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, 09:15 UTC
Add is_finished
Woosuk Kwon committed
Feb 24, 2023 at 11:44 UTC
b39f149a0853c6b6d48716f21fbb7b97828d17f4
1 file changed
+3
cacheflow/sequence.py
+3
@@ -86,6 +86,9 @@ class SequenceGroup:
86
return seq
87
raise ValueError(f'Sequence {seq_id} not found.')
88
89
+ def is_finished(self) -> bool:
90
+ return all(seq.status == SequenceStatus.FINISHED for seq in self.seqs)
91
+
92
def __repr__(self) -> str:
93
return (f'SequenceGroup(group_id={self.group_id}, '
94
f'num_seqs={len(self.seqs)})')