llama.cpp and ggml version 1.0.0 released

The ggml-org team has released llama.cpp version 1.0.0 and ggml version 1.0.0, according to an article published on Hugging Face on November 13, 2026. llama.cpp makes it possible to run multi-modal LLMs across a wide range of hardware, from consumer-grade local machines to high-end enterprise servers. Through quantization, optimized backends, and a portable C/C++ implementation, the project makes AI inference accessible at every level of the software stack. The team describes llama.cpp as the most lightweight, versatile and sensible platform for building cross-platform and private AI products.

During the 3.5 years since its inception, the project has grown, and many downstream applications already depend on its work. The team expects this trend to continue as local AI and privacy become increasingly important in everyday lives. Every new integration means more developers depend on the library interfaces, so having a flexible but stable API is paramount.

With the 1.0.0 release, both llama.cpp and ggml will reflect API and ABI incompatibilities with major-version bumps. As adoption grows, the team will be stricter about making those boundaries visible to downstream consumers.

The release covers two libraries:

  • llama.cpp v1.0.0 - LLM inference in C/C++, library libllama, public headers in llama.cpp/include/
  • ggml v1.0.0 - Tensor library for machine learning, library libggml, public headers in ggml/include/

The projects use semantic versioning with the following rules:

  • MAJOR: Breaking change to the public C API in ./include
  • MINOR: Backward-compatible feature, backend updates, model support, or API addition
  • PATCH: Bug fix with no API change

Distribution channels include pre-release artifacts for Linux, macOS, Windows, Android, and iOS; Docker for Linux; Debian for Linux; Homebrew for macOS and Linux; conda-forge for Windows, macOS, and Linux; MacPorts for macOS; Winget for Windows; and XCFramework for iOS and macOS.

The underlying machine learning engine of llama.cpp is ggml, designed to run on virtually any hardware in existence by implementing dedicated ggml backends. Each backend can be compiled as a dynamic library and optionally loaded at runtime. A complete list of the currently implemented backends is available in the project documentation.

The team is committed to continuous support of all model architectures. Currently, llama.cpp supports more than 150 architecture variants as well as all mainstream speculative decoding methods.

The project has fostered an open-source community with highly-skilled and talented contributors. With the rapid advance of AI capabilities in the field of software engineering, the team continues to adapt and integrate LLMs in its development cycle in a thoughtful and reasonable manner. Maintaining a high quality codebase, staying in control of the architecture, and understanding the implementation details will remain top priorities.

To reinforce the faster pace of development, the team continues to invest resources in improving the CI infrastructure behind the projects. With hardware support from NVIDIA, AMD, Qualcomm, Arm, IBM and Intel, the team continues to enroll more self-hosted runners across all major hardware platforms.

Sources

This article was drafted with AI assistance and checked against the sources above. Company claims are reported as claims. Cover image is AI-generated.