Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
61485844
Unverified
Commit
61485844
authored
Nov 17, 2025
by
Bangsheng Tang
Committed by
GitHub
Nov 17, 2025
Browse files
[BugFix] Corner case that could cause out-of-sync with external launcher mode and dp >1 (#28774)
parent
f77bce00
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
12 additions
and
0 deletions
+12
-0
vllm/v1/worker/gpu_model_runner.py
vllm/v1/worker/gpu_model_runner.py
+12
-0
No files found.
vllm/v1/worker/gpu_model_runner.py
View file @
61485844
...
@@ -2663,6 +2663,18 @@ class GPUModelRunner(
...
@@ -2663,6 +2663,18 @@ class GPUModelRunner(
return
make_empty_encoder_model_runner_output
(
scheduler_output
)
return
make_empty_encoder_model_runner_output
(
scheduler_output
)
if
not
num_scheduled_tokens
:
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
():
if
not
has_kv_transfer_group
():
# Return empty ModelRunnerOutput if no work to do.
# Return empty ModelRunnerOutput if no work to do.
return
EMPTY_MODEL_RUNNER_OUTPUT
return
EMPTY_MODEL_RUNNER_OUTPUT
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment