Skip to content
Merged
Changes from all commits
Commits
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
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