Commit Graph

259 Commits (c407dfa3cb5607683e78c5f2aaecc1065ad07d1a)

Author SHA1 Message Date
nhzlx a25331bc26 cherry-pick from feature/anakin-engine: deal the changing shape when using anakin 6 years ago
nhzlx c79f06d3d8 cherry-pick from feature/anakin-engine: add batch interface for pd-anakin 6 years ago
nhzlx 69d37f81d7 cherry-pick from feature/anakin-engine: refine anakin subgraph. 6 years ago
nhzlx a1d200a5de cherry-pick from feature/anakin-engine: Anakin support facebox 6 years ago
nhzlx b21770a2aa cherry-pick from feature/anakin-engine: Add subgraph fuse support and anakin engine 6 years ago
Wojciech Uss 2579ade45f Add cpu_quantize_pass for C-API quantization () 6 years ago
nhzlx a9ed427749 cant not pass ci 6 years ago
nhzlx 2eff3e26b6 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_static_model_load_for_trt 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
Wojciech Uss daac6a05f5 Removed duplicated code 6 years ago
nhzlx 034ba1c291 add static model load for trt 6 years ago
Gabor Buella da9c94da33 Clang build fixes () 6 years ago
wopeizl 3614dadf23
Merge pull request from wopeizl/windows/fixci 6 years ago
peizhilin 061299be87 fix dependency 6 years ago
Gabor Buella 2bf63f4c33 Fix std::abs usage in memory_optimize_pass.cc () 6 years ago
Yan Chunwei e887d71958
fix ir debug config () 6 years ago
Jiabin Yang 075df09f86
Merge pull request from JiabinYang/feature/imperative 6 years ago
Yan Chunwei 655179089f
AnalysisConfig remove contrib namespace () 6 years ago
JiabinYang 2e309b11c2 test=develop, merge develop 6 years ago
JiabinYang 53d558cd41 test=develop, polish code and merge develop 6 years ago
Zhaolong Xing 97b76c94c4
Merge pull request from NHZlX/trt_int8_ultimate_version 6 years ago
nhzlx b43ea40c51 delete the usage of the const_cast 6 years ago
Yan Chunwei e2818c8608
add dynamic memory optim () 6 years ago
nhzlx 92cf4a4c6b fix comments 6 years ago
nhzlx 0779e35544 fix two bug: 6 years ago
nhzlx 027d24c831 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_int8_ultimate_version 6 years ago
tensor-tang 5c68dee798 fix debug compile of analysis pass fail 6 years ago
Yan Chunwei 885c4e57ab
fea/infer memory optim2 () 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
nhzlx 4e3522e5b4 add trt int8 support 6 years ago
Tao Luo feee78d9f0
Merge pull request from tensor-tang/fix/debug 6 years ago
Tao Luo 9c02765158
Merge pull request from Superjomn/fix/analysis_tester_bug 6 years ago
tensor-tang 69fd3fdb52 fix debug build error 6 years ago
superjomn 23bdd0a223 fix analysis_tester bug 6 years ago
Yan Chunwei 6ccf8685f7
refactor tensorrt node teller () 6 years ago
Zhaolong Xing 4048cfa9da
Merge pull request from NHZlX/add_affine_channel_fuse 6 years ago
nhzlx 71636e677d add min_subgraph_size attr to tensorrt config 6 years ago
nhzlx a6aa8ea771 faster rcnn input is presistable. (fix it in paddle-trt) 6 years ago
minqiyang b1d0a14c14 Change the ut back 6 years ago
minqiyang 7d1533216d Fix syntax error in unit test 6 years ago
nhzlx 050a68dde3 fix comments 6 years ago
superjomn edd1f5a92b fix visualizer 6 years ago
bingyanghuang 943ad4781f One possible solution to add flexibility for mkldnn placement pass () 6 years ago
Tao Luo 743cb840f1 update with comments 6 years ago
Tao Luo 923b18877e Merge branch 'develop' into memory_load 6 years ago