{"id":1628,"date":"2026-06-26T00:00:00","date_gmt":"2026-06-26T00:00:00","guid":{"rendered":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/"},"modified":"2026-06-29T05:59:31","modified_gmt":"2026-06-29T05:59:31","slug":"vllm-jobs","status":"publish","type":"post","link":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/","title":{"rendered":"Run a vLLM Server on HF Jobs in One Command"},"content":{"rendered":"


\n<\/p>\n

\n
\n
\n
\n
\n
\"Quentin<\/span> <\/span> <\/div>\n<\/div><\/div>\n<\/div>\n<\/div>\n

You’ll be able to spin up a personal, OpenAI-compatible LLM endpoint on Hugging Face infrastructure with a single command \u2014 no servers to provision, no Kubernetes, pay-per-second. As soon as it is up, you possibly can question it out of your laptop computer, a pocket book, or wherever else.<\/p>\n

It is the quickest technique to rise up a mannequin for checks, evals, or batch technology. (For those who’re after a managed, production-ready service as an alternative, that is what Inference Endpoints are for \u2014 extra on when to select which on the finish.)<\/p>\n

Here is the entire thing finish to finish.<\/p>\n

\n

\t
\n\t\tConditions
\n\t<\/span>
\n<\/h2>\n

A cost methodology or a constructive pay as you go credit score stability (Jobs is billed per\u2011minute by {hardware} utilization).
\nhuggingface_hub >= 1.20.0: pip set up -U “huggingface_hub>=1.20.0”.
\nLogged in regionally: hf auth login.<\/p>\n

\n

\t
\n\t\tLaunch the server
\n\t<\/span>
\n<\/h2>\n

hf jobs run is docker run for HF infrastructure. We use the official vllm\/vllm-openai picture, ask for a GPU with –flavor, and expose vLLM’s port with –expose:<\/p>\n

hf jobs<\/span> run –flavor a10g-large –expose 8000 —timeout<\/span> 2h
\n vllm\/vllm-openai:newest
\n vllm serve Qwen\/Qwen3-4B –host 0.0.0.0 –port 8000<\/p>\n

–expose 8000 routes the container’s port by way of HF’s public jobs proxy (see the Serve Fashions information for the total reference). The command prints the URL your server is reachable at:<\/p>\n

\u2713 Job began
\n id: 6a381ca1953ed90bfb947332
\n url: https:\/\/huggingface.co\/jobs\/qgallouedec\/6a381ca1953ed90bfb947332
\nTrace: Uncovered ports are reachable at (requires an HF token with learn entry to the job):
\n https:\/\/6a381ca1953ed90bfb947332–8000.hf.jobs<\/p>\n

6a381ca1953ed90bfb947332 is your job ID. Maintain observe of it, we’ll want it. We’ll use as a placeholder for it in the remainder of the put up.<\/p>\n

Give it a few minutes to obtain weights and boot. When the logs present Software startup full, you are dwell.<\/p>\n

\n

\t
\n\t\tQuestion it from wherever
\n\t<\/span>
\n<\/h2>\n

vLLM speaks the OpenAI API, and each request simply wants your HF token as a bearer token. The quickest technique to hit it’s curl:<\/p>\n

curl https:\/\/–8000.hf.jobs\/v1\/chat\/completions
\n -H “Authorization: Bearer $(hf auth token)<\/span>“<\/span>
\n -H “Content material-Sort: utility\/json”<\/span>
\n -d ‘{<\/span>
\n “mannequin”: “Qwen\/Qwen3-4B”,<\/span>
\n “messages”: [{“role”: “user”, “content”: “Hello!”}],<\/span>
\n “chat_template_kwargs”: {“enable_thinking”: false}<\/span>
\n }’<\/span><\/p>\n

which returns the same old OpenAI-style JSON, with decisions[0].message.content material holding “Hey! How can I help you at present? \ud83d\ude0a”.<\/p>\n

Or, from Python, level the OpenAI consumer on the uncovered URL and cross the token because the API key:<\/p>\n

from<\/span> huggingface_hub import<\/span> get_token
\nfrom<\/span> openai import<\/span> OpenAI<\/p>\n

consumer = OpenAI(
\n base_url=“https:\/\/–8000.hf.jobs\/v1”<\/span>,
\n api_key=get_token(),
\n)
\nresp = consumer.chat.completions.create(
\n mannequin=“Qwen\/Qwen3-4B”<\/span>,
\n messages=[{“role”<\/span>: “user”<\/span>, “content”<\/span>: “Hello!”<\/span>}],
\n extra_body={“chat_template_kwargs”<\/span>: {“enable_thinking”<\/span>: False<\/span>}},
\n)
\nprint<\/span>(resp.decisions[0<\/span>].message.content material)<\/p>\n

Hey! How can I help you at present? \ud83d\ude0a<\/p>\n

Fast well being test earlier than you begin: curl https:\/\/–8000.hf.jobs\/v1\/fashions -H “Authorization: Bearer $(hf auth token)” ought to listing the mannequin.<\/p>\n

\n

\ud83d\udd10 The endpoint is gated, not public. Each request should carry an HF token with learn entry to the job’s namespace. A plain browser go to will likely be rejected. In impact, the roles proxy is your API gate: entry is scoped to you (and your org). That is tremendous for personal use, however deal with the URL accordingly: do not share it anticipating it to be open, and do not paste your token into untrusted locations. For those who want finer-grained or public entry, put a correct gateway in entrance as an alternative. Or see HF Jobs or Inference Endpoints? under.<\/p>\n<\/blockquote>\n

\n

\t
\n\t\tClear up
\n\t<\/span>
\n<\/h2>\n

Jobs are billed per second, so cease the server while you’re performed:<\/p>\n

hf jobs<\/span> cancel <\/p>\n

The –timeout you set is a security web (it will auto-stop), however cancelling explicitly is cheaper. An a10g-large runs at $1.50\/hour \u2014 test hf jobs {hardware} for the total value listing and choose the smallest taste that matches your mannequin.<\/p>\n

\n

\t
\n\t\tGoing additional: greater fashions
\n\t<\/span>
\n<\/h2>\n

The identical command scales to a lot bigger fashions \u2014 choose a beefier –flavor and inform vLLM to shard the mannequin throughout the GPUs with –tensor-parallel-size. For instance, the 122B Qwen3.5 mixture-of-experts mannequin on 2\u00d7 H200:<\/p>\n

hf jobs<\/span> run –flavor h200x2 –expose 8000 —timeout<\/span> 2h
\n vllm\/vllm-openai:newest
\n vllm serve Qwen\/Qwen3.5-122B-A10B
\n –host 0.0.0.0 –port 8000 –tensor-parallel-size 2
\n –max-model-len 32768 –max-num-seqs 256<\/p>\n

–tensor-parallel-size ought to match the variety of GPUs within the taste (h200x2 \u2192 2, h200x8 \u2192 8). Run hf jobs {hardware} to see what’s accessible and provides greater fashions an extended –timeout, since they take longer to obtain and cargo. For giant fashions, H200 flavors are often the most effective worth.<\/p>\n

The –max-model-len 32768 –max-num-seqs 256 flags are particular to this mannequin: Qwen3.5-122B is a hybrid Mamba\/consideration structure with a 256K-token default context, which does not go away sufficient reminiscence for vLLM’s default batch settings. Capping the context size and concurrent-sequence rely retains it throughout the GPUs’ reminiscence. If a mannequin fails to start out with an out-of-memory or cache-block error, dialing these two down is the very first thing to strive. Every little thing else (the uncovered URL, the OpenAI consumer, the token auth) stays precisely the identical.<\/p>\n

\n

\t
\n\t\tGoing additional: Chat with it in a UI
\n\t<\/span>
\n<\/h2>\n

Want a chat window over curl? Just a few strains of Gradio level on the identical endpoint. Add –reasoning-parser deepseek_r1 to the vllm serve command so Qwen3’s pondering comes again as a separate area (not needed, however useful), then run this code regionally (you may simply want the job ID):<\/p>\n

import<\/span> gradio as<\/span> gr
\nfrom<\/span> gradio import<\/span> ChatMessage
\nfrom<\/span> huggingface_hub import<\/span> get_token
\nfrom<\/span> openai import<\/span> OpenAI<\/p>\n

consumer = OpenAI(base_url=“https:\/\/–8000.hf.jobs\/v1”<\/span>, api_key=get_token())<\/p>\n

def<\/span> chat<\/span>(message, historical past<\/span>):
\n messages = [{“role”<\/span>: m[“role”<\/span>], “content material”<\/span>: m[“content”<\/span>]} for<\/span> m in<\/span> historical past if<\/span> not<\/span> m.get(“metadata”<\/span>)]
\n messages.append({“position”<\/span>: “consumer”<\/span>, “content material”<\/span>: message})
\n stream = consumer.chat.completions.create(mannequin=“Qwen\/Qwen3-4B”<\/span>, messages=messages, stream=True<\/span>)<\/p>\n

pondering, reply = “”<\/span>, “”<\/span>
\n for<\/span> chunk in<\/span> stream:
\n delta = chunk.decisions[0<\/span>].delta
\n pondering += delta.model_extra.get(“reasoning”<\/span>, “”<\/span>)
\n reply += delta.content material or<\/span> “”<\/span>
\n out = []
\n if<\/span> pondering.strip():
\n standing = “performed”<\/span> if<\/span> reply.strip() else<\/span> “pending”<\/span>
\n out.append(ChatMessage(position=“assistant”<\/span>, content material=pondering, metadata={“title”<\/span>: “\ud83d\udcad Considering”<\/span>, “standing”<\/span>: standing}))
\n if<\/span> reply.strip():
\n out.append(ChatMessage(position=“assistant”<\/span>, content material=reply))
\n yield<\/span> out<\/p>\n

gr.ChatInterface(chat).launch()<\/p>\n

Run it, open http:\/\/127.0.0.1:7860, and chat \u2014 reasoning streams into the collapsible panel, the reply under.<\/p>\n

\n

\t
\n\t\tGoing additional: SSH into the working server
\n\t<\/span>
\n<\/h2>\n

Have to debug a startup failure, watch GPU reminiscence, or tail logs interactively? You’ll be able to open a shell straight into the working job. Launch it with –ssh and ensure your public key’s registered at huggingface.co\/settings\/keys:<\/p>\n

hf jobs<\/span> run –flavor a10g-large –expose 8000 —timeout<\/span> 2h –ssh
\n vllm\/vllm-openai:newest
\n vllm serve Qwen\/Qwen3-4B –host 0.0.0.0 –port 8000<\/p>\n

then join with the job ID:<\/p>\n

hf jobs<\/span> ssh <\/p>\n

You are now contained in the container, the place you possibly can run nvidia-smi, examine the method, or poke on the mannequin immediately \u2014 which makes debugging and monitoring a lot simpler than studying logs from the skin. SSH help requires huggingface_hub >= 1.20.0.<\/p>\n

\n

\t
\n\t\tGoing additional: Use it as a coding-agent backend with Pi
\n\t<\/span>
\n<\/h2>\n

The identical endpoint can again a terminal coding agent. Pi is a provider-agnostic agent harness. Level it on the job and also you get a Learn\/Write\/Edit\/Bash agent working by yourself self-hosted mannequin.<\/p>\n

One factor to arrange first: brokers drive the mannequin by way of instrument calls, and vLLM solely accepts these if the server is launched with instrument calling enabled. So relaunch with –enable-auto-tool-choice and a –tool-call-parser matching the mannequin household (hermes for Qwen3). Brokers additionally profit from a stronger mannequin, so this can be a good place to herald the larger one:<\/p>\n

hf jobs<\/span> run –flavor h200x2 –expose 8000 —timeout<\/span> 2h
\n vllm\/vllm-openai:newest
\n vllm serve Qwen\/Qwen3.5-122B-A10B
\n –host 0.0.0.0 –port 8000 –tensor-parallel-size 2
\n –max-model-len 32768 –max-num-seqs 256
\n –reasoning-parser deepseek_r1
\n –enable-auto-tool-choice –tool-call-parser hermes<\/p>\n

Then add the job as a customized supplier in ~\/.pi\/agent\/fashions.json:<\/p>\n

{<\/span>
\n “suppliers”<\/span>:<\/span> {<\/span>
\n “hf-jobs”<\/span>:<\/span> {<\/span>
\n “baseUrl”<\/span>:<\/span> “https:\/\/–8000.hf.jobs\/v1”<\/span>,<\/span>
\n “api”<\/span>:<\/span> “openai-completions”<\/span>,<\/span>
\n “apiKey”<\/span>:<\/span> “!hf auth token”<\/span>,<\/span>
\n “fashions”<\/span>:<\/span> [<\/span>
\n {<\/span> “id”<\/span>:<\/span> “Qwen\/Qwen3.5-122B-A10B”<\/span> }<\/span>
\n ]<\/span>
\n }<\/span>
\n }<\/span>
\n}<\/span><\/p>\n

Then launch the agent towards it:<\/p>\n

pi<\/p>\n

The mannequin you spun up a few instructions in the past, now driving an interactive coding agent in your terminal.<\/p>\n

\n

\t
\n\t\tHF Jobs or Inference Endpoints?
\n\t<\/span>
\n<\/h2>\n

HF Jobs is not the one technique to serve a mannequin on Hugging Face. Inference Endpoints are our managed product for a similar job, and which one suits will depend on what you are after.<\/p>\n

Attain for HF Jobs while you need most flexibility and management: it is simply docker run on HF infrastructure, so that you choose the picture, the precise vllm serve flags, and the {hardware}, and also you pay per second for so long as the job runs. That makes it an ideal match for experiments, one-off evals, batch technology, or kicking the tires on a mannequin earlier than committing to something.<\/p>\n

Attain for Inference Endpoints while you need one thing extra production-ready. They add the operational niceties a long-lived service wants: finer-grained entry management (an endpoint may be public, protected, or non-public), and scale-to-zero, so you are not billed during times of inactivity. For those who’re standing up a sturdy endpoint relatively than working a job, that is the instrument to seize.<\/p>\n

\n

\t
\n\t\tAdditional studying
\n\t<\/span>
\n<\/h2>\n

This put up sticks to vLLM, however the identical expose-a-port sample works with any OpenAI-compatible server. To serve GGUFs with llama.cpp or run SGLang as an alternative, see the Serve Fashions on Jobs information, which walks by way of these backends.<\/p>\n<\/div>\n


\n
Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

You’ll be able to spin up a personal, OpenAI-compatible LLM endpoint on Hugging Face infrastructure with a single command \u2014 no servers to provision, no Kubernetes, pay-per-second. As soon as it is up, you possibly can question it out of your laptop computer, a pocket book, or wherever else. It is the quickest technique to […]<\/p>\n","protected":false},"author":1,"featured_media":1630,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/huggingface.co\/blog\/assets\/vllm-jobs\/thumbnail.png","fifu_image_alt":"","jnews-multi-image_gallery":[],"jnews_single_post":[],"jnews_primary_category":[],"jnews_override_bookmark_settings":[],"jnews_social_meta":[],"jnews_override_counter":[],"footnotes":""},"categories":[5],"tags":[2093,841,316,2092,2091],"class_list":["post-1628","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-developer-ai-open-source-ecosystem","tag-command","tag-jobs","tag-run","tag-server","tag-vllm"],"yoast_head":"\nRun a vLLM Server on HF Jobs in One Command - Future News 24<\/title>\n<meta name=\"description\" content=\"We\u2019re on a journey to advance and democratize artificial intelligence through open source and open science.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Run a vLLM Server on HF Jobs in One Command - Future News 24\" \/>\n<meta property=\"og:description\" content=\"We\u2019re on a journey to advance and democratize artificial intelligence through open source and open science.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/\" \/>\n<meta property=\"og:site_name\" content=\"Future News 24\" \/>\n<meta property=\"article:published_time\" content=\"2026-06-26T00:00:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-06-29T05:59:31+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/huggingface.co\/blog\/assets\/vllm-jobs\/thumbnail.png\" \/>\n<meta name=\"author\" content=\"Future News 24\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/huggingface.co\/blog\/assets\/vllm-jobs\/thumbnail.png\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Future News 24\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"8 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/\"},\"author\":{\"name\":\"Future News 24\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/person\\\/cecad1bde21cfc357cf70128144d6c83\"},\"headline\":\"Run a vLLM Server on HF Jobs in One Command\",\"datePublished\":\"2026-06-26T00:00:00+00:00\",\"dateModified\":\"2026-06-29T05:59:31+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/\"},\"wordCount\":1630,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/huggingface.co\\\/blog\\\/assets\\\/vllm-jobs\\\/thumbnail.png\",\"keywords\":[\"Command\",\"jobs\",\"run\",\"Server\",\"vLLM\"],\"articleSection\":[\"Developer AI & Open-Source Ecosystem\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/\",\"name\":\"Run a vLLM Server on HF Jobs in One Command - Future News 24\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/huggingface.co\\\/blog\\\/assets\\\/vllm-jobs\\\/thumbnail.png\",\"datePublished\":\"2026-06-26T00:00:00+00:00\",\"dateModified\":\"2026-06-29T05:59:31+00:00\",\"description\":\"We\u2019re on a journey to advance and democratize artificial intelligence through open source and open science.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/#primaryimage\",\"url\":\"https:\\\/\\\/huggingface.co\\\/blog\\\/assets\\\/vllm-jobs\\\/thumbnail.png\",\"contentUrl\":\"https:\\\/\\\/huggingface.co\\\/blog\\\/assets\\\/vllm-jobs\\\/thumbnail.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/2026\\\/06\\\/26\\\/vllm-jobs\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/futurenews24.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Run a vLLM Server on HF Jobs in One Command\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#website\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/\",\"name\":\"Future News 24\",\"description\":\"The Smart Hub for AI and Next-Gen Innovation\",\"publisher\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/futurenews24.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#organization\",\"name\":\"Future News 24\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/futurenews24.com\\\/wp-content\\\/uploads\\\/2026\\\/06\\\/fn24-favicon.png\",\"contentUrl\":\"https:\\\/\\\/futurenews24.com\\\/wp-content\\\/uploads\\\/2026\\\/06\\\/fn24-favicon.png\",\"width\":250,\"height\":250,\"caption\":\"Future News 24\"},\"image\":{\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/futurenews24.com\\\/#\\\/schema\\\/person\\\/cecad1bde21cfc357cf70128144d6c83\",\"name\":\"Future News 24\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g\",\"caption\":\"Future News 24\"},\"sameAs\":[\"https:\\\/\\\/futurenews24.com\"],\"url\":\"https:\\\/\\\/futurenews24.com\\\/index.php\\\/author\\\/mridulpahuja20\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Run a vLLM Server on HF Jobs in One Command - Future News 24","description":"We\u2019re on a journey to advance and democratize artificial intelligence through open source and open science.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/","og_locale":"en_US","og_type":"article","og_title":"Run a vLLM Server on HF Jobs in One Command - Future News 24","og_description":"We\u2019re on a journey to advance and democratize artificial intelligence through open source and open science.","og_url":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/","og_site_name":"Future News 24","article_published_time":"2026-06-26T00:00:00+00:00","article_modified_time":"2026-06-29T05:59:31+00:00","og_image":[{"url":"https:\/\/huggingface.co\/blog\/assets\/vllm-jobs\/thumbnail.png","type":"","width":"","height":""}],"author":"Future News 24","twitter_card":"summary_large_image","twitter_image":"https:\/\/huggingface.co\/blog\/assets\/vllm-jobs\/thumbnail.png","twitter_misc":{"Written by":"Future News 24","Est. reading time":"8 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/#article","isPartOf":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/"},"author":{"name":"Future News 24","@id":"https:\/\/futurenews24.com\/#\/schema\/person\/cecad1bde21cfc357cf70128144d6c83"},"headline":"Run a vLLM Server on HF Jobs in One Command","datePublished":"2026-06-26T00:00:00+00:00","dateModified":"2026-06-29T05:59:31+00:00","mainEntityOfPage":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/"},"wordCount":1630,"commentCount":0,"publisher":{"@id":"https:\/\/futurenews24.com\/#organization"},"image":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/#primaryimage"},"thumbnailUrl":"https:\/\/huggingface.co\/blog\/assets\/vllm-jobs\/thumbnail.png","keywords":["Command","jobs","run","Server","vLLM"],"articleSection":["Developer AI & Open-Source Ecosystem"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/","url":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/","name":"Run a vLLM Server on HF Jobs in One Command - Future News 24","isPartOf":{"@id":"https:\/\/futurenews24.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/#primaryimage"},"image":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/#primaryimage"},"thumbnailUrl":"https:\/\/huggingface.co\/blog\/assets\/vllm-jobs\/thumbnail.png","datePublished":"2026-06-26T00:00:00+00:00","dateModified":"2026-06-29T05:59:31+00:00","description":"We\u2019re on a journey to advance and democratize artificial intelligence through open source and open science.","breadcrumb":{"@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/#primaryimage","url":"https:\/\/huggingface.co\/blog\/assets\/vllm-jobs\/thumbnail.png","contentUrl":"https:\/\/huggingface.co\/blog\/assets\/vllm-jobs\/thumbnail.png"},{"@type":"BreadcrumbList","@id":"https:\/\/futurenews24.com\/index.php\/2026\/06\/26\/vllm-jobs\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/futurenews24.com\/"},{"@type":"ListItem","position":2,"name":"Run a vLLM Server on HF Jobs in One Command"}]},{"@type":"WebSite","@id":"https:\/\/futurenews24.com\/#website","url":"https:\/\/futurenews24.com\/","name":"Future News 24","description":"The Smart Hub for AI and Next-Gen Innovation","publisher":{"@id":"https:\/\/futurenews24.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/futurenews24.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/futurenews24.com\/#organization","name":"Future News 24","url":"https:\/\/futurenews24.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/futurenews24.com\/#\/schema\/logo\/image\/","url":"https:\/\/futurenews24.com\/wp-content\/uploads\/2026\/06\/fn24-favicon.png","contentUrl":"https:\/\/futurenews24.com\/wp-content\/uploads\/2026\/06\/fn24-favicon.png","width":250,"height":250,"caption":"Future News 24"},"image":{"@id":"https:\/\/futurenews24.com\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/futurenews24.com\/#\/schema\/person\/cecad1bde21cfc357cf70128144d6c83","name":"Future News 24","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/d57f07142d73cb5503ab2446ea7bc9ef3d0a5ba378d64a6157692311e42bf097?s=96&d=mm&r=g","caption":"Future News 24"},"sameAs":["https:\/\/futurenews24.com"],"url":"https:\/\/futurenews24.com\/index.php\/author\/mridulpahuja20\/"}]}},"_links":{"self":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts\/1628","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/comments?post=1628"}],"version-history":[{"count":1,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts\/1628\/revisions"}],"predecessor-version":[{"id":1629,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/posts\/1628\/revisions\/1629"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/media\/1630"}],"wp:attachment":[{"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/media?parent=1628"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/categories?post=1628"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/futurenews24.com\/index.php\/wp-json\/wp\/v2\/tags?post=1628"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}