Stuck in creating runtime

[Ricardokevins]

import sglang as sgl


@sgl.function
def multi_turn_question(s, question_1, question_2):
    s += sgl.user(question_1)
    s += sgl.assistant(sgl.gen("answer_1", max_tokens=256))
    s += sgl.user(question_2)
    s += sgl.assistant(sgl.gen("answer_2", max_tokens=256))


def single():
    state = multi_turn_question.run(
        question_1="What is the capital of the United States?",
        question_2="List two local attractions.",
    )

    for m in state.messages():
        print(m["role"], ":", m["content"])

    print("\n-- answer_1 --\n", state["answer_1"])


def stream():
    state = multi_turn_question.run(
        question_1="What is the capital of the United States?",
        question_2="List two local attractions.",
        stream=True,
    )

    for out in state.text_iter():
        print(out, end="", flush=True)
    print()


def batch():
    states = multi_turn_question.run_batch(
        [
            {
                "question_1": "What is the capital of the United States?",
                "question_2": "List two local attractions.",
            },
            {
                "question_1": "What is the capital of France?",
                "question_2": "What is the population of this city?",
            },
        ]
    )

    for s in states:
        print(s.messages())


if __name__ == "__main__":
    runtime = sgl.Runtime(model_path="xxxxxx/PLM/meta-llama/Meta-Llama-3.1-8B-Instruct",tp_size=1,dp_size=4,enable_torch_compile=False)
    print("\n========== End ==========\n")

I can use SGL by deploying in command line.
But when i try to use in python wrapper: it stuck in creating Runtime. (Successfully load model and see the GPU memory increase, but not observe print)

grateful for any suggestion!

[merrymercy]

@Ricardokevins Can you try to use other ports for the runtime?
e.g., sgl.Runtime(..., port=5000)

also, you can kill the existing zombie sglang processes with https://github.com/sgl-project/sglang/blob/main/test/killall_sglang.sh before you run your script