ggml-org and Hugging Face · Local inference library

llama.cpp v1.0.0

llama.cpp and its underlying ggml tensor library both reach v1.0.0, with a stated commitment to bump the major version for any breaking change to the public C API or ABI. The post says llama.cpp supports more than 150 architecture variants and all mainstream speculative decoding methods, and it lists pre-release artifacts and packages for Linux, macOS, Windows, Android, iOS, Docker, Homebrew, conda-forge, Winget and XCFramework. The release is open source, and the public headers are in the llama.cpp and ggml include directories.

Open the source ↗

Similar Developer Tools releases

  • cuda.bindings.cudla (cuDLA Python API)

    NVIDIA · Python DLA Runtime · Week 47, 2026

  • MACaQ

    Huawei CSL (huawei-csl) · Model quantisation toolkit · Week 47, 2026

  • Needle 3

    Cactus Compute · Tiny Device Model · Week 39, 2026

  • edge0

    Edge0-AI · Streaming MoE Inference · Week 37, 2026

  • Magnitude

    magnitudedev · Local Model Server · Week 36, 2026

  • SwarmLLM

    SwarmLLM · Peer-to-Peer Inference · Week 36, 2026

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.