen2 a8c077df7c Implement leaky relu tensorRT converter
6 years ago
hjchen2 2825685f2a Fix tensorrt plugin cmake dependency, test=develop
6 years ago
Wu Yi a2d9b34417
Refine operator cmake (#14413)
6 years ago
nhzlx 8f9a8c455a delete unused test code.
6 years ago
nhzlx 83f8c403a7 Merge branch 'develop' of https://github.com/paddlepaddle/paddle into fix_avg_pool_trt_bug
6 years ago
nhzlx b969116988 fxi avg pool trt bug and fix cpplint
6 years ago
hjchen2 6a7b995737 Refine commit message to enable ci, test=develop
6 years ago
hjchen2 413f5948b2 Fix code style
6 years ago
hjchen2 21f33b4274 Complete PRelu plugin and Conv2d transpose op converter
6 years ago
nhzlx 15bdb7ef14 delete error uploaded files
6 years ago
nhzlx ddb120357c Merge branch 'develop' of https://github.com/paddlepaddle/paddle into add_trt_plugin
6 years ago