[Feat][SP] Suport SP for VL MoE models (#7044)

### What this PR does / why we need it?

2nd PR for https://github.com/vllm-project/vllm-ascend/issues/5712,
extend SP to VL MoE models.


### Does this PR introduce _any_ user-facing change?
remove `sp_threshold` in additional config and reuse `sp_min_token_num`
from vLLM.


### How was this patch tested?
- Model: Qwen3-VL-30B-A3B, 
- TP4 DP2
- 100 reqs
- max concurrency 1

| Seq length | Mean TTFT (ms) main | Mean TTFT (ms) this PR |
|------------|---------------------|------------------------|
| 4k         | 429.40               | 323.3                  |
| 16k        | 1297.01              | 911.74                |

- vLLM version: v0.16.0
- vLLM main:
4034c3d32e

---------

Signed-off-by: realliujiaxu <realliujiaxu@163.com>

tests/e2e/multicard/2-cards/test_sp_pass.py

@@ -39,9 +39,9 @@ def test_qwen3_vl_sp_tp2(model: str) -> None:
         compilation_config={
             "cudagraph_capture_sizes": [2, 4],
             "cudagraph_mode": "FULL_DECODE_ONLY",
-            "pass_config": {"enable_sp": True},
+            "pass_config": {"enable_sp": True, "sp_min_token_num": 10},
         },
-        additional_config={"sp_threshold": 10, "ascend_compilation_config": {"enable_npugraph_ex": False}},
+        additional_config={"ascend_compilation_config": {"enable_npugraph_ex": False}},
     ) as runner:
         sp_outputs = runner.model.generate(prompts, sampling_params)