### What this PR does / why we need it?
Following https://github.com/vllm-project/vllm/pull/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:
```bash
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:
```bash
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:
ad32e3e19c
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
6c478531f8