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
[Minor] Fix CompletionOutput.__repr__ (#157)
Woosuk Kwon committed
Jun 18, 2023 at 19:58 UTC
7e2a913c64bae56e1835e061d3b23c490508ec52
1 file changed
+1
-1
vllm/outputs.py
+1
-1
@@ -41,7 +41,7 @@ class CompletionOutput:
41
f"text={self.text!r}, "
42
f"token_ids={self.token_ids}, "
43
f"cumulative_logprob={self.cumulative_logprob}, "
44
- f"logprobs={self.logprobs},"
44
+ f"logprobs={self.logprobs}, "
45
f"finish_reason={self.finish_reason})")
46
47