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 14, 05:30 UTC
fix: print outputt offline_inference/base/chat.py example (#25744)
Signed-off-by: Iceber Gu <caiwei95@hotmail.com>
Iceber Gu committed
Sep 26, 2025 at 16:18 UTC
6e30010d2fc409471d10781b767157025c34827f
1 file changed
+1
examples/offline_inference/basic/chat.py
+1
@@ -87,6 +87,7 @@ def main(args: dict):
87
use_tqdm=False,
88
chat_template=chat_template,
89
)
90
+ print_outputs(outputs)
91
92
93
if __name__ == "__main__":