[v0.9.1][Bugfix] Fix guided decoding invalid backend (#2645)

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

```bash
pytest -sv tests/singlecard/test_guided_decoding.py
```

Come across an error:

```bash
FAILED tests/singlecard/test_guided_decoding.py::test_guided_json_completion[guidance:disable-any-whitespace] - NotImplementedError: VLLM_USE_V1=1 is not supported with --guided-decoding-backend=guidance:disable-any-whitespace.
FAILED tests/singlecard/test_guided_decoding.py::test_guided_regex[guidance:disable-any-whitespace] - NotImplementedError: VLLM_USE_V1=1 is not supported with --guided-decoding-backend=guidance:disable-any-whitespace.
```

### How was this patch tested?

Run:

```bash
pytest -sv tests/singlecard/test_guided_decoding.py
```

Output:

```bash
=========================================================================== test session starts ===========================================================================
platform linux -- Python 3.10.18, pytest-8.4.1, pluggy-1.6.0
rootdir: /home/sss/github/vllm-v0.9.1/vllm-ascend
configfile: pytest.ini
plugins: anyio-4.10.0, mock-3.14.1
collected 8 items                                                                                                                                                         

tests/singlecard/test_guided_decoding.py ss.ss..s                                                                                                                   [100%]

============================================================================ warnings summary =============================================================================
<frozen importlib._bootstrap>:241
  <frozen importlib._bootstrap>:241: DeprecationWarning: builtin type SwigPyPacked has no __module__ attribute

<frozen importlib._bootstrap>:241
  <frozen importlib._bootstrap>:241: DeprecationWarning: builtin type SwigPyObject has no __module__ attribute

../../../miniconda3/envs/vllm-v0.9.1/lib/python3.10/site-packages/torch_npu/dynamo/torchair/__init__.py:8
  /home/sss/miniconda3/envs/vllm-v0.9.1/lib/python3.10/site-packages/torch_npu/dynamo/torchair/__init__.py:8: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html
    import pkg_resources

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
========================================================== 3 passed, 5 skipped, 3 warnings in 193.21s (0:03:13) ===========================================================
```

---------

Signed-off-by: shen-shanshan <[email protected]>

Author: shen-shanshan

.github/workflows/vllm_ascend_test.yaml

@@ -179,8 +179,7 @@ jobs:
         run: |
           if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
             VLLM_USE_MODELSCOPE=True pytest -sv tests/singlecard/test_offline_inference.py
-            # guided decoding doesn't work, fix it later
-            # pytest -sv tests/singlecard/test_guided_decoding.py.py
+            pytest -sv tests/singlecard/test_guided_decoding.py
             # test_ascend_config.py should be ran separately because it will regenerate the global config many times.
             pytest -sv tests/singlecard/test_ascend_config.py
             pytest -sv tests/singlecard/test_camem.py
@@ -216,8 +215,7 @@ jobs:
         run: |
           if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
             VLLM_USE_MODELSCOPE=True  pytest -sv tests/singlecard/test_offline_inference.py
-            # guided decoding doesn't work, fix it later
-            # pytest -sv tests/singlecard/test_guided_decoding.py.py
+            pytest -sv tests/singlecard/test_guided_decoding.py
             pytest -sv tests/singlecard/test_camem.py
             # test_ascend_config.py should be ran separately because it will regenerate the global config many times.
             pytest -sv tests/singlecard/test_ascend_config.py

tests/singlecard/test_guided_decoding.py

@@ -34,7 +34,7 @@
     "lm-format-enforcer",
     "xgrammar",
 ]
-GuidedDecodingBackendV1 = ["xgrammar", "guidance:disable-any-whitespace"]
+GuidedDecodingBackendV1 = ["xgrammar", "guidance"]
 GuidedDecodingBackend = list(
     set(GuidedDecodingBackendV0 + GuidedDecodingBackendV1))
 
@@ -94,6 +94,10 @@ def test_guided_json_completion(guided_decoding_backend: str,
         # xgrammar does not support json schema, will fall back to outlines, skip it
         pytest.skip(
             f"{guided_decoding_backend} will fall back to outlines, skip it")
+    if guided_decoding_backend == "outlines":
+        pytest.skip(
+            f"{guided_decoding_backend} will take up too much time for json "
+            "completion, skip it")
     if guided_decoding_backend not in GuidedDecodingBackendV0 and os.getenv(
             "VLLM_USE_V1") == "0":
         # guidance does not support on v0, skip it