LIVE
DeepMindDeepMind gives Gemini 3.5 Flash desktop control·Google AIGoogle Finance exits beta with new Android app·HuggingFaceRun vLLM on HuggingFace Jobs with One Command·HuggingFaceNVIDIA NeMo AutoModel Automates Fine-Tuning, Cuts Time by 40%·OpenAIOpenAI research: AI agents extend work beyond simple tasks·HuggingFaceHuggingFace launches CUGA: lightweight harness for agentic apps·OpenAIOmio Uses OpenAI to Build Conversational Travel Experiences·HuggingFacePP-OCRv6 Arrives on Hugging Face: 50 Languages, Tiny to Medium Models·OpenAISamsung equips 100,000+ employees with ChatGPT Enterprise·OpenAIOpenAI Rolls Out Spend Controls and Analytics for ChatGPT Enterprise·HuggingFaceMosaicLeaks Benchmark Exposes Research Agents' Inability to Keep Secrets·Google AIGoogle's AMIE Medical AI Matches Doctors in Disease Management·HuggingFaceMolmoMotion: Language-Guided 3D Motion Forecasting Hits HuggingFace·DeepMindDeepMind and UK government build AI prototype to speed housing decisions·HuggingFaceHugging Face lets you deploy robot policies from Hub to real hardware·OpenAIOpenAI's Deployment Simulation predicts model behavior before launch·Google AIGoogle invests $1.5B in Alabama data center expansion·OpenAIOpenAI launches Partner Network with $150M investment fund·OpenAIOpenAI launches three Agent Academy courses for workplace AI skills·DeepMindDeepMind's DiffusionGemma speeds text generation 4x·DeepMindDeepMind gives Gemini 3.5 Flash desktop control·Google AIGoogle Finance exits beta with new Android app·HuggingFaceRun vLLM on HuggingFace Jobs with One Command·HuggingFaceNVIDIA NeMo AutoModel Automates Fine-Tuning, Cuts Time by 40%·OpenAIOpenAI research: AI agents extend work beyond simple tasks·HuggingFaceHuggingFace launches CUGA: lightweight harness for agentic apps·OpenAIOmio Uses OpenAI to Build Conversational Travel Experiences·HuggingFacePP-OCRv6 Arrives on Hugging Face: 50 Languages, Tiny to Medium Models·OpenAISamsung equips 100,000+ employees with ChatGPT Enterprise·OpenAIOpenAI Rolls Out Spend Controls and Analytics for ChatGPT Enterprise·HuggingFaceMosaicLeaks Benchmark Exposes Research Agents' Inability to Keep Secrets·Google AIGoogle's AMIE Medical AI Matches Doctors in Disease Management·HuggingFaceMolmoMotion: Language-Guided 3D Motion Forecasting Hits HuggingFace·DeepMindDeepMind and UK government build AI prototype to speed housing decisions·HuggingFaceHugging Face lets you deploy robot policies from Hub to real hardware·OpenAIOpenAI's Deployment Simulation predicts model behavior before launch·Google AIGoogle invests $1.5B in Alabama data center expansion·OpenAIOpenAI launches Partner Network with $150M investment fund·OpenAIOpenAI launches three Agent Academy courses for workplace AI skills·DeepMindDeepMind's DiffusionGemma speeds text generation 4x·
Back
🤗HuggingFace
Product/HuggingFace

Run vLLM on HuggingFace Jobs with One Command

H

HuggingFace

June 26, 2026

3 MIN

Original source

huggingface.co — read the full announcement →

HuggingFace Jobs Adds One-Click vLLM Deployment

HuggingFace just dropped a feature that makes deploying a vLLM server almost ridiculously easy. Instead of wrestling with Dockerfiles, environment variables, and spot-instance orchestration, you can now spin up a production-grade inference server with a single command. The integration targets the popular vLLM library, which handles PagedAttention and continuous batching for huge speedups on LLM inference. HuggingFace Jobs — their managed compute service — now auto-provisions the right GPU (A10G, A100, H100 depending on your model), installs dependencies, and exposes an OpenAI-compatible endpoint. The company claims setup time drops from hours to under five minutes. For teams that just want to serve a model without becoming Kubernetes experts, this is a big deal. The one-liner is something like `hfjobs run --model meta-llama/Meta-Llama-3.1-8B --command "vllm serve"`. That's it.

Before This: vLLM Deployment Was a Multi-Step Headache

Until now, running vLLM on cloud infrastructure meant stitching together several pieces. You'd need a VM or a Kubernetes cluster with a GPU, then install vLLM, then configure the server (API key, model path, tensor parallelism), then expose it with a load balancer. Most teams either wrote custom Terraform scripts or used tools like Ray Serve or BentoML — all workable, but far from frictionless. The community has long wanted a 'serverless' experience for self-hosted LLMs, especially given the cost of API services like OpenAI or Anthropic. HuggingFace already had Inference Endpoints, but those were higher-level and less flexible. With this one-command vLLM integration, they're blurring the line between managed inference and raw GPU access. It's a direct response to the growing demand for open-weight models served on your own infra without the ops overhead.

What This Means for Inference at Scale

Honestly, the most interesting part isn't the one command — it's what this enables. For companies running hundreds of models in production, being able to launch a vLLM server in seconds means faster iteration cycles and lower experimentation costs. If you're in the middle of testing a new fine-tune, you don't want to wait 30 minutes for your infra to spin up. This cuts that to near-zero. It also democratizes access: smaller teams that couldn't justify a dedicated MLOps person can now self-host competitive models without the overhead. That said, vLLM isn't magic. It still requires the right GPU memory for your model context length. And HuggingFace Jobs pricing isn't cheap — you're paying per GPU-hour on reserved instances. The real win is for teams who already trust HuggingFace's ecosystem and want to keep their entire workflow in one place.

The Catch: Limits and Unanswered Questions

Before you migrate all your inference to HF Jobs, know the gaps. First, the one-command setup only handles basic vLLM configurations. Want to set custom tensor parallelism? Use a different scheduling policy? You'll need to provide your own command or Dockerfile. The feature is a shortcut, not a full replacement for custom deployments. Second, autoscaling isn't baked in — you're deploying a single server instance. If you need to handle variable traffic, you'll still need to manage horizontal scaling yourself. Third, HuggingFace Jobs doesn't yet support every vLLM feature, like speculative decoding or LoRA adapters out of the box. Fourth, the pricing model for spot instances vs on-demand isn't transparent in the CLI. Finally, lock-in is a real concern: once you're running on HF Jobs, migrating to another provider means rewriting your deployment scripts. The one-liner is neat, but it's still early.

Related video

Watch explainers and coverage of this topic on YouTube.

Search on YouTube

Frequently Asked Questions

What is HuggingFace Jobs?

HuggingFace Jobs is a managed compute service that lets you run ML workloads — training, evaluation, inference — on cloud GPUs without managing infrastructure. It integrates directly with the HuggingFace Hub, so models and datasets are a natural fit.

Do I need a HuggingFace Pro subscription to use this?

No, but you do need a HuggingFace account with billing set up. Jobs are pay-per-use, so there's no upfront commitment. The one-command vLLM feature is available to all users with GPU quota.

Can I serve any vLLM-compatible model with this one command?

Most models that vLLM supports (like LLaMA, Mistral, Qwen) will work, as long as they fit on a single GPU with the context length you need. The command automatically downloads the model from the Hub if it's publicly accessible.

Is this cheaper than using OpenAI's API for production inference?

It depends on your throughput. At high scale, self-hosting with vLLM can be significantly cheaper per token because you're paying for GPU time, not per-token markup. But for low-volume use, OpenAI's variable pricing might be simpler and more cost-effective.

What if I need to scale beyond one GPU instance?

The current one-command version deploys a single server. To horizontally scale, you'd need to either manually launch multiple Jobs and route traffic yourself, or wait for HuggingFace to add built-in autoscaling — which they've hinted at but not delivered yet.

↑ SWIPE FOR NEXT