EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[BugFix][v0.18.0] fix remote KV waiting promotion in balance scheduler (#8280)

Browse Source 
<!--  Thanks for sending a pull request!

BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html

-->
### What this PR does / why we need it?
## Problem

In PD-disaggregated serving with `mooncake_connector` and
`VLLM_ASCEND_BALANCE_SCHEDULING=1`, requests may enter
`WAITING_FOR_REMOTE_KVS` and never be promoted back to runnable state
after remote KV transfer finishes.

The issue is in `BalanceScheduler`'s handling of
`WAITING_FOR_REMOTE_KVS` requests. The current code treats
`_update_waiting_for_remote_kv()` as if it returns a boolean readiness
flag:

```python
is_ready = self._update_waiting_for_remote_kv(request)
if is_ready:
    ...
else:
    ...
```
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->

### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->

Signed-off-by: Pz1116 <zpbzpb123123@gmail.com>
This commit is contained in:
pz1116
2026-04-17 10:06:36 +08:00
committed by GitHub
parent f85144cc57
commit ceb1e49661
1 changed files with 8 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
vllm_ascend/patch/platform/patch_balance_schedule.py
View File

@@ -275,15 +275,7 @@ class BalanceScheduler(Scheduler):
# KVTransfer: skip request if still waiting for remote kvs.
if request.status == RequestStatus.WAITING_FOR_REMOTE_KVS:
is_ready = self._update_waiting_for_remote_kv(request)
if is_ready:
if request.num_preemptions:
# We must be loading for a resumed preemption
# rather than a new request.
request.status = RequestStatus.PREEMPTED
else:
request.status = RequestStatus.WAITING
else:
if request.request_id not in self.finished_recving_kv_req_ids:
logger.debug(
"%s is still in WAITING_FOR_REMOTE_KVS state.",
request_id,
@@ -291,6 +283,13 @@ class BalanceScheduler(Scheduler):
self.waiting.pop_request()
skipped_waiting_requests.prepend_request(request)
continue
self._update_waiting_for_remote_kv(request)
if request.num_preemptions:
# We must be loading for a resumed preemption
# rather than a new request.
request.status = RequestStatus.PREEMPTED
else:
request.status = RequestStatus.WAITING
# Skip request if the structured output request is still waiting
# for FSM compilation.