Hugging Face Spaces
hugging-face-spaces-d6811715·7 events·first seen 28d agoAliases: Hugging Face Spaces
Co-occurring entities
More like this (12)
Recent events (7)
Hugging Face demonstrates agent chaining two Spaces to build a 3D Paris gallery
A Hugging Face blog post describes an agent that autonomously chains two Hugging Face Spaces to generate a 3D gallery of Paris, illustrating multi-step tool use and Space-to-Space orchestration. The demo showcases how agents can compose existing hosted ML tools without custom infrastructure. This is a practical capability demonstration relevant to the agent-tool ecosystem.
Run ComfyUI Workflows for Free with Gradio on Hugging Face Spaces
Hugging Face has published a guide enabling users to run ComfyUI workflows via Gradio on Hugging Face Spaces at no cost. This integration bridges the ComfyUI node-based image generation interface with Gradio's web UI framework, hosted on Spaces infrastructure. The post targets practitioners building and sharing diffusion model pipelines without local GPU requirements.
Deploy Livebook notebooks as apps to Hugging Face Spaces
Hugging Face and the Livebook team have integrated to allow Elixir-based Livebook notebooks to be deployed as interactive web applications directly to Hugging Face Spaces. This enables developers to package machine learning workflows built in Livebook—including those using Nx and Bumblebee for model inference—into shareable, hosted apps. The integration lowers the barrier for Elixir ML practitioners to publish and share AI-powered applications.
Make your ZeroGPU Spaces go brrr with ahead-of-time compilation
Hugging Face introduces ahead-of-time (AOT) compilation support for ZeroGPU Spaces, enabling faster cold-start and inference times by pre-compiling model kernels before deployment. The post explains how AOT compilation reduces the JIT compilation overhead that typically occurs on first inference in ZeroGPU's shared GPU environment. This is a practical infrastructure improvement for developers hosting models on Hugging Face Spaces.
Google Cloud TPUs made available to Hugging Face users
Hugging Face has announced the availability of Google Cloud TPUs for its Inference Endpoints and Spaces products. This integration allows Hugging Face users to deploy and run models on TPU hardware directly through the Hugging Face platform. The move expands the hardware options available to developers and researchers working with large models on Hugging Face infrastructure.
Hugging Face Machine Learning Demos on arXiv
Hugging Face announced an integration allowing ML demos to be linked or embedded directly on arXiv paper pages. This lowers the barrier between research publication and interactive model demonstration. The feature connects academic papers to live Spaces or model demos hosted on Hugging Face.
Data is Better Together: Community-Driven Dataset Building with Argilla and Hugging Face Spaces
Hugging Face and Argilla are launching a collaborative initiative to enable communities to collectively build higher-quality datasets using Argilla's annotation tooling integrated with Hugging Face Spaces. The effort targets the data curation bottleneck in AI development by crowdsourcing human feedback and annotations at scale. This represents a community-oriented approach to producing training and evaluation datasets for open-source AI models.