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 12, 06:00 UTC
Add missing return in _check_vllm_model_embed_input_ids (#29834)
Signed-off-by: Johnny Yang <johnnyyang@google.com>
Johnny Yang committed
Dec 1, 2025 at 19:22 UTC
f441d36cee366126dc4f6db5b6ca262c1e0cc20c
1 file changed
+1
vllm/model_executor/models/interfaces_base.py
+1
@@ -76,6 +76,7 @@ def _check_vllm_model_embed_input_ids(model: type[object] | object) -> bool:
76
"this method to `embed_input_ids`."
77
)
78
model.embed_input_ids = model_get_input_embeddings
79
+ return True
80
logger.warning(
81
"The model (%s) is missing the `embed_input_ids` method.",
82
model,