[V0][V1][Core] Add outlines integration for V1, and update V0 integration. (#15975)

Signed-off-by: Nathan Hoos <thwackyy.y@gmail.com>

vllm/v1/engine/processor.py

@@ -23,6 +23,8 @@ from vllm.v1.engine import EngineCoreRequest
 from vllm.v1.engine.mm_input_cache import MirroredProcessingCache
 from vllm.v1.structured_output.backend_guidance import (
     validate_guidance_grammar)
+from vllm.v1.structured_output.backend_outlines import (
+    validate_structured_output_request_outlines)
 from vllm.v1.structured_output.backend_xgrammar import (
     validate_xgrammar_grammar)
 
@@ -193,6 +195,9 @@ class Processor:
             # https://github.com/guidance-ai/llguidance/blob/main/docs/syntax.md#special-tokens
             # Without tokenizer these are disallowed in grammars.
             validate_guidance_grammar(params, tokenizer=None)
+        elif engine_level_backend == "outlines":
+            # outlines backend
+            validate_structured_output_request_outlines(params)
         else:
             # NOTE: engine_level_backend must be "auto" here, because we have
             # checked supported_backends above.