* add embedding backward rule

* update backward api

* revert api

* matmul inferbackward

* update unitest

* add shard tensor api

* add DistAttr api

* add unittest for coverage

* fix process mesh sample code

* fix checking error

* add skip_gc_vars for 1f1b schedule mode

* add pp_degree and pp_stage

* auto parallel support pipeline scheduler with standalone executor

* rm check_fetch

* update cmakelist and flags env

* rm set micro batch id

* rm import

* update utils func

* raise error when merge tensor for return_numpy is False

* fix _pipeline_opt

* fix unittest

* add auto tuner

* compare and record module

* revert launch main

* add prune rule

* add unit test

* add auto tuner

* revert launch main

* add prune rule

* modify unit test script

* fix bug for dump nodes; fix bug for checking log file

* fix bug

---------
Co-authored-by: Ncaozhou <caozhou@radi.ac.cn>

* add auto tuner

* fix prune

* fix sharding prune and mbs candidates

* fix cfg

* fix launch

* fix launch

* add unittest

* fix code style

* Fix bug of reduce_sum op. When input.numel() > INT32_MAX, its result
is wrong.

* Remove climits.

* Fix problem of pickle and NCCL_P2P_DISABLE in distributed testcases in
cuda12.

* Fix problem of TimeOut of distributed testcases under cuda12.

* Remove useless modification.

* Remove useless modification.

* construct dist tensor

* move constructor to header

* fix a100 cuda12 timeout

* fix cuda12 pickle loads problem

* fix ist_sharding_save ut

* [AutoParallel] add 1F1B

* rm amp

* [AutoParallel] update while control_flow with pipeline

* update process group instantiate

* fix micro_bsz for reshard

* update api for micro batch size

* add strategy for dp optimization

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* polish

* mv ps distributed dir

* fix

* add del auto_parallel

* add auto_parallel

* fix ps

* fix bug

* fix test bug

* fix test bug

* merge develop fix error

* merge develop fix error

* merge develop fix error

* add o2 tune

* add unittest

* fix error

* set unittest timeout

* unique id for mesh

* rng ctrl

* support dropout

* register op

* adopt for recompute

* update unitest

* support pp

* add fuse adamw pass

* fix some bugs

* fix CIbug

* change chunk_size

* fix CI bug

* rm test_fused_adam_op.py

* fix CI bugs

* fix fuse_adamw_op_pass.cc

* change code style

* fix CI bug

* fix ut bug and use_adamw_op_pass.cc

* fix test_fuse_adamw_pass.py

* fix CI bug

* remove fluid

* fix ci bug

* fix CI bug

* add patterns

* update rule based tuner

* add forward sub program completion

* add unittest

* add bwd sub program completion

* [AutoParallel] support bloom

* fix import

* align amp and bf16

* update func name

* clipbyglobalnorm and add_n support bf16

* upgrade amp strategy api

* update bf16 unittest

* fix static clip

---------
Co-authored-by: Nliangjianzhong <liangjianzhong@baidu.com>
Co-authored-by: NAurelius84 <zhangliujie@baidu.com>

* update env setting

* update pass logic

* dist op support bf16

* backward cast update

* update setting

* update backward

* revert amp pass

* update fp16 backward logic

* register c_embedding bf16

* revert engine

* add unitest

* add unitest

* update unitest

* update cmake

* update math

* update math.py

* update unitest

* update unitest

* revise unitest

* revise unitest

* update unitest

* update unitest

* update unitest

* auto parallel align tool

* modify function get_var's return

* add save and load in align_tool

* modify load function and save function

* add finding different ops in align tool

* full auto parallel align tool

add test file for auto parallel align tool

set timeout for test

modify get_backward_tmp_var function

add annotation for align tool

modify test file

modify code to restart CI

remove timeout

* set timeout

* fix the processing order of passes in pass_base.py

* fix processing order

* add _PASS_PROCESS_ORDER_LIST

* delete some pass in _PASS_PROCESS_ORDER_LIST

* add assert in pass_base.py

* remove fuse_optimizer

* add _fusion_opt_list_rule

* add test_pass_base_list.py

* fix some bug

* add fused_attention

* add some passes to list

* fix ci bug

* fix ci bug

* add FusedLinear pass

* add fused_op_list and renname PASSES to OP_FUSION

* add fused_passes_list to constants.py

* add test_passes.py

* fix test_fused_passes.py

* fix add if float(paddle.version.cuda()) >= 11.6:

* renamed test_fused_passes.py

* fix CMakeList.txt

* auto parallel bf16

* fix input order

* add unittest

* update cmakelist

* [AutoParallel] quantization pass support export

* support subgraph

* move_presist_var_to_global_block

* update unittest

* fix ci-coverage

* fix codestyle

* fix fake_dequantize_op

* remove unused var

* fix ci error and aprroval error

* add unittest for fp16 in test_dequant_linear

* replace mutable data

* fix unittest in non-cuda-core

* fix unittest
Co-authored-by: Ncarryyu <569782149@qq.com>
Co-authored-by: Nwufeisheng <wfs1997@163.com>

* [AutoParallel] recompute tuning

* fix conflict

* update comment

* bug fix

* update rc algo

* tiny fix

* fix clear process_group

* remove comment

* update segment print

* fix import OpRole

* adapt amp pass and grad_clip pass for opt_tuner

* update tuning config

* fix import

* annotate recompute info on ops and upgrade recompute pass

* add op_namescope for seed op

* record reserved vars

* fix recompute var's dist_attr

* fix strategy unittest

* adapt for fp16

* update unittest

* revert copy opt

* update unittest

* rename set_recompute_segments

* fix unittest

* add cluster_partition and device_meshes to process_meshes funcs

* add unitest

* add pattern match

* add unittest

* add pattern for auto search

* add unittest

* [AutoParallel] selective recompute

* add cmakelist

* fp16 pass support assign op

* choose assign op exec mode

* add unittest

* add cmakelist

* [Auto Parallel] Improve the c++ dist attr

* [Auto Parallel] Modify test_program.py

* [Auto Parallel] Add the missiong import

* fix engine build method

* fix import

* update engine cost

* update raise error

* update cmakelist

* revert optimizer

* revert optimizer

* fix unittest

* fix unittest
Co-authored-by: Ncaozhou <caozhou@radi.ac.cn>

* add parallel tuner

* add unittest

* fix unittest

* set timeout of unittest

* set unittest timeout

* fix auto_mode setting

* update unittest

* sync from develop and update unittest

* remove unused import

* update unittest

* update cmakelist

* add unittests

* [AutoParallel] add callbacks

* fix unittest

* fix dist_context

* fix engine

* fix cmakelist

* fix unittest's returns

* fix cmakelist