Skip to content
    vLLM logo

    vLLM

    Run an OpenAI-compatible inference endpoint with Qwen3-Coder
    OfficialAIInferenceLlmOpenAI

    About vLLM

    Deploy an OpenAI-compatible REST API endpoint using vLLM with GPU acceleration. This template runs Qwen/Qwen3-Coder-Next across 2+ GPUs with tensor parallelism, tool calling support, and HuggingFace model caching.
    The endpoint is fully compatible with the OpenAI Chat Completions API, making it a drop-in replacement for any OpenAI SDK client.
    Use Verda servers with 2xA100, 2xH100, or similar multi-GPU configurations. Make sure to set HF_TOKEN environment variable to your HuggingFace token to be able to properly download the model.
    DollarDeploy

    About DollarDeploy

    DollarDeploy deploys and manages apps on your own VPS — no SSH, no YAML, no lock-in. Launch vLLM in a few clicks, then get HTTPS, monitoring, logs and backups handled for you.