[Core][V0] Add guidance backend for structured output (#14589)

Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Loc Huynh <lohuynh@microsoft.com>
Co-authored-by: Michal Moskal <michal@moskal.me>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>

vllm/config.py

@@ -2785,7 +2785,9 @@ class DecodingConfig:
         return hash_str
 
     def __post_init__(self):
-        valid_guided_backends = ['outlines', 'lm-format-enforcer', 'xgrammar']
+        valid_guided_backends = [
+            'outlines', 'lm-format-enforcer', 'xgrammar', 'guidance'
+        ]
 
         backend = GuidedDecodingParams(
             backend=self.guided_decoding_backend).backend_name