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 15, 23:30 UTC
[Misc] Remove redundant statements in scheduler.py (#13229)
Wang Ran (汪然) committed
Feb 14, 2025 at 14:07 UTC
40932d7a05916a725890fd87e277b9204542bfa7
1 file changed
-1
vllm/core/scheduler.py
-1
@@ -770,7 +770,6 @@ class Scheduler:
770
swapped_queue.popleft()
771
self._swap_in(seq_group, blocks_to_swap_in)
772
self._append_slots(seq_group, blocks_to_copy, enable_chunking)
773
- is_prefill = seq_group.is_prefill()
773
if is_prefill:
774
prefill_seq_groups.append(
775
ScheduledSequenceGroup(