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 13, 07:00 UTC
[CI] Bug: Fix ci entrypoint pooling (#28684)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Wentao Ye committed
Nov 13, 2025 at 17:19 UTC
e64011f29a63ef9c4fc67bad1fd42af4f3cfad35
1 file changed
+1
vllm/v1/engine/processor.py
+1
@@ -579,6 +579,7 @@ class Processor:
579
prompt_len == max_prompt_len
580
and prompt_type == "decoder"
581
and not model_config.is_multimodal_model
582
+ and self.model_config.runner_type != "pooling"
583
):
584
suggestion = (
585
"Make sure that `max_model_len` is no smaller than the "