[ops] npu_top_k_top_p supports k or p is None

[linfeng-yuan]

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

• vLLM version: v0.11.0
• vLLM main: vllm-project/vllm@83f478b

[gemini-code-assist]

Code Review

This pull request updates the _apply_top_k_top_p sampler function to leverage the npu_top_k_top_p operator when either k (top-k) or p (top-p) parameters are None. While the change correctly broadens the conditions for using the optimized NPU kernel, it introduces a potential for a runtime crash. My review focuses on a critical fix to handle empty tensors safely.

[gemini-code-assist]

This condition is unsafe. If k is a non-None but empty tensor, k.max() will raise a RuntimeError, causing a crash. Please add a check to ensure the tensor is not empty before calling .max().

Suggested change

	if k is None or 1 <= int(k.max()) <= 1024:
	if k is None or (k.numel() > 0 and 1 <= int(k.max()) <= 1024):

[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.