* Implement conv2d_fusion NHWC format using CUTLASS
* Add unit testing for CUTLASS Conv in inference
* Add experimental API for CUTLASS.

* Deleted mkldnn_inplace_pass code

* Fixed error with cmake

* Resolve conflicts

* rewrite delete_weight_deqquant_linear_op_encoder/decoder pass

* general optimization no_varlen embedding layernorm

* pass

* pass

* draft version

* share mem opt

* remove sharemem

* add pattern for the case with circle_shift=0

* add UT

* pass opt

* test_fix

* code-commit

* code-style

* code style

* code-style

* ut-fix

* op teller refine

* resolve conflict

* adjust position op_teller list and pass order for swin

* ut code style update

* adjust paddle pass order

* refine pass order

* refine pass order

* refine pass order

* delete unnecessary shape and slice op
Co-authored-by: NYour Name <you@example.com>

* optimization for ln

* fix

* added output to gpd

* added formatting

* fix

* generate static graph code for some ops by yaml

* remove deleted files

* update cmake

* update cmake

* udpate cmake

* add roformer pass&&plugin（novarlen）

* add fuse_multi_transformer_layer_pass

* softplus+activation

* fc + elementwise_add test refactored

* rename MKLDNN to OneDNN

* fc+activation tests refactored

* remove softplus ut

* whitespace

* whitespace

* codestyle

* codestyle

* add more cases to fc+act

* remove softplus+hard_sigmoid pass

* remove softplus + hard_sigmoid UT

* add approximate for gelu

* swish beta range

* new codestyle

* reduce number of tests

* suqeeze2 transpose2 fuse onednn

* format

* fix output shape

* fix conflict

* format

* format

* remove useless

* remove log

* simply pass

* fix comment

* fix

* fix msg

* fix error msg

* format

* tmp save

* minor chnage

* CI fix

* added FC optimizations

* latest update

* CI fix

* fixed bug with fusing fc

* make all cpp tests dynamic linked to libpaddle.so

* add comments

* keep old cc_test for some tests

* fix some ut

* make some ut use cc_test_old

* fix typos and fit for win32

* fix lib path

* fix some tests

* skip lite test

* fit for rocm

* fit for cinn

* fit for mac

* fit for win32

* skip inference ut

* skip  windows

* fix coverage

* prelnlayernorm_shift

* add ut

* remove paddle_enforce

* remove useless

* add UT

* remove UT

* add UT

* set timeout

* fc/matmuls + scale fuse pass

* remove double-extension

* add unit tests

* comments from review

* codestyle

* add pass to int8 list

* new codestyle

* attr name typo

* add fused_multi_transformer_encoder/decoder pass, run GPT-3 success

* first version, accuracy corrected

* disable debug print

* use blockReduceSum in phi

* add UT

* add opCompat

* code style

* code refine

* bug fix

* code refine

* test fix

* bugfix

* codesytle fix

* code style

* code-style

* code-style

* code-style

This reverts commit 166ff39a.

* [Paddle Inference]support n lookup_tables fuse to embeddinglayernorm(3)

* use cinn in the paddle inference

* fix some cmake errors

* Avoid division by zero in the arange_kernel.

* Avoid dynamic ops.

* Remove some useless codes.

* Use OpTransInfo to encapsulate some codes used in the build_cinn_pass.

* first commit

* conver done

* correct format

* layernorm_shift_partition

* correct convert

* redefine plugin

* runable

* bug fix

* modify ShiftPartitionPattern

* correct

* add UT

* modify ut

* compile

* modify enforce

* modify UT

* add del dropout op pass to jit pe enigne

* add delete dropout test

add constant folding pass， for some model，it will get less latency；

* merge conv_concat_relu to conv_act

* fix typo

* extend unit test

* reuse existing gpd

* codestyle

* enforce mkldnn conv

* convert multihead to oss

* fix:bug

* fix:delete const cast

* fix:don't support bias_qk

* add vit pass

* fix:convert bug and add preln_residual_bias

* support length=-1

* add UT for convert

* add no_bias_qk support for gpu_multihead_op

* delete infer_shape depends on bias_qk

* oss just can be used in T4 and A*

* fix:change api for ROCM CI

* remove v2_transpose_reshape

* matmul_transpose_reshape

* reshape_transpose_matmul

* restore ut

* adjust old ut

* restore parallel UT ruels

* feedback from review

* Add unit tests

* matmul_v2 + activation

* matmuls + elementwise_add

* matmul_v2 postops

* transform matmul to v2

* opcompat

* fix fusing matmul with multipe outs

* add shape constraints

* remove unused vars

* change pass order

* - Unit tests to be debugged

- fix

- refactor

- diagnostic

- more diagnostic

- fix

- Fix number two

- fix

- fix

- fix

- alpha added

- more fixes

- compilation fix

- removed diagnostic code

- cosmetic fixes

* lint

* add alpha constraint

* merge matmul refactor

* trigger CI

* - fix

* - another fix

* code style

* add support for matmul+elementwise_add+activation

* code style

* fix bfloat16 bugs

* change append_binary to append_sum
Co-authored-by: NJacek Czaja <jacek.czaja@intel.com>

* Set more attrs in ReplaceScaleLossGradOp

* Fix typos

* Fix CI errors

* Add UT