[PD] Fix dynamic port support and MLA buffer for Mooncake (#5415)

Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> Co-authored-by: ybyang <ybyang7@iflytek.com>
2025-04-15 19:29:31 +08:00
parent 471650dee0
commit ffde65a094
6 changed files with 171 additions and 180 deletions
--- a/python/sglang/srt/managers/scheduler.py
+++ b/python/sglang/srt/managers/scheduler.py
@@ -599,6 +599,7 @@ class Scheduler(
                bootstrap_port=self.server_args.disaggregation_bootstrap_port,
                gloo_group=self.tp_worker.get_attention_tp_cpu_group(),
                transfer_backend=self.transfer_backend,
+                scheduler=self,
            )
            # The prefill requests that are in the middle of kv sending
            self.disagg_prefill_inflight_queue: List[Req] = []