Merge pull request !25082 from DeshiChen/1015_set_kernel_attr

it's unreasonable to change the node when generating kernel json.
instead, it should be set in a pass.

most of the operators in original akg_kernel_attrs_process are not longer used,
so we deleted them, leaving only the "Cast" and "MatMul/BatchMatMul".

This reverts commit b077aa1cab.

Revert "[feat] [assistant] [I3T96X] add new Dataset operator LibriSpeechDataset"

This reverts commit 4e6f7dc97d.

delete pass_registry_test.cc

comment  hiai_nlu_model_multi.pb related  line

Merge pull request !21653 from ZengZitao/gk_fix_waring_master

deal with workspace on cuda

Signed-off-by: zhoufeng <zhoufeng54@huawei.com>

1. Update akg submodule
2. Refactor akg_kernel_build, akg_ascend_kernel_build, akg_gpu_kernel_build
3. Add akg_kernel_json_decoder to support converting kernel_json to AnfNode.
4. Add GraphKernel Cost Model. (mindspore/_extends/graph_kernel)
5. Add some GraphKernel passes to GpuSession, move these passes to backend/optimizer/graph_kernel.
6. Add global id for ir files.
7. Fix bug in ConstInputToAttr.

Signed-off-by: zhoufeng <zhoufeng54@huawei.com>

Merge pull request !3938 from liubuyu/master