Ggml.ai joins Hugging Face to ensure the long-term progress of Local AI

Source: Hacker News

Announcement

We are happy to announce that ggml.ai (the founding team of llama.cpp) are joining Hugging Face in order to keep future AI truly open.

Georgi and the team are joining HF with the goal of scaling and supporting the ggml/llama.cpp community as Local AI continues to make exponential progress in the coming years.

Summary / Key‑points

• The ggml‑org projects remain open and community‑driven as always.
• The ggml team continues to lead, maintain, and support full‑time the ggml and llama.cpp libraries and related open‑source projects.
• The new partnership ensures long‑term sustainability of the projects and will help foster new opportunities for users and contributors.
• Additional focus will be dedicated to improving user experience and integration with the Hugging Face transformers library for better model support.

Why this change?

Since its foundation in 2023, the core mission of ggml.ai has continuously been to support the development and adoption of the ggml machine‑learning library. Over the past three years, the small team behind the company has grown the open‑source developer community and helped establish ggml as the definitive standard for efficient local AI inference. This was achieved through strong collaboration with individual contributors, partnerships with model providers, and independent hardware vendors. As a result, today llama.cpp is a fundamental building block in countless projects and products, enabling private and easily accessible AI on consumer hardware.

Throughout this development, Hugging Face stood out as the strongest and most supportive partner. During the last couple of years, HF engineers (notably @ngxson and @allozaur) have:

• Contributed several core functionalities to ggml and llama.cpp.
• Built a solid inference server with a polished user interface.
• Introduced multi‑modal support to llama.cpp.
• Integrated llama.cpp into the Hugging Face Inference Endpoints.
• Improved compatibility of the GGUF file format with the Hugging Face platform.
• Implemented multiple model architectures into llama.cpp.
• Assisted ggml projects with general maintenance, PR reviews, and more.

The teamwork between our teams has always been smooth and efficient. Both sides, as well as the community, have benefited from these joint efforts. Formalizing this collaboration makes sense to strengthen it for the future.

What will change for ggml/llama.cpp, the open‑source project and the community?

Not much – Georgi and the team will continue to dedicate 100 % of their time to maintaining ggml/llama.cpp. The community will remain fully autonomous and will continue making technical and architectural decisions as usual. Hugging Face is providing the project with long‑term sustainable resources, improving the chances of growth and thriving. The project will stay 100 % open‑source and community‑driven. Expect your favorite quantizations to be supported even faster once a model is released.

Technical focus

Seamless “single‑click” integration with the transformers library

The transformers framework has become the “source of truth” for AI model definitions. Improving compatibility between transformers and the ggml ecosystem is essential for broader model support and quality control.

Better packaging and user experience of ggml‑based software

As local inference becomes a competitive alternative to cloud inference, simplifying how casual users deploy and access local models is crucial. We will work towards making llama.cpp ubiquitous and readily available everywhere, while continuing to partner with downstream projects.

Long term vision

Our shared goal is to provide the building blocks that make open‑source superintelligence accessible to the world over the coming years. Together with the growing Local AI community, we will build the ultimate inference stack that runs as efficiently as possible on our devices.