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/test/srt/test_metrics.py
+++ b/test/srt/test_metrics.py
@@ -56,6 +56,7 @@ class TestEnableMetrics(CustomTestCase):
                "sglang:token_usage",
                "sglang:gen_throughput",
                "sglang:num_queue_reqs",
+                "sglang:num_grammar_queue_reqs",
                "sglang:cache_hit_rate",
                "sglang:spec_accept_length",
                "sglang:prompt_tokens_total",