Testing vllm

main.py

@@ -1,8 +1,16 @@
 from fastapi import FastAPI
+from vllm import LLM, SamplingParams
 
 app = FastAPI()
 
 
 @app.get("/")
 def read_root():
-    return {"Hello": "World!"}
+    prompts = [
+        "Hello, my name is",
+        "The president of the United States is",
+        "The capital of France is",
+        "The future of AI is",
+    ]
+    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+    return {"output": sampling_params}