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, 06:45 UTC
Fix `__repr__` of `SequenceOutputs` (#1311)
Wang Ran (汪然) committed
Oct 11, 2023 at 00:58 UTC
ac5cf86aa6aebbf9e42df51f7e377fbee85bc703
1 file changed
+2
-2
vllm/sequence.py
+2
-2
@@ -359,8 +359,8 @@ class SequenceOutputs:
359
360
def __repr__(self) -> str:
361
return (f"SequenceOutputs(parent_seq_id={self.parent_seq_id}, "
362
- f"output_token={self.output_token}), "
363
- f"logprobs={self.logprobs}")
362
+ f"output_token={self.output_token}, "
363
+ f"logprobs={self.logprobs})")
364
365
def __eq__(self, other: object) -> bool:
366
if not isinstance(other, SequenceOutputs):