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
[Minor] Fix printing format
Woosuk Kwon committed
Feb 24, 2023 at 11:56 UTC
6aef2278f457e564c17a84465b8b4e74986ccd3c
1 file changed
+1
-1
cacheflow/master/frontend.py
+1
-1
@@ -53,4 +53,4 @@ class Frontend:
53
for seq in seq_group.seqs:
54
token_ids = seq.get_token_ids()
55
output = self.tokenizer.decode(token_ids, skip_special_tokens=True)
56
- print(f'Seq {seq.seq_id}: {output}')
56
+ print(f'Seq {seq.seq_id}: {output!r}')