* add vs src group

* check condition first

* wip

* wip

* wip

* fix avx2 test

Co-authored-by: mgrad <mgrad@meraki.com>

* wip

* fix slice pack8 test

* fix flatten pack8 test

* fix binaryop pack8 test

* fix interp pack8 test

* rewrite cast test for different blob type and packing

* Add mips softmax layer

* Fix bias value error in bias_layer

* Fix max and min value error in clip_layer

* Remove unused elempack variable

* Add sigmoid mips layer

* Add mips tanh math func

* Add mips tanh layer

* Add msa_fill_w_f32 for load float type data

* Remove conv layer header

* lstm with direction

* convert onnx lstm

* lstm works

* fix requant relu6 bug

* fix

* delete pipeline change in forward/forward_inplace avoid race in multithreading