[PD] Handle P/D failure and reconnect without affecting other instances (#6263)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
This commit is contained in:
@@ -417,6 +417,8 @@ class SchedulerDisaggregationPrefillMixin:
|
||||
self.tree_cache.cache_finished_req(req) # unlock the tree
|
||||
req.finished_reason = FINISH_LENGTH(length=0)
|
||||
# FIXME: clean up req's data in transfer engine
|
||||
if hasattr(req.disagg_kv_sender, "clear"):
|
||||
req.disagg_kv_sender.clear()
|
||||
done_reqs.append(req)
|
||||
elif poll == KVPoll.Failed:
|
||||
error_message = f"Prefill transfer failed for request rank={self.tp_rank} {req.rid=} {req.bootstrap_room=}"
|
||||
|
||||
Reference in New Issue
Block a user