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 11, 16:15 UTC
[Deprecation] Remove missed fallback for `embed_input_ids` (#30469)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Dec 11, 2025 at 18:06 UTC
13d63b65e0604db23c1485d370dbf9adc4e651c7
1 file changed
+1
-7
vllm/model_executor/models/interfaces_base.py
+1
-7
@@ -49,13 +49,7 @@ class VllmModel(Protocol[T_co]):
49
50
def embed_input_ids(self, input_ids: torch.Tensor) -> torch.Tensor:
51
"""Apply token embeddings to `input_ids`."""
52
- if hasattr(self, "get_input_embeddings"):
53
- logger.warning_once(
54
- "`get_input_embeddings` for vLLM models is deprecated and will be "
55
- "removed in v0.13.0 or v1.0.0, whichever is earlier. Please rename "
56
- "this method to `embed_input_ids`."
57
- )
58
- return self.get_input_embeddings(input_ids)
52
+ ...
53
54
def forward(self, input_ids: torch.Tensor, positions: torch.Tensor) -> T_co: ...
55