[CustomOp] Register AscendApplyRotaryEmb CustomOp and remove related patch

[shen-shanshan]

What this PR does / why we need it?

Following vllm-project/vllm#29873, register AscendApplyRotaryEmb CustomOp and remove related patch.

Does this PR introduce any user-facing change?

How was this patch tested?

✅ Test Qwen2.5-VL

Run:

vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct \
--max_model_len 16384

Output:

{"id":"chatcmpl-b02c1ff3415d2462","object":"chat.completion","created":1766129265,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-In struct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the illustration is \"TONGYI Qwen.\" The word \"TONGYI\" is writ  ten in blue, and \"Qwen\" is written in gray. The text appears to be part of a logo or branding design.","refusal":null,"annotations":null,"audio":   null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"stop","stop_reason":null,"tok    en_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":78,"total_tokens":129,"completion_tokens":51,"prompt_tokens_d

✅ Test Qwen3-VL

Run:

vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct \
--max_model_len 16384

Output:

{"id":"chatcmpl-a3a7de5a900a9321","object":"chat.completion","created":1766129586,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the illustration is **“TONGYI Qwen”**.\n\n### How it looks:\n- **“TONGYI”** is written in **uppercase letters** in a **bold, modern sans-serif font**, colored **blue**.\n- **“Qwen”** is written in **lowercase letters** in a **slightly thinner, elegant sans-serif font**, colored **dark gray**.\n- The two lines of text are stacked vertically, with “TONG","refusal":null,"annotations":null,"audio":null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"length","stop_reason":null,"token_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":112,"total_tokens":212,"completion_tokens":100,"prompt_tokens_details":null},"prompt_logprobs":null,"prompt_token_ids":null,"kv_transfer_params":null}

• 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.

[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.

[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.

[wangxiyuan]

https://github.com/vllm-project/vllm-ascend/blob/main/vllm_ascend/patch/__init__.py should be updated as well. And delete related comment by this #5196 as well.

[github-actions]

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

[shen-shanshan]

CC @wangxiyuan All CI passed.