Add worker interface "reload_weights"

[ivyilike]

What this PR does / why we need it?

Some worker interfaces called by vLLM are missing in vLLM Ascend. It's good to add the support.
this PR add support to "reload_weights" interface.
this will explicitly reload weights inplace, without re-initialize the model

• vLLM version: v0.12.0
• vLLM main: vllm-project/vllm@ad32e3e

[wangxiyuan]

Thanks!

[gemini-code-assist]

Code Review

This pull request adds a reload_weights interface to the Ascend worker, allowing for in-place reloading of model weights without re-initializing the model. The implementation correctly adds the reload_weights method to NPUModelRunner and NPUWorker. However, there is a critical issue in NPUWorker.reload_weights where an assertion will incorrectly fail when sleep mode is enabled, preventing the feature from working as intended in that configuration.

[github-actions]

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

• A PR should do only one thing, smaller PRs enable faster reviews.
• Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
• Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

[github-actions]

This pull request has conflicts, please resolve those before we can evaluate the pull request.