Coding Tools
Run vLLM Server on HF Jobs with One Command
Hugging Face Bloghigh confidence
Why it matters
- →Simplifies the deployment of AI models for testing and evaluation.
- →Offers scalable solutions for handling larger models with ease.
- →Provides a cost-effective, temporary hosting option for developers.
Hugging Face has introduced a simplified method to deploy a vLLM server using their Jobs platform. By executing a single command, developers can quickly set up a model server for testing and evaluation purposes. The process involves using the vllm/vllm-openai image and selecting appropriate GPU resources, allowing for scalable deployments. This new capability is particularly useful for developers who need temporary model hosting without the complexity of managing infrastructure. The service is billed per minute, offering a cost-effective solution for short-term model usage.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Deploy Models from HuggingFace with Ease
Together AI Blog · May 8, 2026 · Related
- 2Hugging Face Boosts Inference with Asynchronous Batching
Hugging Face Blog · May 14, 2026 · Related
- 3llama.cpp b9330 release improves model performance
llama.cpp Releases · May 27, 2026 · Background
- 4vLLM v0.22.0 Release Enhances Model Performance
vLLM Releases · May 31, 2026 · Related
What happened next
- 5vLLM v0.25.0 Release Enhances Model Execution
vLLM Releases · July 13, 2026 · Related
- 6OpenAI Models Breach Hugging Face Systems
Sifted · July 22, 2026 · Background
- 7Together AI Introduces Autoscaling for LLM Inference
Together AI Blog · July 31, 2026 · Background
- 8Async GRPO with LoRA Enhances HF Jobs Efficiency
Hugging Face Blog · September 10, 2026 · Related
- 9llama.cpp v0.5.0: Backend performance and multi-address server
llama.cpp Releases · September 24, 2026 · Background
Follow this story
Open the full story →Run vLLM Server on HF Jobs with One Command
2 developments
- Jun 26 · Hugging Face Blog
Run vLLM Server on HF Jobs with One Command (This article) - Jul 8 · Hugging Face Blog
vLLM Boosts Transformers Backend for Native-Speed Inference↳ vLLM enhances transformers backend for native-speed inference via torch.fx and layer fusions, eliminating need for custom code.
More from Hugging Face Blog
© Hugging Face BlogAgentsagents
NVIDIA Nemotron powers interactive Halloween agent
An NVIDIA engineer built a fully local voice agent for a Halloween attraction using the new Nemotron Voice Agent framework. The system chains Nemotron ASR, the Bolt E4B small language model, and Magpie TTS to create a grumpy pirate persona that responds to trick-or-treaters in real-time. Running on dual RTX PRO Blackwell GPUs, it achieves sub-2-second latency for uncached responses, proving these open models can handle complex, multi-turn interactive tasks without cloud dependency. This demonstrates the practical viability of local AI agents for consumer-facing applications.
Hugging Face Blog
© Hugging Face BlogModels & Labsmodels
Granite Switch 4.1.1 patches adapters without retraining base
IBM’s Granite Switch 4.1.1 proves modular architectures can move with the speed of standard software updates. By keeping the base model untouched and only updating specialized adapters like the multilingual ASR and decision logic, they sidestep the massive compute cost of full retraining. This approach lets developers compose new expertise on a single endpoint without migration headaches. It signals a shift toward composable AI where models evolve incrementally rather than in disruptive leaps.
Hugging Face Blog
© Hugging Face BlogGeneral AIresearch
Project ProtoStar launches to make public science AI-ready
Hugging Face and a coalition of major universities are launching Project ProtoStar to solve the 'last mile' problem of scientific data: making it machine-actionable. With $190 billion in annual U.S. federal R&D funding, the initiative pushes institutions like CMU and Purdue to release datasets in standardized formats rather than static files. The kickoff challenge tests AI's ability to predict urban climate conditions using historical weather records from 210 cities. This shifts the focus from mere publication to actual interoperability, creating a reusable infrastructure for AI-driven discovery.
Hugging Face Blog
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
llama.cpp Releases