* for pure fp16

* opt topk

* modify for wincheck-inference case

* modify according to zhouwei's comment

* modify according to zhouwei's comment 2nd time
Co-authored-by: Nzhangkaihuo <zhangkaihuo@baidu.com>

Fix CI build error

Fix Paddle-CINN CI

PR to Add Paddle-CINN CI

* notest;test=123

* notest;test=123

* notest;test=123

* notest;test=123

* notest;test=123

* notest;test=123

* notest;test=123

* fix

CI build PR and dev whl

* Add New CI - GPUBOX

* [NPU] fix npu pr

Fix CPU CI build-time

* [NPU] update batch norm op, test=develop

* add NHWC support for bn, test=develop

* [NPU] add int64 kernels, test=develop

* update ci scripts to be able to trun WITH_ASCEND_INT64 on, test=develop

* [NPU] update npu ut skil scirpts, test=develop

* update, test=develop

* update scripst, test=develop

* add debug code, test=develop

* update

* [NPU] fix cmake for ascend ci, test=develop

* update paddle_build.sh scripts, test=allcase

* notest;test=cpu

* test

* test=document_fix

* notest;test=cpu_gpu

* notest;test=cpu_gpu

* notest;test=cpu_gpu

* notest;test=cpu_gpu

* notest;test=cpu_gpu

* notest;test=cpu_gpu

* notest;test=cpu_gpu

* fix

* fix

* Modify ci time count & fix resnet50_quant multi_thread tests

* fix wrong time variable

* notest;test=gpu-inference

* notest;test=gpu-inference

* notest;test=gpu-inference

* notest;test=gpu-inference

* fix error

* notest;test=gpu-inference

* notest;test=gpu-inference

* notest;test=gpu-inference

* test=gpu-inference

* add resnet50 trt test in pr-ci-inference test

* [NPU] update NPU ci tests, test=npu_aarch64

* [NPU] fix x86 build and add disable_ut for NPU, test=npu_aarch64

* [NPU] address review comments, test=develop