We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 584ed86 commit ddbb116Copy full SHA for ddbb116
tensorrt_llm/executor/base_worker.py
@@ -428,7 +428,7 @@ def _deduce_max_tokens(request: GenerationRequest,
428
# default_max_tokens is the biggest available value
429
if max_tokens is None:
430
return default_max_tokens
431
- elif max_tokens > default_max_tokens:
+ elif max_tokens > default_max_tokens and default_max_tokens > 0:
432
logger.warning(
433
f"User-specified `max_tokens` ({max_tokens}) is greater than deduced "
434
f"`default_max_tokens` ({default_max_tokens}), using default_max_tokens instead."
0 commit comments