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
[Bugfix] Fix missing parentheses (#13263)
Xu Song committed
Feb 14, 2025 at 17:07 UTC
83481ceb499b105b11e7ae1507a409c6f7711bfa
1 file changed
+2
-2
vllm/sequence.py
+2
-2
@@ -381,7 +381,7 @@ class SequenceData(msgspec.Struct,
381
f"prompt_token_ids={self._prompt_token_ids}, "
382
f"output_token_ids={self.output_token_ids}, "
383
f"cumulative_logprob={self.cumulative_logprob}, "
384
- f"get_num_computed_tokens={self.get_num_computed_tokens()}")
384
+ f"get_num_computed_tokens={self.get_num_computed_tokens()})")
385
386
387
class Sequence:
@@ -606,7 +606,7 @@ class Sequence:
606
def __repr__(self) -> str:
607
return (f"Sequence(seq_id={self.seq_id}, "
608
f"status={self.status.name}, "
609
- f"num_blocks={self.n_blocks}, ")
609
+ f"num_blocks={self.n_blocks})")
610
611
612
class SequenceGroupState(msgspec.Struct,