xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 01:15:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

[NIXL] Improve request_finished() debug logs (#25665)

Browse Source 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
This commit is contained in:
Mark McLoughlin 2025-10-16 14:55:17 +01:00 committed by GitHub
parent 314fa8abbf
commit 4a510ab487
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
View File

@ -463,7 +463,9 @@ class NixlConnectorScheduler:
params = request.kv_transfer_params params = request.kv_transfer_params
logger.debug( logger.debug(
"NIXLConnector request_finished, request_status=%s, kv_transfer_params=%s", "NIXLConnector request_finished(%s), request_status=%s, "
"kv_transfer_params=%s",
request.request_id,
request.status, request.status,
params, params,
) )
@ -495,6 +497,12 @@ class NixlConnectorScheduler:
if delay_free_blocks: if delay_free_blocks:
# Prefill request on remote. It will be read from D upon completion # Prefill request on remote. It will be read from D upon completion
logger.debug(
"NIXLConnector request_finished(%s) waiting for %d seconds "
"for remote decode to fetch blocks",
request.request_id,
envs.VLLM_NIXL_ABORT_REQUEST_TIMEOUT,
)
self._reqs_need_send[request.request_id] = ( self._reqs_need_send[request.request_id] = (
time.perf_counter() + envs.VLLM_NIXL_ABORT_REQUEST_TIMEOUT time.perf_counter() + envs.VLLM_NIXL_ABORT_REQUEST_TIMEOUT
) )