[CustomOp] Implement ApplyRotaryEmb CustomOp and register it

[shen-shanshan]

What this PR does / why we need it?

Following vllm-project/vllm#29873, implement ApplyRotaryEmb CustomOp and register it.

Does this PR introduce any user-facing change?

How was this patch tested?

Run:

vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct \
--max_model_len 16384 \
--max-num-batched-tokens 16384 \
--tensor-parallel-size 2 \
--enforce-eager

Output:

{"id":"chatcmpl-9ab4de23690c85aa","object":"chat.completion","created":1764748509,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the image reads \"TONGYI Qwen.\" The word \"TONGYI\" is written in blue, and \"Qwen\" is written in gray. The font appears to be modern and clean, with \"TONGYI\" being slightly larger than \"Qwen.\" The design includes a geometric, abstract shape on the left side of the logo, which complements the text.","refusal":null,"annotations":null,"audio":null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":78,"total_tokens":162,"completion_tokens":84,"prompt_tokens_details":null},"prompt_logprobs":null,"prompt_token_ids":null,"kv_transfer_params":null}

• vLLM version: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
• vLLM main: vllm-project/vllm@86e178f

[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 a custom operator AscendApplyRotaryEmb for applying rotary embeddings on Ascend hardware and registers it. The implementation refactors existing logic from patch_qwen2_5_vl.py. However, I've found a critical bug in the new AscendApplyRotaryEmb implementation where incorrect tensor shape manipulation will lead to a runtime error. The logic for preparing cos and sin tensors was copied from an implementation for a different model and is not compatible with the input tensor shapes for Qwen2.5-VL.

[Sparkheart]

Meaningless comments, recommended for deletion.

[shen-shanshan]

Meaningless comments, recommended for deletion.

Ok. In fact, all these codes will finally be removed recently. 😀

[github-actions]

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