Hermes Vector

AI & SI

llama.cpp team at Hugging Face releases llama.cpp v1.0.0 and ggml v1.0.0

The llama.cpp team at Hugging Face has released llama.cpp v1.0.0 and ggml v1.0.0, establishing semantic versioning rules for the local AI inference library and its tensor backend.

By Hermes Vector

Also in: Español · Português · Français · Deutsch · हिन्दी

Checked against 1 sourceHugging Face
Illustration for: llama.cpp team at Hugging Face releases llama.cpp v1.0.0 and ggml v1.0.0

In brief

  • The llama.cpp team at Hugging Face released llama.cpp v1.0.0 and ggml v1.0.0 on November 13, 2026.
  • llama.cpp v1.0.0 provides LLM inference in C/C++ through libllama; ggml v1.0.0 is the tensor library libggml.
  • Both projects will use semantic versioning, with major bumps for API and ABI breaking changes.
  • Pre-release artifacts support Linux, macOS, Windows, Android, and iOS across multiple distribution channels.

llama.cpp team at Hugging Face releases llama.cpp v1.0.0 and ggml v1.0.0

The llama.cpp team at Hugging Face has released llama.cpp v1.0.0 and ggml v1.0.0, marking a new phase for the local AI inference library and its underlying tensor library.

Release details

llama.cpp v1.0.0 provides LLM inference in C/C++ through the libllama library, with public headers in llama.cpp/include/. ggml v1.0.0 is the tensor library for machine learning, distributed as libggml with public headers in ggml/include/.

The team states that 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, using quantization, optimized backends, and a portable C/C++ implementation.

Versioning policy

Moving forward, both llama.cpp and ggml will reflect API and ABI incompatibilities with major-version bumps. The semantic versioning rules are:

  • 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

The team says having a flexible but stable API is paramount as more developers depend on the library interfaces.

Distribution and hardware support

Pre-release artifacts are available for Linux, macOS, Windows, Android, and iOS. Distribution channels include 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 project receives hardware support from NVIDIA, AMD, Qualcomm, Arm, IBM, and Intel, and uses HF Buckets and HF Jobs to scale CI infrastructure.

Why it matters

The v1.0.0 release establishes a formal versioning contract for downstream applications that depend on llama.cpp and ggml, as local AI and privacy become increasingly important in everyday life.


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.

Questions readers ask

Who released llama.cpp v1.0.0 and ggml v1.0.0?
The llama.cpp team at Hugging Face released llama.cpp v1.0.0 and ggml v1.0.0.
What does llama.cpp v1.0.0 provide?
llama.cpp v1.0.0 provides LLM inference in C/C++ through the libllama library, with public headers in llama.cpp/include/.
What defines a major version bump for these libraries?
A major version bump indicates a breaking change to the public C API in ./include.
Why is this release significant for developers?
The v1.0.0 release establishes a formal versioning contract for downstream applications that depend on llama.cpp and ggml.

The day's checked news, by email

One short email a day with the top stories. Free, and you can unsubscribe in one click.

Or follow for the latest news:

How do you feel about this story?

Comments 0

No comments yet. Start the discussion.

AI & SI

South Korea tightens exam security over AI cheating fears

South Korean officials are deploying trained supervisors and considering device restrictions ahead of the Suneung college entrance exam after a tax accountant exam top scorer confessed to AI-assisted cheating.

Checked against 4 sourcesft.com2news.comnewspressnow.com+1 more