Support configuring the request limit per receiving poll (#14076)

Co-authored-by: Peng Wang <peng_wang@linux.alibaba.com> Co-authored-by: Feng Su <225349073+sufeng-buaa@users.noreply.github.com>
2025-11-28 16:14:21 +08:00
parent 621061f017
commit ab9a46d462
3 changed files with 12 additions and 0 deletions
@@ -178,6 +178,7 @@ class Envs:
    # Scheduler: others:
    SGLANG_EMPTY_CACHE_INTERVAL = EnvFloat(-1)  # in seconds. Set if you observe high memory accumulation over a long serving period.
    SGLANG_DISABLE_CONSECUTIVE_PREFILL_OVERLAP = EnvBool(False)
+    SGLANG_SCHEDULER_MAX_RECV_PER_POLL = EnvInt(-1)
    SGLANG_EXPERIMENTAL_CPP_RADIX_TREE = EnvBool(False)

    # Test: pd-disaggregation