[npugraph_ex]enable npugraph_ex by default (#6664)

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

This pull request enables the `npugraph_ex` backend by default to
improve performance on Ascend NPUs, as proposed in the
[RFC](https://github.com/vllm-project/vllm-ascend/issues/6214).


### Does this PR introduce _any_ user-facing change?

Yes. `npugraph_ex` is now enabled by default. Users can disable it by
setting `enable: false` in the `npugraph_ex_config` section of the
`additional_config`.

### How was this patch tested?

CI passed. The changes are covered by existing and new E2E tests
(`test_aclgraph_accuracy.py`) and unit tests (`test_ascend_config.py`)
that have been updated to reflect the new default behavior. The tests
verify correctness and consistency with `npugraph_ex` enabled and
disabled, as well as with the new static kernel option.

Signed-off-by: huyuanquan1 <huyuanquan1@huawei.com>
Co-authored-by: huyuanquan1 <huyuanquan1@huawei.com>

tests/e2e/singlecard/test_aclgraph_accuracy.py

@@ -147,6 +147,11 @@ def test_full_decode_only_res_consistency(cur_case: LLMTestCase, monkeypatch):
             "cudagraph_mode": "FULL_DECODE_ONLY"
         },
         "quantization": cur_case.quantization,
+        "additional_config": {
+            "npugraph_ex_config": {
+                "enable": False
+            }
+        },
     }
     gen_and_valid(runner_kwargs=runner_kwargs,
                   prompts=cur_case.prompts,

tests/ut/test_ascend_config.py

@@ -67,7 +67,7 @@ class TestAscendConfig(TestBase):
         self.assertTrue(ascend_config.multistream_overlap_shared_expert)
 
         npugraph_ex_config = ascend_config.npugraph_ex_config
-        self.assertFalse(npugraph_ex_config.enable)
+        self.assertTrue(npugraph_ex_config.enable)
         self.assertFalse(npugraph_ex_config.enable_static_kernel)
 
         ascend_compilation_config = ascend_config.ascend_compilation_config