[Core][VLM] Support image embeddings as input (#6613)

docs/source/models/vlm.rst

@@ -49,6 +49,17 @@ To pass an image to the model, note the following in :class:`vllm.inputs.PromptI
         "multi_modal_data": {"image": image},
     })
 
+    for o in outputs:
+        generated_text = o.outputs[0].text
+        print(generated_text)
+
+    # Inference with image embeddings as input
+    image_embeds = torch.load(...) # torch.Tensor of shape (1, image_feature_size, hidden_size of LM)
+    outputs = llm.generate({
+        "prompt": prompt,
+        "multi_modal_data": {"image": image_embeds},
+    })
+
     for o in outputs:
         generated_text = o.outputs[0].text
         print(generated_text)