[Auto Sync] Update scheduler.py (20260104) (#16424)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com>
Co-authored-by: Hanming Lu <hanming@x.ai>
Co-authored-by: Jie Ren <no-replay@github.com>
This commit is contained in:
Lianmin Zheng
2026-01-04 23:32:56 -08:00
committed by GitHub
parent 7f6a678f8f
commit 012dc5866d
2 changed files with 107 additions and 3 deletions

View File

@@ -2510,6 +2510,7 @@ class Scheduler(
"token_capacity": int(self.max_total_num_tokens),
"graph": round(self.tp_worker.model_runner.graph_mem_usage, 2),
}
ret["effective_max_running_requests_per_dp"] = self.max_running_requests
if not self.spec_algorithm.is_none() and self.spec_total_num_forward_ct > 0:
ret["avg_spec_accept_length"] = (