EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[PD] Fix abort_request for PD disaggregation (#8352)

Browse Source 
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>
This commit is contained in:
Shangming Cai
2025-07-28 12:48:27 +08:00
committed by GitHub
parent 4ad9737045
commit 2fd5c7049f
2 changed files with 47 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
python/sglang/srt/managers/scheduler.py
View File

@@ -2440,6 +2440,37 @@ class Scheduler(
req.grammar.cancel()
req.set_finish_with_abort("Aborted by AbortReq.")
# Delete requests not in the waiting queue when PD disaggregation is enabled
if self.disaggregation_mode == DisaggregationMode.PREFILL:
# Abort requests that have not yet been bootstrapped
for i, req in enumerate(self.disagg_prefill_bootstrap_queue.queue):
logger.debug(f"Abort bootstrap queue request. {req.rid=}")
if recv_req.abort_all or req.rid.startswith(recv_req.rid):
if hasattr(req.disagg_kv_sender, "abort"):
req.disagg_kv_sender.abort()
# Abort in-flight requests
for i, req in enumerate(self.disagg_prefill_inflight_queue):
logger.debug(f"Abort inflight queue request. {req.rid=}")
if recv_req.abort_all or req.rid.startswith(recv_req.rid):
if hasattr(req.disagg_kv_sender, "abort"):
req.disagg_kv_sender.abort()
elif self.disaggregation_mode == DisaggregationMode.DECODE:
# Abort requests that have not yet finished preallocation
for i, decode_req in enumerate(self.disagg_decode_prealloc_queue.queue):
logger.debug(f"Abort prealloc queue request. {decode_req.req.rid=}")
if recv_req.abort_all or decode_req.req.rid.startswith(recv_req.rid):
if hasattr(decode_req.kv_receiver, "abort"):
decode_req.kv_receiver.abort()
# Abort requests waiting for kvcache to release tree cache
for i, decode_req in enumerate(self.disagg_decode_transfer_queue.queue):
logger.debug(f"Abort transfer queue request. {decode_req.req.rid=}")
if recv_req.abort_all or decode_req.req.rid.startswith(recv_req.rid):
if hasattr(decode_req.kv_receiver, "abort"):
decode_req.kv_receiver.abort()
# Delete requests in the running batch
if self.cur_batch is self.running_batch or self.cur_batch is None:
reqs = self.running_batch.reqs