* pnnx support grid_sample op

* complete the permute and gridsample operator fusion

* spilt calculation into two stages and support permute fusion

* mha is now permute and reshape free
* gemm user defined tile mnk param

* fix doc, sync x86 gemm fix

Co-authored-by: EdVince <EdVince@users.noreply.github.com>
Co-authored-by: nihuini <nihuini@tencent.com>

Co-authored-by: LRY89757 <LRY89757@users.noreply.github.com>
Co-authored-by: nihuini <nihuini@tencent.com>
Co-authored-by: nihui <shuizhuyuanluo@126.com>

* Add DeformableConv2D
* add unittest and docs
* pnnx torchvision deformconv2d conversion

Co-authored-by: miemie2013 <miemie2013@users.noreply.github.com>
Co-authored-by: nihui <shuizhuyuanluo@126.com>

* fix sigmoid returns nan with very large input

Co-authored-by: ElvisYu <elvisyuovo@gmail.com>
Co-authored-by: 余浩文 <m18107220188@163.com>
Co-authored-by: Zr2223 <67497651+Zr2223@users.noreply.github.com>

change weight type

* implement convolution1d and pooling1d

* add conv1d pool1d test

* fuse convolution1d activation

* update operator doc

* fix vulkan adpative pooling

Co-authored-by: wq.chu <wq.chu@tianrang-inc.com>

* add convolutiondepthwise/crop/sigmoid/tanh in operators.md

* sort by alphabet

* delete impl_type

* cannot delete impl_type

* cannot delete impl_type

Co-authored-by: yaobin.li <yaobin.li@rokid.com>

* update operators.md, add binaryop/Operation type

* fix with_scalar

* Update operators.md

* Update operators.md

* Add LSTM and softmax to operators.md

* Fix lowercase and support_inplace