refactor rejection sampler

[realliujiaxu]

What this PR does / why we need it?

Currently, we are using AscendRejctionSampler that extends from RejctionSampler in spec decoding. AscendRejctionSampler override forward of RejctionSampler, only aming to replace rejection_sample func. This
causes a lot of code of RejctionSampler cannot be reused, for example:

• [V1] Logit processors for rejection sampler vllm#19482
• [V1][spec decode] return logprobs for spec decoding vllm#26060
• [Core] Support logprobs with spec decode + async scheduling  vllm#29223

Proposed Change:

• Delete AscendRejctionSampler and use RejctionSampler directly in model runner.
• Patch RejctionSampler.expand_batch_to_tokens and RejctionSampler.rejection_sample, maybe a better way is to make them as custom ops.
• Modify NPUModelRunner following [V1][spec decode] return logprobs for spec decoding vllm#26060

Does this PR introduce any user-facing change?

How was this patch tested?

• test logits processor for spec decoding

• test logprobs for spec decoding

• test logprobs for spec decoding + async shcheduling

• vLLM version: v0.12.0

• vLLM main: vllm-project/vllm@ad32e3e

[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.

[gemini-code-assist]

Code Review

This pull request refactors the rejection sampler implementation to better align with the upstream vLLM project. The custom AscendRejectionSampler class is removed in favor of using the standard vllm.v1.sample.rejection_sampler.RejectionSampler and monkey-patching its dependencies with Ascend-optimized implementations. This is a solid architectural improvement that will enhance maintainability. The sample_tokens method in NPUModelRunner has also been cleanly refactored into smaller, more focused helper methods. The changes appear correct and logically sound. I have not found any issues of high or critical severity.

[github-actions]

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

[github-actions]

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

[github-actions]

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