* add support for three-dimentional input in reduce max test=develop

* add view suffix to read-only classes for flatbuffers, test=develop

* add some write-apis for flatbuffers, test=develop

* [ascend] add pool and elementwise op, test=develop

* [ascend] add batch_norm op and simpify tensor update, test=develop

test=develop

* change pooling3x3s2max padding right to intrisic. test=develop

* add int32->int64 cast arm cpu kernel. test=develop

* [test] flatbuffers io, test=develop

* determine the basic interfaces and help functions of flatbuffers, test=develop

[RKNPU] Adapting to the changing of the quantization parameters, and supporting the fully quantized mobilenetv1 model (#4046)

* [RKNPU] Adapting to the changing of the quantization parameters, and supporting the fully quantized mobilenetv1 model
test=develop

* [Doc] Update the doc for apu and rknpu
test=develop

* add ParamDesc, test=develop

* serialize tensor funcs, test=develop

* update prior profile, test=develop

* fix review. test=develop

* test=develop

* fix opencl backend. test=develop

[ARM] [NPU] Fix the overflow of layer_norm op bridge, fix the registration of lstm op kernel (#4007) (#4017)

* [NPU] Fix the overflow of layer_norm op bridge
test=develop

* [ARM] Fix the registration of lstm op kernel
test=develop

* fix arm winograd compute segment. test=develop

 [Framework] Fix the issue that `CreatePaddlePredictor` method is not safe for multi-thread condition #4014

* add elu act

* fix elu act not find error, test=develop

* fix format.test=develop

* fix int8 model opt error in conv+conv fusion, test=develop

* fix format. test=develop

* test=develop