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
[misc] fix typo in value error (#24995)
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Prashant Gupta committed
Sep 16, 2025 at 20:58 UTC
ea3de5ef0d8cbf0e61ee27647954e5a867fae020
1 file changed
+1
-1
vllm/entrypoints/renderer.py
+1
-1
@@ -383,7 +383,7 @@ class CompletionRenderer(BaseRenderer):
383
"""Create validated EngineTokensPrompt."""
384
if max_length is not None and len(token_ids) > max_length:
385
raise ValueError(
386
- f"This maximum context length is {max_length} tokens. "
386
+ f"This model's maximum context length is {max_length} tokens. "
387
f"However, your request has {len(token_ids)} input tokens. "
388
"Please reduce the length of the input messages.")
389