28 Commits (7c3d64e0c9e9631794e851f50ce4b2693f2bc90a)

Author SHA1 Message Date
  wilfChen ba9bbfadf8 gpu inference mixed precision 4 years ago
  zhupuxu 978d7512e7 device tensor 4 years ago
  mindspore-ci-bot 0cfd8b7c9e !13364 Add WordpieceTokenizer and AddDict to Jieba 4 years ago
  wilfChen db2668d72a gpu inference context 4 years ago
  mindspore-ci-bot 4b329090b6 !13938 library size optimization for 310 4 years ago
  lixian 84c1705319 add GetOutputsByNodeName 4 years ago
  zhoufeng e4c59a1c8f library size optimization for 310 4 years ago
  lixian 08ed63ff91 fix write for big endian devices 4 years ago
  lixian 693b4cfdc8 refactor cpp context, add string tensor, add get tensor by name 4 years ago
  alex-yuyue 2d6d608fae Add WordpieceTokenizer to API and IR. Add AddDict to C++ API 4 years ago
  Lixia Chen 72da42a3a6 Fix converting between optional string and char 4 years ago
  zhupuxu 5ca25451ee dynamic_batch 4 years ago
  wilfChen 0ce25b4724 gpu inference config 4 years ago
  wilfChen 156e8e92e9 gpu inference config 4 years ago
  mindspore-ci-bot 7036d35e9d !12871 add 310 options 4 years ago
  zhoufeng 96aea47492 310 add context options 4 years ago
  luoyang 24de4f12fa MindData support dual ABI 4 years ago
  zhoufeng 504f215800 api support dual abi 4 years ago
  lixian d0c9736fa5 remove cross dependency of context 4 years ago
  zhoufeng 539d88552a check modeltype 4 years ago
  lixian 7d2fd6e76c cxx api refactor: tensor/status/model 4 years ago
  wilfChen a911b9ef9e mindspore serving support gpu backend 4 years ago
  zhoufeng ad1e49b7a3 modify timeout of version check subprocess to 3s 5 years ago
  zhoufeng cd1ce73a25 remove pybind calling in cxx library 5 years ago
  zhoufeng 3204ecb7d6 mindspore c++ interface 5 years ago
  zhupuxu da0a18c5e3 fix codedex 5 years ago
  xuyongfei a3b9218919 support mindpsore::api:Model 910 inference, support 310 model convert in python env 5 years ago
  zhoufeng 183742009f mindspore cxx api for 310 inference 5 years ago