[Auto Sync] Add max_total_num_tokens metric: Update scheduler_metrics_mixin.py, collector.py (20251202) (#14256)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Dan Zheng <dzheng@x.ai>

python/sglang/srt/metrics/collector.py

@@ -184,6 +184,8 @@ class SchedulerStats:
     num_running_reqs_offline_batch: int = 0
     cache_hit_rate: float = 0.0
 
+    max_total_num_tokens: int = 0
+
     # Speculative decoding
     spec_accept_length: float = 0.0
     spec_accept_rate: float = 0.0
@@ -294,6 +296,13 @@ class SchedulerMetricsCollector:
             multiprocess_mode="mostrecent",
         )
 
+        self.max_total_num_tokens = Gauge(
+            name="sglang:max_total_num_tokens",
+            documentation="Maximum total number of tokens in the KV cache pool.",
+            labelnames=labels.keys(),
+            multiprocess_mode="mostrecent",
+        )
+
         # Speculative decoding
         self.spec_accept_length = Gauge(
             name="sglang:spec_accept_length",
@@ -640,6 +649,8 @@ class SchedulerMetricsCollector:
         )
         self._log_gauge(self.cache_hit_rate, stats.cache_hit_rate)
 
+        self._log_gauge(self.max_total_num_tokens, stats.max_total_num_tokens)
+
         # Speculative decoding
         self._log_gauge(self.spec_accept_length, stats.spec_accept_length)
         self._log_gauge(self.spec_accept_rate, stats.spec_accept_rate)