* aded slice FWD FP32

* added tests for slice FWD FP32

* added slice bwd

* added bf16 tests

* CI fix

* CI fix

* added reason to skip_if

* minor change

* temporary fix for failing test

* temporary fix

* changes after review

* CI rerun

* modify fetch logic, use D2H Stream, test=develop

* refine, test=develop

* add strided_slice_grad op for npu

* stablize depthwise conv

* clean commend

* support KL label smooth

* update UT for KL label_smooth

* add ElementwiseTernary, Reduce, ReadDataStride

* add trt error information.

* rerun ci

As the title, see details at the PR description.

* [NPU] Add log_loss op

* [NPU] Add log_loss op

* [NPU] Add log_loss op

* [Op Def] Add extra def of linear_interp & linear_interp_v2

* [Op Def] Add extra def of linear_interp & linear_interp_v2 & addmm

* tmp

* Tile - Assign - Crop

* Finish the set value npu kernel and test case in npu

* improve the error message

* Modify according to zhangliujie

* code review

* add maxunppol2d op, test=develop

* fix typo, test=develop

* fix unpool unitest, test=develop

* fix unpool code-example, test=develop

* fix for unpool_op_unittest,test=develop

* fix example code, test=develop

* add noqa:F401, test=develop

* fix converage, test=develop

* fix unitest for unpool, test=develop

* rename unpool2d to unpool, test=develop

* rename unpool2d to unpool, test=develop

* sparse_momentum_op is used to save w@GRAD memory for gather_op when gather from a large parameter

* add elementwise max grad op for npu

* add elementwise max grad op for npu

* add elementwise max grad op for npu

* add elementwise max grad op for npu

* add elementwise max grad op for npu

* polish the error message of paddle.slice.

* polish code.

[oneDNN] disable caching oneDNN primitives in  matmul v2, Reduce grad and elementwise_add grad, expand_v2 (#35132)

* - grad caching disabled of matmul_v1

- compilation fix

- compilation fix

* - reduction removed

* - Matmul v2 disabled caching

* Draft of further changes

* - workaround for reducegrad

* - fixes to UT

* - fix to compilation

* - another fix

* - fix

* fix assign bug support fp16 uint8

* fix dygragh assign bool bug

* modify code style

* revoke bool modification

* Support dropout backward in eval mode

* add downscale case

* minor fix

* minor fix

* Modify into QueueSync QueueAsync

* fix complie on MacOS

* fix pointer

* fix conflict

* polish unittest

* fix windows fetch error

* polish code according reviewer

* fix device_guard on CPU place

Describe

Add feed_forward for fused attention op.
(1) Encapsulate matmul impl (forward and backward) used in attention op.
(2) Implement bias_add (forward and backward) used in attention op.

* add_roi_align_npu

* update

* update

* update

* temporary change

* fix for expand_v2

* changes after review, activated ppyolov inference test

* add fetch, test=develop

* fix fetch2op, test=develop

* fix fetch2op, test=develop

* refine, test=develop

* fix fetch ctx, test=develop

* add wait, test=develop

* rename fetch2 to fetch_v2, test=develop

* merge, test=develop

* fix bmm bug

* bmm style

* fix bmm