* optimize token prune

* support default use_gpudnn=True

* fully support cudnn in phi

* add header file

* add white_list, verify accuracy

* phi support all cudnn

* opt affine_grad

* try different arches of pretrained_model

* try different arches of pretrained_model

* add debug string

* debug eager_method

* add debug string, pass all local ctest

* polish all debug code

* delete use_cudnn relevant code autogen

* fix depthwise_conv2d

* Share all other members of Tensor except use_cudnn

* polish codes according to review opinion

* polish codes according to review opinion, fix bug

* polish codes according to review opinion, opt performance

* polish codes according to review opinion, fix pooling.py

Note: this is a temporary solution, should be replaced once reduce kernel
is natively supported on KL2

* do not calc reduce_all in eager mode

* refine python c cast list

* refine

* refine

* refine

* refine

* refine

* refine

* refine

* refine

* refine

* dense tensor in eager mode support data_ptr

* feat: static check

* decouple im2col from fluid

* move im2col to phi

* fix build error

* delete redundant comment

* add nparray case for basic operator

* fix unit test

* fix unit test

* add unit test

* fix unit test

* add stat tool

* add roll and roll_grad kernels and strided_slice and strided_slice_grad kernels, test=kunlun

* add masked_selected_grad kernel,test=kunlun

* make bfloat16 implicit convert to float/double

* fix bfloat16_test ut compile

* first commit

* 2nd commit

* use fused mlp in multi transformer
* Restruct code
* use cublaslt to fuse ffn
* fix conflict

* Migrate elementwise_div

* Migrate elementwise grad kernels

* fix:fix the bug of trt_8.0.3.4

* fix: fix the bug of trt_8.0

* fix: notes

* move vol2col from fluid to phi

* update copyright year

* Skip tests that use fused_ops on H100

* Add error message to FusedOps on H100

Removed ResidualData and Bias from ExtraAttrProperties because it's not an attribute.
Removed bug with checking for ResidualData attribute in matmul_elementwise_add_fuse_pass
Removed residualData from list of matmul outputs in cpu_bfloat16_pass.cc because it's input
Co-authored-by: NTomasz Socha <tomasz.socha@intel.com>

* Delete caching from requantize_mkldnn_op and changed to Acquire API
* Fixed codestyle and implementation

* move "paddle/phi/backends/gpu/gpu_device_function.h" to phi

* update copyright years

* rm "fluid/platform/device/gpu/gpu_device_function.h" in phi

* rm dependence to "gpu_device_function.h" in fluid

* rm gpu_device_function.h etc in fluid

* fix rocm-complie bugs

* fix cuda_helper_test.cu bugs

* fix doc of NPUPlace

* fix doc of NPUPlace, test=document_fix

* add fc-residual quantization

* revert removal of check for use_mkldnn

* fix bug

* add disable_logs

* review fix

call twice AreScalesPresntForNodes instead of if-else

* rewrite residual input to output

* revert fc mkldnn taking residual data

* format fix

* fix LoDTensor->DenseTensor

* LoDTensor->DenseTensor

* output->input

* revert changes to unsupported script

revert changes to unsupported script

* remove fc residualdata from output blocklist in cpu_bfloat16_pass.cc

* cleanup unused code

* unify is_int8 is_bfloat16

* Simplify matmul_v2 FWD kernel

* remove RunKernel methods

* remove import namespace

* remove headers

* clean fluid/phi cross imports

* remove fluid axpy_handler

* delete fluid methods

* activations

* OneDNNMemDesc

* MKLDNNFormatForSize

* MatchShapeToLayout

* MKLDNNMemoryFormat

* MKLDNNFormat

* ReorderMKLDNNHandler

* to_void_cast

* review suggestions

* interpolate

* remove fluid depedency

* init

* ExecuteMatMulV2

* rm fluid kernel

* matmul_grad

* remove mutable_data

* mul_grad

* use mma for QK dot computing in fused_multi_transformer.
* Update fused_multi_transformer_op.cu.h

* refine reduce_all

* Fix wrong eigen header include

* fix compile bug