fix dp of has_unfinished_dp

[zhaowei1936]

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

• vLLM version: v0.10.2
• vLLM main: vllm-project/vllm@4e5affe

[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.

[gemini-code-assist]

Code Review

This pull request introduces Ascend-specific implementations for data parallel group initialization and for checking for unfinished sequences across data parallel workers. This is achieved by monkey-patching methods on vllm.config.ParallelConfig. The changes appear functionally correct, but I have one suggestion to improve the implementation of ascend_has_unfinished_dp to be more idiomatic and clearer by using boolean tensors and logical operators, which is a better practice for this kind of distributed check.

[gemini-code-assist]

For improved clarity and correctness, it's better to use a boolean tensor with a logical OR operation (ReduceOp.LOR) for this check. The current implementation uses an integer tensor with ReduceOp.MAX, which works but is less direct and requires comments to explain the logic. Using torch.bool and ReduceOp.LOR is more idiomatic for boolean reductions and makes the code's intent self-evident, removing the need for extra casting and explanatory comments.

Suggested change

	tensor = torch.tensor([has_unfinished], dtype=torch.int32, device="npu")
	# dp rank 0: has_unfinished_seqs=True
	# dp rank 1: has_unfinished_seqs=False
	# aggregated: has_unfinished_seqs=True
	# so this is an OR operation, i.e. MAX in integers
	torch.distributed.all_reduce(tensor, op=ReduceOp.MAX, group=dp_group)
	aggregated_has_unfinished = bool(tensor.item())
	return aggregated_has_unfinished
	tensor = torch.tensor([has_unfinished], dtype=torch.bool, device="npu")
	torch.distributed.all_reduce(tensor, op=ReduceOp.LOR, group=dp_group)
	return tensor.item()