Commit Graph

37 Commits (742cbe666024415f856ec77721b19a8a58c8e44f)

Author SHA1 Message Date
Wilber 632125415c
Refine python inference api (#26958)
5 years ago
joanna.wozna.intel 0627a319b0
Restore "Add mkldnn bfloat16 option to C-API " (#26882)
5 years ago
石晓伟 ced6e87eee
Revert "Add mkldnn bfloat16 option to C-API (#26676)" (#26854)
5 years ago
Wilber 68e0560c2f
refine paddle inference api (#26774)
5 years ago
joanna.wozna.intel 02083bda40
Add mkldnn bfloat16 option to C-API (#26676)
5 years ago
Pei Yang 55b6205ddf
add set_mkldnn_cache_capacity python api(#25524)
5 years ago
石晓伟 7206417259
supports xpu runtime, test=develop (#25554)
5 years ago
Pei Yang 43f9f180e5
Add api to clear intermediate tensors in AnalysisPredictor (#25069)
5 years ago
Pei Yang 14b8540551
add default ctor for AnalysisConfig python api. test=develop (#24924)
5 years ago
Chen Weihang d1062d5278
Replace all errors thrown by LOG(FATAL) with PADDLE_THROW (#24759)
5 years ago
mozga-intel 3baaee9aab
Remove: NGraph engine from PDPD repository (#23545)
5 years ago
石晓伟 9b82e4c183
change the cmake and apis of lite engine, test=develop (#22934)
5 years ago
Zhaolong Xing 430b0099c9
[Paddle-TRT]: Ernie Dynamic shape support. (#23138)
5 years ago
Zhaolong Xing dd67d44a50
[Paddle-TRT] : (Part1) Dynamic shape support (#22868)
5 years ago
石晓伟 1861ca88f1
serialize the PaddleTensor, test=develop (#22810)
5 years ago
石晓伟 e1b0d7cbb1
remove anakin from code, test=develop (#22420)
5 years ago
flame 2bbc0d7d60
python zero copy inference, delete pass (#21897)
5 years ago
Pei Yang 443f604c3b
add DisableGlogInfo() to AnalysisConfig, test=develop (#20581)
5 years ago
Pei Yang 9cbc1eff2d
zerocopytensor support uint8, analysis config support profile, analysis predictor support GetInputTensorShape, test=develop (#19822)
5 years ago
liu zhengxi 32598ffd8f
Python infer api update and add unit test (#19353)
6 years ago
Tao Luo 5f5648a8ff
Revert "Python inference API support numpy (#19009)" (#19160)
6 years ago
flame b7e1a1d7e7 Python inference API support numpy (#19009)
6 years ago
flame 65d987527d
python inference enable_memory_optim(#18817)
6 years ago
Zhaolong Xing 61238d31f7
Trt fp16 support (#18860)
6 years ago
Zhaolong Xing 88b52a27fe
Inference: fix mask rcnn model diff, optim memory usage, memory leak. (#18532)
6 years ago
翟飞跃 993c703bcc INT8 MKL-DNN v2 integrate to slim (#17634)
6 years ago
Zhaolong Xing 61221ebc28
TRT: Support set dynamic range in int8 mode. (#17524)
6 years ago
石晓伟 a72dbe9abf
Cherry-pick benchmark related changes from release/1.4 (#17156)
6 years ago
Tao Luo 7d2740db83
Revert "cache runtime_context"
6 years ago
luotao1 d94fd97230 add runtime_context_cache_pass
6 years ago
Tao Luo 6f2581e4c5
Merge pull request #16090 from lidanqing-intel/paddle-int32
6 years ago
nhzlx a9ed427749 cant not pass ci
6 years ago
lidanqing 4aeb261da9 Add INT32 support. INT32 in last switch case
6 years ago
Gabor Buella da9c94da33 Clang build fixes (#15628)
6 years ago
Yan Chunwei 655179089f
AnalysisConfig remove contrib namespace (#15540)
6 years ago
nhzlx 36abc964df fix pybind problem: add an enum to AnalysisConfig
6 years ago
flame d60751fb71
add python inference api (#15248)
6 years ago