Sakhanda Wire
NVDA $153.77 -1.52% MSFT $504.91 -2.53% GOOGL $281.52 -0.78% META $620.99 -0.87% AMZN $256.80 -0.37%
← Back to the news

llama.cpp and ggml reach version 1.0.0

The llama.cpp project has released version 1.0.0 of its libraries, alongside version 1.0.0 of ggml, the machine-learning tensor library. The team said the milestone reflects the growing number of downstream applications that rely on their interfaces. From now on, incompatible changes to the public API or ABI in llama.cpp and ggml will be marked by major-version increases.

Under the stated semantic-versioning rules, minor releases will cover backward-compatible features, backend updates, model support and API additions, while patch releases will be reserved for bug fixes without API changes. The releases provide the libllama and libggml libraries and their public headers.

llama.cpp is designed to run multimodal large language models on hardware ranging from consumer computers to enterprise servers. Its implementation uses quantization, optimized backends and portable C/C++. The project currently supports more than 150 architecture variants and mainstream speculative-decoding methods. The software is distributed through channels including Docker, Debian, Homebrew, conda-forge, MacPorts, Winget and XCFramework, with platforms covering Linux, macOS, Windows, Android and iOS. The team also said it is expanding continuous-integration capacity with support from NVIDIA, AMD, Qualcomm, Arm, IBM and Intel.

Written by Sakhanda Wire AI from reporting by Hugging Face. Facts, quotes and full context are in the original article below.

Originally published by Hugging Face on

Read the original on Hugging Face ↗

The reporting and the image belong to Hugging Face and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news