support glm5

[grimoire]

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

Please describe the motivation of this PR and the goal you want to achieve through this PR.

Modification

Please briefly describe what modification is made in this PR.

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.

[Copilot]

Pull request overview

This PR extends LMDeploy’s model support by adding a dedicated config builder for Deepseek V3.2–style models (including a GLM-5-related model_type) and updating documentation to list GLM-5 as supported.

Changes:

• Add DeepseekV32ModelConfigBuilder and route model_type deepseek_v32 / glm_moe_dsa to the V3.2-specific cache/env configuration.
• Simplify/guard Deepseek V3.2 model internals (remove unused scale_fmt, avoid unconditional rope scaling factor lookup).
• Update supported-model docs and READMEs to include GLM-5.

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
lmdeploy/pytorch/models/deepseek_v32.py	Removes an unused quant field and tightens rope scaling logic to avoid unnecessary key access.
lmdeploy/pytorch/configurations/deepseek_v32.py	Introduces a V3.2-specific config builder with env checks and FP8 cache shape setup; includes glm_moe_dsa routing.
lmdeploy/pytorch/configurations/deepseek_v2.py	Removes V3.2 special-casing now handled by the new dedicated builder.
docs/zh_cn/supported_models/supported_models.md	Adds GLM-5 to the supported model table.
docs/en/supported_models/supported_models.md	Adds GLM-5 to the supported model table.
README.md	Lists GLM-5 among supported models.
README_zh-CN.md	Lists GLM-5 among supported models.
README_ja.md	Lists GLM-5 among supported models.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Avoid using assert for runtime/environment requirements (asserts are skipped with python -O). Raise a RuntimeError/ValueError with the same message instead so the check is always enforced.

Suggested change

	assert hf_config.use_flash_mla, 'DeepSeek-V3.2 requires flash_mla to be available.'
	if not hf_config.use_flash_mla:
	raise RuntimeError('DeepSeek-V3.2 requires flash_mla to be available.')