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 db3c373 commit b334102Copy full SHA for b334102
tensorrt_llm/executor/base_worker.py
@@ -432,7 +432,7 @@ def _deduce_max_tokens(request: GenerationRequest,
432
# default_max_tokens is the biggest available value
433
if max_tokens is None:
434
return default_max_tokens
435
- elif max_tokens > default_max_tokens:
+ elif max_tokens > default_max_tokens and default_max_tokens > 0:
436
logger.warning(
437
f"User-specified `max_tokens` ({max_tokens}) is greater than deduced "
438
f"`default_max_tokens` ({default_max_tokens}), using default_max_tokens instead."
0 commit comments