llama.cpp reaches version 1.0 with stricter rules on breaking changes

Nov 13, 2026
The local AI inference project and its ggml engine will now signal API and ABI breaks with major-version bumps.

ggml-org has released version 1.0.0 of llama.cpp and the underlying ggml library, the widely used open-source software for running AI models locally, the team announced on the Hugging Face blog. From now on, changes that break the API or ABI will come with a major-version bump, so developers building on the libraries can see them coming.

llama.cpp runs multimodal models on hardware from laptops to enterprise servers through quantisation and portable C/C++ code, and supports more than 150 model architecture variants and all mainstream speculative decoding methods. The team said it uses LLMs in its own development "in a thoughtful and reasonable manner" and runs its test infrastructure on Hugging Face services, with hardware support from Nvidia, AMD, Qualcomm, Arm, IBM and Intel.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

Guide
Humanoid Robot Makers

Humanoid Robot Makers

Companies building humanoid robots, from startups to Tesla and Boston Dynamics

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.