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, 11:15 UTC
[BugFix] Add embed_input_ids method to make QWenLMHeadModel a vllm model (#30674)
Signed-off-by: root <iwzbi@zju.edu.cn> Co-authored-by: root <iwzbi@zju.edu.cn>
duke committed
Dec 15, 2025 at 18:38 UTC
e4806d973acba6550dd061830471b19e8c54e692
1 file changed
+3
vllm/model_executor/models/qwen.py
+3
@@ -281,6 +281,9 @@ class QWenBaseModel(nn.Module):
281
self.transformer.make_empty_intermediate_tensors
282
)
283
284
+ def embed_input_ids(self, input_ids: torch.Tensor) -> torch.Tensor:
285
+ return self.transformer.wte(input_ids)
286
+
287
def compute_logits(
288
self,
289
hidden_states: torch.Tensor,