[Feature]refactor the npugraph_ex config, support online-infer with static kernel (#5775)

### What this PR does / why we need it?
This is a part of
https://github.com/vllm-project/vllm-ascend/issues/4715#issue-3694310762
1. refactor the npugraph_ex config，modified the default configuration of
the static kernel, new default value of static kernel is false
2. support online-infer with static kernel
3. fixed the issue where manually modifying FX graphs caused an abnormal
model return type, and removed the related redundant code.

### Does this PR introduce _any_ user-facing change?
yes，the new config of npugraph_ex is as follow:
```
additional_config={
            "npugraph_ex_config": {
                "enable": True,
                "enable_static_kernel": False
            }
        }
```
### How was this patch tested?
```
vllm serve /data/DeepSeek-V3.1-Terminus-w4a8 \
    --host 0.0.0.0 \
    --port 8004 \
    --data-parallel-size 4 \
    --tensor-parallel-size 4 \
    --quantization ascend \
    --seed 1024 \
    --served-model-name deepseek_v3 \
    --enable-expert-parallel \
    --max-num-seqs 48 \
    --max-model-len 40000 \
    --async-scheduling \
    --max-num-batched-tokens 9000 \
    --trust-remote-code \
    --no-enable-prefix-caching \
    --speculative-config '{"num_speculative_tokens": 3, "method":"deepseek_mtp","disable_padded_drafter_batch": false}' \
    --gpu-memory-utilization 0.9 \
    --compilation-config '{"cudagraph_capture_sizes":[4,32,64,112,160,176,192], "cudagraph_mode": "FULL_DECODE_ONLY"}' \
    --additional-config \
    '{"enable_shared_expert_dp": true,"multistream_overlap_shared_expert": true,"npugraph_ex_config":{"enable":true}}'
```

- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef

---------

Signed-off-by: chencangtao <chencangtao@huawei.com>
Signed-off-by: ChenCangtao <50493711+ChenCangtao@users.noreply.github.com>
Co-authored-by: chencangtao <chencangtao@huawei.com>

tests/ut/test_ascend_config.py

@@ -65,7 +65,10 @@ class TestAscendConfig(TestBase):
         ascend_config = init_ascend_config(test_vllm_config)
         self.assertEqual(ascend_config.eplb_config.num_redundant_experts, 2)
         self.assertTrue(ascend_config.multistream_overlap_shared_expert)
-        self.assertFalse(ascend_config.enable_npugraph_ex)
+
+        npugraph_ex_config = ascend_config.npugraph_ex_config
+        self.assertFalse(npugraph_ex_config.enable)
+        self.assertFalse(npugraph_ex_config.enable_static_kernel)
 
         ascend_compilation_config = ascend_config.ascend_compilation_config
         self.assertFalse(ascend_compilation_config.fuse_norm_quant)
@@ -79,11 +82,16 @@ class TestAscendConfig(TestBase):
     def test_init_ascend_config_enable_npugraph_ex(self, mock_fix_incompatible_config):
         test_vllm_config = VllmConfig()
         test_vllm_config.additional_config = {
-            "enable_npugraph_ex": True,
-            "refresh": True,
+            "npugraph_ex_config": {
+                "enable": True,
+                "enable_static_kernel": True
+            },
+            "refresh": True
         }
-        ascend_config = init_ascend_config(test_vllm_config)
-        self.assertTrue(ascend_config.enable_npugraph_ex)
+        npugraph_ex_config = init_ascend_config(
+            test_vllm_config).npugraph_ex_config
+        self.assertTrue(npugraph_ex_config.enable)
+        self.assertTrue(npugraph_ex_config.enable_static_kernel)
 
     @_clean_up_ascend_config
     @patch("vllm_ascend.platform.NPUPlatform._fix_incompatible_config")