Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[BugFix][Core] Multistep Fix Crash on Request Cancellation #8059

Merged
merged 6 commits into from
Aug 31, 2024
Merged

[BugFix][Core] Multistep Fix Crash on Request Cancellation #8059

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
23817b2
avoid crash on abort
robertgshaw2-neuralmagic Aug 31, 2024
0c129f2
fix
robertgshaw2-neuralmagic Aug 31, 2024
550d9b9
format
robertgshaw2-neuralmagic Aug 31, 2024
f6b566f
Revert "format"
robertgshaw2-neuralmagic Aug 31, 2024
a0e0ab2
format
robertgshaw2-neuralmagic Aug 31, 2024
c7880e6
Update multi_step.py
robertgshaw2-neuralmagic Aug 31, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion vllm/engine/output_processor/multi_step.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,9 +88,15 @@ def process_outputs(self,
# TODO: Add support for async if necessary
assert not is_async

# Sequences can be in RUNNING or FINISHED_ABORTED state
# once scheduled, as a sequence is moved to FINSIHED_ABORTED
# if a client disconnects from the api server.
seqs = sequence_group.get_seqs(status=SequenceStatus.RUNNING)
if seqs is None:
seqs = sequence_group.get_seqs(
status=SequenceStatus.FINISHED_ABORTED)

assert seqs, "expected running sequences"
assert seqs, "Expected RUNNING or FINISHED_ABORTED sequences"
assert len(seqs) == 1, (
"Beam search not supported in multi-step decoding.")
seq = seqs[0]
Expand Down
Loading