Commit Graph

370 Commits (35c89f38c3b03d9ace53aec0bb263b54b08d64bb)

Author SHA1 Message Date
Michał Gallus 2d8b7b3a76 Refine default MKL-DNN Pass order (#16490)
7 years ago
Wojciech Uss 09dfc7a2aa
C-API quantization core 2 (#16396)
7 years ago
nhzlx 953bdde058 Merge branch 'develop' of https://github.com/paddlepaddle/paddle into HEAD
7 years ago
nhzlx 45b3766fdf fix comments
7 years ago
liuwei1031 de3b70a101
fix cdn issue, test=develop (#16423)
7 years ago
nhzlx 3df7b98a0f Merge branch 'develop' of https://github.com/paddlepaddle/paddle into HEAD
7 years ago
nhzlx f3a2e4b3d8 1. Add ANAKIN_ROOT compile option
7 years ago
Wojciech Uss cbe2dbf0db Add enabling quantization (#16326)
7 years ago
nhzlx 4f4daa4b66 cherry-pick from feature/anakin-engine: add data type for zero copy #16313
7 years ago
nhzlx 07dcf2856c git cherry-pick from feature/anakin-engine: update anakin subgraph #16278
7 years ago
nhzlx c407dfa3cb cherry-pick from feature/anakin-engine: refine paddle-anakin to new interface. #16276
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
luotao1 82af8031d9 add runtime_context_cache_pass
7 years ago
Tao Luo 7d2740db83
Revert "cache runtime_context"
7 years ago
luotao1 a275fd6e0c Merge branch 'develop' into runtime_context
7 years ago
Wojciech Uss 2579ade45f Add cpu_quantize_pass for C-API quantization (#16127)
7 years ago
luotao1 5ecdc49c6b set enable_runtime_context_cache_ default false
7 years ago
luotao1 1510b866b6 turn off runtime_context_cache for tensorrt
7 years ago
luotao1 d94fd97230 add runtime_context_cache_pass
7 years ago
luotao1 1283833395 zero_copy tensor support INT32
7 years ago
luotao1 31c4e1d9fc Merge branch 'develop' into zero_copy
7 years ago
Tao Luo e5e7e9b865 Merge branch 'develop' into transformer_ut
7 years ago
Tao Luo 6f2581e4c5
Merge pull request #16090 from lidanqing-intel/paddle-int32
7 years ago
Zhaolong Xing 3d63aa0a11
Merge pull request #15729 from NHZlX/add_static_model_load_for_trt
7 years ago
nhzlx a9ed427749 cant not pass ci
7 years ago
luotao1 fad06cb928 unify ZeroCopy in analysis_test
7 years ago
lidanqing 4aeb261da9 Add INT32 support. INT32 in last switch case
7 years ago
luotao1 06aab1b493 refine SetCpuMathLibraryNumThreads
7 years ago
nhzlx 3c40cb767b 7 refine zero copy
7 years ago
Yiqun Liu 1616c32acf
Add the include of cudnn.h to enable the use of CUDNN_VERSION. (#15961)
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
Sylwester Fraczek 1943119fc5 fix typo memeroy->memory
7 years ago
Sylwester Fraczek 8bc604571f fix typo seriazlized->serialized
7 years ago
Sylwester Fraczek 543e53db05 fix typo releated->related
7 years ago
tensor-tang e1c707fe9c
fix warnings (#15790)
7 years ago
nhzlx 2070fb246d 4. do the trt_engine optim during init.
7 years ago
Yan Chunwei 3a5d6e5e64
move passes to src to avoid different behavior in deployment (#15705)
7 years ago
Yan Chunwei c00ed19df2
add more comment (#15603)
7 years ago
Gabor Buella da9c94da33 Clang build fixes (#15628)
7 years ago
Chunwei d85c2e4e5c fix anakin compile dependency
7 years ago
qingqing01 943d972878
Fix analysis predictor when loading the persistable RAW type variable. (#15613)
7 years ago
Yan Chunwei e887d71958
fix ir debug config (#15571)
7 years ago
Yan Chunwei 897789b16e
fix save_inferece_model bug (#15365)
7 years ago
Tao Luo 3d0ecab41b add analyzer_transformer_test
7 years ago