A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 08:00 UTC
Clean up code (#844)
wenjun93 committed
Aug 24, 2023 at 07:44 UTC
75c0ca9d432199d336e0bc6ae854aa1d35ba35ce
1 file changed
-3
vllm/core/scheduler.py
-3
@@ -379,9 +379,6 @@ class Scheduler:
379
seq_group: SequenceGroup,
380
blocks_to_swap_out: Dict[int, int],
381
) -> None:
382
- seqs = seq_group.get_seqs(status=SequenceStatus.RUNNING)
383
- for seq in seqs:
384
- seq.status = SequenceStatus.SWAPPED
382
self._swap_out(seq_group, blocks_to_swap_out)
383
self.swapped.append(seq_group)
384