vLLM over HTTP

Dockerfile

FROM vllm/vllm-openai:latest
RUN curl -fsSL https://surfra.io/install.sh | sh
ENTRYPOINT ["surfra", "worker"]

deploy.py

import surfra

surfra.App("qwen").deploy(
    image="ghcr.io/you/vllm-surfra:1",
    entrypoint="vllm serve Qwen/Qwen3-0.6B --host 127.0.0.1 --port 8000",
    runtime={
        "engine": "http",
        "port": 8000,
        "path": "/v1/chat/completions",
        "ready_path": "/health",
        "ready_timeout": 1800,
    },
    autoscale={
        "max_replicas": 3,
        "idle_timeout_sec": 600,
        "execution_timeout_sec": 600,
        "providers": [
            {"provider": "salad", "gpu": "rtx4090", "priority": 1},
            {"provider": "runpod", "gpu": "rtx4090", "priority": 2},
        ],
    },
)

chat.py

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.surfra.io/openai/qwen/v1", api_key=os.environ["SURFRA_API_KEY"])
reply = client.chat.completions.create(
    model="Qwen/Qwen3-0.6B",
    messages=[{"role": "user", "content": "Say hi"}],
)
print(reply.choices[0].message.content)

The first call waits for the image pull and model download. Raise ready_timeout for larger models. The same pattern works for SGLang, TGI, and Ollama. See HTTP servers.