[LITE][NPU][XPU] Refine subgraph pass, and support NPU/XPU model generation at execution time (#2576)

[LITE][NPU] Add fusion_elementwise_add_activation bridge, remove the limitation of the dimensions of input tensors in the graph compute kernel, and refine log message (#2395)

test=develop

* Add supporting for Huawei offical DDK
* Fix the param of graph op in NPU graph computing kernel

* move lite/backends/npu/bridges --> lite/kernels/npu/

test=develop

* fix namespace for npu

test=develop

* mv npu runtime file to lite/backends/npu

test=develop

* [NPU] Fix the bug of loading multi NPU models
test=develop

* [NPU] Use lite tensor to store NPU model, fix the management of multi NPU models, support loading NPU model from memory and reduce the modification of framework
test=develop

* [NPU] Remove redundant header files for NPU bridges,
test=develop

* [NPU] fix NPU deps
test=develop

* [NPU] refine the compiling script for NPU
test=develop

* [NPU] remove redundant subdirectory in lite/CMakeLists.txt
test=develop

* [NPU] Fix and refine NPU test case
test=develop

* [NPU] revoke the modification of other non-NPU modules
test=develop

* [NPU] Remove NPU bridges if target is tiny publish
test=develop

* fix bug: npu permute's input w need unique name

test=develop

* fix bn, eltwise, pool, shuffle_channel, softmax, transpose unique name

test=develop