xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-05 03:37:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BugFix] Corner case that could cause out-of-sync with external launcher mode and dp >1 (#28774)

Browse Source
This commit is contained in:
Bangsheng Tang 2025-11-17 15:22:11 -08:00 committed by GitHub
parent f77bce001a
commit 61485844fc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
vllm/v1/worker/gpu_model_runner.py
View File

@ -2663,6 +2663,18 @@ class GPUModelRunner(
return make_empty_encoder_model_runner_output(scheduler_output)
if not num_scheduled_tokens:
if (
self.parallel_config.distributed_executor_backend
== "external_launcher"
and self.parallel_config.data_parallel_size > 1
):
# this is a corner case when both external launcher
# and DP are enabled, num_scheduled_tokens could be
# 0, and has_unfinished_requests in the outer loop
# returns True. before returning early here we call
# dummy run to ensure coordinate_batch_across_dp
# is called into to avoid out of sync issues.
self._dummy_run(1)
if not has_kv_transfer_group():
# Return empty ModelRunnerOutput if no work to do.
return EMPTY_MODEL_RUNNER_OUTPUT