[V1][Spec Decode] Share input embedding of target model with EAGLE draft model to free ~1GB for llama 3 model (#17326)

Co-authored-by: root <root@ekagra-8xh100.us-east5-a.c.serving-efficiency-poc.internal>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

examples/offline_inference/eagle.py

@@ -105,6 +105,13 @@ def main():
     outputs = llm.generate(prompt_token_ids=prompt_ids,
                            sampling_params=sampling_params)
 
+    # print the generated text
+    for output in outputs:
+        print("-" * 50)
+        print(f"prompt: {output.prompt}")
+        print(f"generated text: {output.outputs[0].text}")
+        print("-" * 50)
+
     if not hasattr(outputs, "metrics") or outputs.metrics is None:
         return