* [PYTHON] Support DLTensor compatible API

* optimize for common path

* [DOC] Doc redirection

* fix setup url

* [CODEGEN/RUNTIME] Metal support, runtime improvement.

* Fix case when no device is available

* [CODEGEN/PASS] Improve callpacked lowering, allow pass array callback.

* fix cython

* [LANG/CODEGEN] Intrinsics and Extern Math

* fix lint

* [DOC] API doc organization.

* remove breathe for now

* Add setup.py, fix comments

* Update installation document

* [DOC] Initial doc system

* Migrate API

* Update docs

* [PERF] Persitent kernel

* fix doc