[ascend] support glm52

[wanfengcxz]

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Support GLM-5.2 W8A8 inference

Modification

1. Add Ascend GLM-5.2 W8A8 inference support with ModelSlim quantization metadata, static W8A8 linear, dynamic W8A8 MoE, and TP/EP-aware weight loading.
2. Add the Ascend BF16 DSA/MLA path, including Lightning Indexer, sparse attention, 128-sized paged KV cache, and graph-safe attention metadata.
3. Add dlinfer interleaved RoPE; fix shared-expert communication.

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
3. If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
4. The documentation has been modified accordingly, like docstring or example tutorials.