### What this PR does / why we need it?
Following https://github.com/vllm-project/vllm/pull/30125, register
`AscendMMEncoderAttention` CustomOp and remove related patch.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
✅ Run Qwen2.5-VL:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct \
--max_model_len 16384
```
Output:
```
{"id":"chatcmpl-b4e3053f30ab2442","object":"chat.completion","created":1764922950,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the image is \"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}
```
✅ Run Qwen3-VL:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct \
--max_model_len 16384
```
Output:
```
{"id":"chatcmpl-97571fbda8267bd1","object":"chat.completion","created":1764923306,"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>
Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
b84ad8c5d8