{
  "schema_version": "1.0",
  "id": "archive:https://huggingface.co/blog/vllm-jobs",
  "slug": "vllm-jobs-0236m0i",
  "url": "https://feed7.dev/p/vllm-jobs-0236m0i",
  "title": "Run a vLLM Server on HF Jobs in One Command",
  "why_included": "HF Jobs now stands up an OpenAI-compatible vLLM endpoint in one command, billed per second (A10G at $1.50/hr). Useful for throwaway endpoints: one-off evals, batch runs, agent experiments against open models.",
  "summary": "**The gist** Hugging Face Jobs can launch a vLLM server as an **OpenAI-compatible endpoint** with a single `hf jobs run` command on the stock **vllm/vllm-openai** Docker image — requires **huggingface_hub >= 1.20.0** and a payment method. Billing is **per second** by hardware flavor (**A10G Large at $1.50/hour**; paired H200s with tensor parallelism serve a 122B model), endpoints are gated behind HF tokens, and SSH debugging is available.",
  "practical_implication": "**Why it matters** When your agent stack needs a temporary open-model endpoint — a one-off eval, batch generation, or trying a model before committing — this is faster to wire than a managed Inference Endpoint, and anything speaking the **OpenAI client** protocol points at it unchanged.",
  "agent_context": "**The gist** Hugging Face Jobs can launch a vLLM server as an **OpenAI-compatible endpoint** with a single `hf jobs run` command on the stock **vllm/vllm-openai** Docker image — requires **huggingface_hub >= 1.20.0** and a payment method. Billing is **per second** by hardware flavor (**A10G Large at $1.50/hour**; paired H200s with tensor parallelism serve a 122B model), endpoints are gated behind HF tokens, and SSH debugging is available.\n\n**Why it matters** When your agent stack needs a temporary open-model endpoint — a one-off eval, batch generation, or trying a model before committing — this is faster to wire than a managed Inference Endpoint, and anything speaking the **OpenAI client** protocol points at it unchanged.\n\n**Watch out** This is for **experiments, not production**: jobs stop at their **--timeout**, you pay until you cancel, and larger models need manual tuning of --max-model-len and --max-num-seqs to fit memory.",
  "source": {
    "name": "huggingface.co",
    "url": "https://huggingface.co/blog/vllm-jobs",
    "published_at": null
  },
  "source_class": "blog_post",
  "content_type": "Source",
  "layer": "infra",
  "domains": [],
  "topics": [
    "open-models"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "This is for **experiments, not production**: jobs stop at their **--timeout**, you pay until you cancel, and larger models need manual tuning of --max-model-len and --max-num-seqs to fit memory."
  ],
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/vllm-jobs-0236m0i",
    "json": "https://feed7.dev/p/vllm-jobs-0236m0i.json",
    "markdown": "https://feed7.dev/p/vllm-jobs-0236m0i.md"
  }
}