HomeAIHugging Face Enables Single-Command vL
AI

Hugging Face Enables Single-Command vLLM Servers on HF Jobs

Hugging Face introduced single-command vLLM deployments on its Jobs infrastructure, offering private OpenAI-compatible endpoints billed per second.

WHAT YOU NEED TO KNOW
  • Hugging Face launched single-command vLLM server execution on HF Jobs on June 26, 2026.
  • Hardware usage is billed per second, with an a10g-large GPU instance priced at $1.50 per hour.
  • Endpoints are gated by default and require a Hugging Face read-access token for API requests.
  • The port-exposure pattern also supports SSH access, coding agents, and alternative backends like SGLang and llama.cpp.

Hugging Face announced on June 26, 2026, that users can deploy private, OpenAI-compatible vLLM servers on its Jobs infrastructure using a single command. The system allows model deployment without provisioning servers or managing Kubernetes clusters, with billing calculated per second based on hardware usage.

Users must install huggingface_hub version 1.20.0 or higher, authenticate locally via hf auth login, and maintain an active payment method or credit balance before running a job. Executing the hf jobs run command deploys the official vllm/vllm-openai Docker image, using flags such as --flavor to allocate GPU hardware and --expose to route ports through Hugging Face's public jobs proxy.

Endpoints require a Hugging Face bearer token with read access to receive API requests, keeping the server gated to authorized account holders. Supported hardware options range from an a10g-large GPU instance priced at $1.50 per hour up to multi-GPU configurations like h200x2 and h200x8 for larger models such as Qwen3.5-122B.

Execution and Tool Integration

Developers can open an SSH shell directly into running job containers when passing the --ssh flag, provided their public SSH key is registered in their Hugging Face settings. Endpoints can also back terminal-based AI coding agents such as Pi when vLLM is launched with automatic tool choice enabled and configured with matching tool parsers.

Managed Inference Endpoints remain Hugging Face's alternative service for long-lived production workloads requiring scale-to-zero functionality, whereas HF Jobs targets flexible tasks like model evaluations and batch processing. The underlying port-exposure pattern on HF Jobs also supports alternative backends beyond vLLM, including llama.cpp and SGLang.

Xentir Media
Xentir Media NewsroomSource-backed AI and technology coverage, drafted by Xentir's automated editorial system under fixed human-set rules. See our editorial policy and AI usage policy.
J
Jomon · Founder & EditorFounder and editor of Xentir Media. Sets the editorial rules the newsroom system runs under, and is accountable for its corrections. About Jomon · hello@xentirmedia.com
The Xentir Brief
The developments worth knowing — one useful email.
Get the Brief →