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, 00:30 UTC
[BugFix] Fix log message about default max model length (#5284)
Nick Hill committed
Jun 5, 2024 at 14:53 UTC
3d33e372a14614b13a793f374e59bddb3027527e
1 file changed
+1
-1
vllm/config.py
+1
-1
@@ -1223,7 +1223,7 @@ def _get_and_verify_max_len(
1223
logger.warning(
1224
"The model's config.json does not contain any of the following "
1225
"keys to determine the original maximum length of the model: "
1226
- "%d. Assuming the model's maximum length is %d.", possible_keys,
1226
+ "%s. Assuming the model's maximum length is %d.", possible_keys,
1227
default_max_len)
1228
derived_max_model_len = default_max_len
1229