Testing inference

main.py

@@ -13,4 +13,9 @@ def read_root():
         "The future of AI is",
     ]
     sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
-    return {"output": sampling_params}
+
+    llm = LLM(model="facebook/opt-125m")
+
+    outputs = llm.generate(prompts, sampling_params)
+
+    return {"outputs": outputs}