From dc1b4a6f1300003ae27f033afbdff5e2683721ce Mon Sep 17 00:00:00 2001
From: Russell Bryant <rbryant@redhat.com>
Date: Sun, 13 Apr 2025 22:13:38 -0400
Subject: [PATCH] [Core][V0] Enable regex support with xgrammar (#13228)

Signed-off-by: Russell Bryant <rbryant@redhat.com>
---
 tests/entrypoints/llm/test_guided_generate.py     | 15 +++++++++++++--
 vllm/model_executor/guided_decoding/__init__.py   |  9 ++-------
 .../guided_decoding/xgrammar_decoding.py          | 10 ++++++++++
 3 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/tests/entrypoints/llm/test_guided_generate.py b/tests/entrypoints/llm/test_guided_generate.py
index 3b85ad68..e43e9826 100644
--- a/tests/entrypoints/llm/test_guided_generate.py
+++ b/tests/entrypoints/llm/test_guided_generate.py
@@ -286,15 +286,26 @@ def test_validation_against_both_guided_decoding_options(sample_regex, llm):
 
 @pytest.mark.skip_global_cleanup
 def test_disable_guided_decoding_fallback(sample_regex, llm):
+    # see has_xgrammar_unsupported_json_features()
+    unsupported_json = {
+        "type": "object",
+        "properties": {
+            "example": {
+                "type": "string",
+                "minLength": 5  # unsupported by xgrammar
+            }
+        }
+    }
     sampling_params = SamplingParams(temperature=0.8,
                                      top_p=0.95,
                                      guided_decoding=GuidedDecodingParams(
-                                         regex=sample_regex,
+                                         json=unsupported_json,
                                          backend="xgrammar:no-fallback"))
 
     with pytest.raises(
             ValueError,
-            match="xgrammar does not support regex guided decoding"):
+            match="xgrammar does not support advanced JSON schema features "
+            "like enums, patterns or numeric ranges."):
         llm.generate(prompts="This should fail",
                      sampling_params=sampling_params,
                      use_tqdm=True)
diff --git a/vllm/model_executor/guided_decoding/__init__.py b/vllm/model_executor/guided_decoding/__init__.py
index 6f0eede7..d4ee1be9 100644
--- a/vllm/model_executor/guided_decoding/__init__.py
+++ b/vllm/model_executor/guided_decoding/__init__.py
@@ -59,14 +59,9 @@ def maybe_backend_fallback(
         from vllm.model_executor.guided_decoding.xgrammar_decoding import (
             xgr_installed)
 
-        # xgrammar doesn't support regex, fallback to outlines
-        if guided_params.regex is not None:
-            fallback_or_error(
-                guided_params,
-                "xgrammar does not support regex guided decoding.", "outlines")
         # xgrammar doesn't support some JSON schema features
-        elif (guided_params.json is not None
-              and has_xgrammar_unsupported_json_features(guided_params.json)):
+        if (guided_params.json is not None and
+                has_xgrammar_unsupported_json_features(guided_params.json)):
             fallback_or_error(
                 guided_params,
                 "xgrammar does not support advanced JSON schema features like "
diff --git a/vllm/model_executor/guided_decoding/xgrammar_decoding.py b/vllm/model_executor/guided_decoding/xgrammar_decoding.py
index d7e600e9..ff223c3c 100644
--- a/vllm/model_executor/guided_decoding/xgrammar_decoding.py
+++ b/vllm/model_executor/guided_decoding/xgrammar_decoding.py
@@ -152,6 +152,7 @@ class GrammarConfig:
     grammar_str: str | None = None
     json_object: bool | None = None
     any_whitespace: bool = True
+    regex_str: str | None = None
     max_threads: int = 8
 
     @classmethod
@@ -255,6 +256,13 @@ class GrammarConfig:
                 max_threads=max_threads,
                 tokenizer_data=tokenizer_data,
             )
+        elif guided_params.regex:
+            return cls(
+                regex_str=guided_params.regex,
+                tokenizer_hash=tokenizer_hash,
+                max_threads=max_threads,
+                tokenizer_data=tokenizer_data,
+            )
         else:
             raise ValueError(
                 "Currently only support JSON and EBNF grammar mode for xgrammar"
@@ -330,6 +338,8 @@ class XGrammarLogitsProcessor:
                 self.ctx = compiler\
                     .compile_json_schema('{"type": "object"}',
                                          any_whitespace=any_whitespace)
+            elif self.config.regex_str:
+                self.ctx = compiler.compile_regex(self.config.regex_str)
             else:
                 raise ValueError(
                     "Invalid configuration for xgrammar logits processor")