[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>
This commit is contained in:
Lianmin Zheng
2025-12-01 16:34:34 -08:00
committed by GitHub
co-authored by github-actions[bot] <github-actions[bot]@users.noreply.github.com> Dan Zheng
parent 1da59e8304
commit 796d82b107
2 changed files with 15 additions and 0 deletions
@@ -172,6 +172,8 @@ class SchedulerMetricsMixin:
self.stats.num_grammar_queue_reqs = len(self.grammar_queue)
self.stats.cache_hit_rate = cache_hit_rate
self.stats.max_total_num_tokens = self.max_total_num_tokens
# Retract
self.stats.num_retracted_reqs = self.num_retracted_reqs
self.stats.num_paused_reqs = self.num_paused_reqs
@@ -320,6 +322,8 @@ class SchedulerMetricsMixin:
self.stats.num_grammar_queue_reqs = len(self.grammar_queue)
self.stats.cache_hit_rate = cache_hit_rate
self.stats.max_total_num_tokens = self.max_total_num_tokens
# Speculative decoding
self.stats.spec_accept_rate = spec_accept_rate
self.stats.spec_accept_length = spec_accept_length