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 16, 20:45 UTC
[Bugfix] Fix a log error in chunked prefill (#6694)
Woosuk Kwon committed
Jul 23, 2024 at 09:27 UTC
461089a21a5b00d6c6712e3bf371ce2d9cfa0860
1 file changed
+1
-1
vllm/config.py
+1
-1
@@ -814,7 +814,7 @@ class SchedulerConfig:
814
if enable_chunked_prefill:
815
logger.info(
816
"Chunked prefill is enabled with max_num_batched_tokens=%d.",
817
- max_num_batched_tokens)
817
+ self.max_num_batched_tokens)
818
819
self.max_num_seqs = max_num_seqs
820
self.max_model_len = max_model_len