* remove nccl dep when the number of GPU is 1
test=develop

* use multi card run syncBN
test=release/1.5

Add trainer_desc proto DEPS to solve CI random fail.

Add cascade rcnn support.

Cherry pick #18077 and  #18111 unify FP32 vs. INT8 comparison tests output, reuse C-API INT8 unit test application (#18145)

* unify FP32 vs. INT8 comparison tests output (#18111)

test=release/1.5

* reuse C-API INT8 unit test application (#18077)

test=release/1.5

* fix dygraph mem leak, test=release/1.5

* polish msg, test=release/1.5

cherry pick for deform roi pooling

cherry-pick for (https://github.com/PaddlePaddle/Paddle/pull/17402)

Add Pipeline Concurrency Train Mode:
- Cpp: pipeline_trainer & section_worker
- Python: PipelineOptimizer
- Add a new data_feed type: PrivateInstantDataFeed
- Add a test demo of pipeline trainer and the test model is gnn
- Do not support win32 now

* fix multithreading issue

test=develop

* rview fixes

test=develop

* reivew fix: omp->cpu, infernce_api.cc->pybind.cc

test=release/1.5

* fix py_reader iterable bug, test=release/1.5

* move data from buffered_reader,test=release/1.5

* update CPU_NUM config
test=develop

test=release/1.5
cherry-pick from #17952
The scatter op has a calc bug when the indices has same index, the scatter op use overwrite mode to calculate the same index, fix this bug by using the accumulate mode to calculate the same index.At the same time, the gather op has the same bug when the op calc the grad. And we use the lib of open-blas and eigen to optimize the time cost in accumulate mode.

Added unit test for QAT FP32 & INT8 comparison (#17814)
Disable MKLDNN FC in Resnet50 test (#18030)

test=release/1.5

test=release/1.5

Fix #17955
Fix bug in sequence_unpad op, when allocate the output memory do not match actual memory, check memory failed. Fix this bug by allocating the output memeory in correct code position.

test=release/1.5

* support avx and noavx core
* add catch and give some log
* fix build
* add missing package
* fix pybind name
* fix import error
* conbime noavx core
* add requirements
* fix unkown message
* fix api spec
* refine and clean
* update
* follow comments
* refine scripts

* fix: when use the load model from memory mode, the RAM occupy is high

test=release/1.5

fix merge conflict of 'Remove attribute in Allocator::Allocate' and elementwise_add_mkldnn_op (#17949)

test=develop

test=develop

* remove attribute in Allocator::Allocate, test=develop

* fix travis ci error, test=develop

* Enable seq_pool op to accept len 0 input

test=develop

* Update sequence_pool's api

test=develop

* Add more unittest cases for seq_pool op

test=develop

* Remove legacy comments

test=develop

* Don't use template in op maker

test=develop

test=develop

* add reshape support tensor; test=develop

* fix reshape bug; test=develop

* change reshape attribute default value; test=develop

* fix reshape input name; test=develop

* fix reshape unitest; test=develop

* check dim tensor shape; test=develop

* WIP

* WIP

* test=develop, add api doc and example code for dygraph

* Add auto pruning strategy.
1. Fix compressor.
2. Enhence graph executor.
3. Add SAController
4. Add auto pruning strategy.
5. Add unitest for auto pruning strategy.
test=develop

* Init light-nas

* Add light nas.

* Some fix.
test=develop

* Fix sa controller.
test=develop

* Fix unitest of light nas.
test=develop

* Fix setup.py.in and API.spec.
test=develop

* Fix unitest.
1. Fix unitest on windows.
2. Fix package importing in tests directory.

* 1. Remove unused comments.
2. Expose eval_epoch option.
3. Remove unused function in search_agent.
4. Expose max_client_num to yaml file.
5. Move flops constraint to on_epoch_begin function
test=develop

* Fix light nas strategy.
test=develop

* Make controller server stable.
test=develop

* 1. Add try exception to compressor.
2. Remove unitest of light-nas for windows.
test=develop

* Add comments
Enhence controller
test=develop

* Fix comments.
test=develop

* fix cuda/cudnn version detection error, test=develop

* fix again, test=develop

test=develop

test=develop

test=develop

fix bug: the lod_tensor_to_array op will aplly a new var but not release when dong inference (#17856)

test=develop