Tutorials & Tips

Launch a vLLM server on HF Jobs with one command

Original title:Run a vLLM Server on HF Jobs in One Command

AI summary

HuggingFace Jobs supports launching a vLLM server with one command for testing, evaluation or batch generation. Use the `hf jobs run` command, specify the official `vllm/vllm-openai` image, a GPU flavor such as `a10g-large`, expose port 8000 and set a timeout. Once the server starts, it is accessible through an OpenAI-compatible API, and each request must carry an HF token as a bearer token (limited to users with read permission). The example deploys Qwen/Qwen3-4B (multi-GPU requires `--tensor-parallel-size`). `a10g-large` costs $1.50/hour, billed by the minute, and can be stopped with `hf jobs cancel`.

Key Takeaways

  • HuggingFace Jobs supports launching a vLLM server with one command for testing,evaluation or batch…
  • Use the `hf jobs run` command,specify the official `vllm/vllm-openai` image,a GPU flavor such as…
  • Once the server starts,it is accessible through an OpenAI-compatible API,and each request must…
  • The example deploys Qwen/Qwen3-4B (multi-GPU requires `--tensor-parallel-size`).
  • `a10g-large` costs $1.

Quick Facts

Published
Updated
Source
Hugging Face 社区博客(混合发现)
Category
Tutorials & Tips
AI score
62
Read the original Read the full article at the original source
Why it matters

这是一条命令在HF上启动vLLM的完整教程,适合快速测试模型的开发者,但方案完全绑定Hugging Face平台,通用性有限。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Launch a vLLM server on HF Jobs with one command. June 26, 2026. https://new.nat6.net/en/news/cmqwr2hi6008msliky22llevm/

View all →