[CodeStyle][F401] remove unused imports in python_paddle/inference_device_profiler_text_metric_incubate_quantization_libs_audio_amp_jit. (#46762)

make fused_multi_transformer support dynamically set the cache_kvs' shape and support input prefix_caches. (#46777)

* make fused_multi_transformer support dynamically set the cache_kvs' shape and support input prefix_caches.

* Add new attr of fused_multi_transformer

* fix format

* add note

* add in layer

* fixfixfixfix

* use yapf to format all python file

* yapf exclude two unittests file for they rely on writing and reading file, and format will break them

* disable diff_py_file because too many diff files cause command following failed

* add fused_bias_dropout_residual_ln op and layer.

* fix bug:
1. atten: set the default value of attn_dropout_rate to None
2. ffn: add activation parameter

* for pure fp16

* Add a SparseCsrTensor

* remove unused functional

* remove const

* remove SetMemoberTensor

* remove non_zero_nums_, the number of non zero elements of each batch can be obtained from the crows

* SparseCooTensor

* add SetMember

* merge upstream; add SetMember

* merge upstream

* merge upstream; add newline at end of file

* add newline at end of file

* remove newline at end of file

* remove newline at end of file

* stash

* user pten::framework::make_ddim

* user pten::framework::make_ddim

* merge upstream; use the latest mutable_data

* merge upstream; use the latest mutable_data

* return mutable dense tensor

fused_attention_op的实现中，使用了bias_add，且其实现是通过使用kernel primitive来实现的，之后kernel primitive的WriteData api接口及函数内部实现发生了更改，将判断越界的逻辑移到了template的参数中，使得调用的分支有错误，产生了越界赋值操作，污染了别的显存空间的内容。具体表现为：test_fused_attention_op_api.py 单次执行基本上不会报错，多次循环执行不同shape的输入，结果计算不对，具有偶发性，bug不易察觉。

* fix bug:
1. atten: set the default value of attn_dropout_rate to None
2. ffn: add activation parameter

* Fix fused_attention english doc test=document_fix

本PR是fused_transformer的layer层代码，包含FusedFeedForward的layer层代码和FusedTransformerEncoderLayer的代码。

功能：本PR的目标是提高attention模块的计算性能。
为了减少框架层对op的调度开销，本PR通过在C++层手动实现attention模块，对外提供attention 大op；
为了减少防存开销，本PR采取了两种优化方法：
（1）在q,k,v计算时通过共享输入X，将该处的gemm，transpose和bias add从三次调用减少为一次；
（2）使用kernel融合优化技术，在不同cuda kernel之间通过寄存器传输数据；

This PR adds error exception in fused transformer python interface.
The function body are not implemented (will be implemented later).
Following zhiqiu's comment in previous PR-35206 (merged already), it is better to raise an exception instead of using "pass".

This PR adds fused transformer python related files. It defines interface of fused transformer.

Fused transformer implements an optimized version of transformer layer (in python/paddle/nn/layer/transformer.py). In this PR, four layers (functions) are defined:
(1) FusedMultiHeadAttention: multi-head attention layer
(2) FusedFeedForward: feed forward layer
(3) FusedTransformerEncoderLayer: transformer encoder layer
(4) FusedTransformer: transformer layer