Commit Graph

260 Commits (07dcf2856cdf49af2415432c07dea6545992940d)

Author SHA1 Message Date
nhzlx 07dcf2856c git cherry-pick from feature/anakin-engine: update anakin subgraph #16278
7 years ago
nhzlx a25331bc26 cherry-pick from feature/anakin-engine: deal the changing shape when using anakin #16189
7 years ago
nhzlx c79f06d3d8 cherry-pick from feature/anakin-engine: add batch interface for pd-anakin #16178
7 years ago
nhzlx 69d37f81d7 cherry-pick from feature/anakin-engine: refine anakin subgraph. #16157
7 years ago
nhzlx a1d200a5de cherry-pick from feature/anakin-engine: Anakin support facebox #16111
7 years ago
nhzlx b21770a2aa cherry-pick from feature/anakin-engine: Add subgraph fuse support and anakin engine #16018
7 years ago
Wojciech Uss 2579ade45f Add cpu_quantize_pass for C-API quantization (#16127)
7 years ago
nhzlx a9ed427749 cant not pass ci
7 years ago
nhzlx 2eff3e26b6 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_static_model_load_for_trt
7 years ago
nhzlx 06a088a199 fix comments and fix cpplint
7 years ago
nhzlx 0ed63b2108 6. delete useless predictor id
7 years ago
nhzlx 1d5ef7c9ee 5. add static trt load model
7 years ago
nhzlx 2070fb246d 4. do the trt_engine optim during init.
7 years ago
nhzlx ecc12fb430 3. when runing in trt mode, do not allocate memory for parameters in fluid.
7 years ago
Wojciech Uss daac6a05f5 Removed duplicated code
7 years ago
nhzlx 034ba1c291 add static model load for trt
7 years ago
Gabor Buella da9c94da33 Clang build fixes (#15628)
7 years ago
wopeizl 3614dadf23
Merge pull request #15631 from wopeizl/windows/fixci
7 years ago
peizhilin 061299be87 fix dependency
7 years ago
Gabor Buella 2bf63f4c33 Fix std::abs usage in memory_optimize_pass.cc (#15627)
7 years ago
Yan Chunwei e887d71958
fix ir debug config (#15571)
7 years ago
Jiabin Yang 075df09f86
Merge pull request #15470 from JiabinYang/feature/imperative
7 years ago
Yan Chunwei 655179089f
AnalysisConfig remove contrib namespace (#15540)
7 years ago
JiabinYang 2e309b11c2 test=develop, merge develop
7 years ago
JiabinYang 53d558cd41 test=develop, polish code and merge develop
7 years ago
Zhaolong Xing 97b76c94c4
Merge pull request #15242 from NHZlX/trt_int8_ultimate_version
7 years ago
nhzlx b43ea40c51 delete the usage of the const_cast
7 years ago
Yan Chunwei e2818c8608
add dynamic memory optim (#15457)
7 years ago
nhzlx 92cf4a4c6b fix comments
7 years ago
nhzlx 0779e35544 fix two bug:
7 years ago
nhzlx 027d24c831 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_int8_ultimate_version
7 years ago
tensor-tang 5c68dee798 fix debug compile of analysis pass fail
7 years ago
Yan Chunwei 885c4e57ab
fea/infer memory optim2 (#14953)
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
nhzlx 4e3522e5b4 add trt int8 support
7 years ago
Tao Luo feee78d9f0
Merge pull request #15214 from tensor-tang/fix/debug
7 years ago
Tao Luo 9c02765158
Merge pull request #15210 from Superjomn/fix/analysis_tester_bug
7 years ago
tensor-tang 69fd3fdb52 fix debug build error
7 years ago
superjomn 23bdd0a223 fix analysis_tester bug
7 years ago
Yan Chunwei 6ccf8685f7
refactor tensorrt node teller (#15181)
7 years ago
Zhaolong Xing 4048cfa9da
Merge pull request #15048 from NHZlX/add_affine_channel_fuse
7 years ago
nhzlx 71636e677d add min_subgraph_size attr to tensorrt config
7 years ago
nhzlx a6aa8ea771 faster rcnn input is presistable. (fix it in paddle-trt)
7 years ago
minqiyang b1d0a14c14 Change the ut back
7 years ago
minqiyang 7d1533216d Fix syntax error in unit test
7 years ago
nhzlx 050a68dde3 fix comments
7 years ago
superjomn edd1f5a92b fix visualizer
7 years ago
bingyanghuang 943ad4781f One possible solution to add flexibility for mkldnn placement pass (#14768)
7 years ago
Tao Luo 743cb840f1 update with comments
7 years ago