@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 3d33e372a1
Fork 0

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