### What this PR does / why we need it?
This PR updates the GLM-5 documentation to include:
- Information about the first supported version
(`vllm-ascend:v0.17.0rc1`).
- Updated `--additional-config` parameters to use the new nested
`ascend_compilation_config` structure.
- Added `VLLM_ASCEND_BALANCE_SCHEDULING` environment variable to
deployment scripts.
- Improved formatting of deployment steps.
- A new "Notice" section explaining optimization environment variables
(`VLLM_ASCEND_ENABLE_FLASHCOMM1`, `VLLM_ASCEND_ENABLE_FUSED_MC2`,
`VLLM_ASCEND_ENABLE_MLAPO`).
- A "Best Practices" section for prefill-decode disaggregation.
- An "FAQ" section addressing common tokenizer issues and function
calling configuration.
### Does this PR introduce _any_ user-facing change?
No, this is a documentation-only update.
### How was this patch tested?
Documentation changes were verified for correctness and formatting.
---------
Signed-off-by: Zhu Jiyang <zhujiyang2@huawei.com>
4969a0d783