Improve structured outputs: fix race condition, server crash, metrics and style (#6188)

2025-05-11 08:36:16 -07:00
parent 94d42b6794
commit 01bdbf7f80
13 changed files with 568 additions and 258 deletions
--- a/python/sglang/srt/managers/schedule_batch.py
+++ b/python/sglang/srt/managers/schedule_batch.py
@@ -533,6 +533,7 @@ class Req:

        # Constrained decoding
        self.grammar: Optional[BaseGrammarObject] = None
+        self.grammar_wait_ct = 0

        # The number of cached tokens that were already cached in the KV cache
        self.cached_tokens = 0