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 1, 21:15 UTC
Fix `LLM.wait_for_completion` output type docstring (#44617)
Signed-off-by: viiccwen <viiccwen@gmail.com>
Vic Wen committed
Jun 5, 2026 at 15:16 UTC
ef3af56a974aa3bce145068d480c4b864375cbc9
1 file changed
+2
-1
vllm/entrypoints/llm.py
+2
-1
@@ -556,7 +556,8 @@ class LLM(BeamSearchOfflineMixin, PoolingOfflineMixin, OfflineInferenceMixin):
556
and returns their outputs. Use after enqueue() to get results.
557
558
Args:
559
- output_type: The expected output type, defaults to RequestOutput.
559
+ output_type: The expected output type(s). If not provided, accepts
560
+ both RequestOutput and PoolingRequestOutput.
561
use_tqdm: If True, shows a tqdm progress bar.
562
563
Returns: