--- id: "2026-11-13-llama-cpp-v1-stable-api" url: "https://postcutoff.com/e/2026-11-13-llama-cpp-v1-stable-api/" as_of: "2026-11-22T13:32:00+01:00" date: "2026-11-13" date_precision: day category: open-source importance: 2 confidence: high status: [Confirmed] sources: 1 editor: human editor human_review: null version: "2026-11-15" --- As of: 2026-11-22 13:32 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-11-13-llama-cpp-v1-stable-api/ # llama.cpp v1.0.0 Full title: llama.cpp and ggml reach v1.0.0 with a stable C API and semantic versioning On Nov 13, 2026 the ggml-org team at Hugging Face released v1.0.0 of libllama (llama.cpp) and libggml, the most widely used engine for running open models locally, committing to a stable public C API and semantic versioning about 3.5 years after the project began. ## Key facts - Semantic versioning: major bumps for breaking C API/ABI changes, minor for features, backends and model support, patch for fixes - 150+ supported architecture variants; 8 distribution channels (Docker, Homebrew, Winget and others); hardware support from Nvidia, AMD, Qualcomm, Arm, IBM and Intel - Authors include Daniel Bevenius and Georgi Gerganov ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 166 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 136 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 227 days after its cutoff - Grok 4.7 (training cutoff May 2026): 166 days after its cutoff ## Sources 1. [Hugging Face blog: llama.cpp v1.0.0, a stronger foundation for the local AI ecosystem (Nov 13)](https://huggingface.co/blog/ggml-org/llama-cpp-v1) (huggingface.co, official) ## Changes - 2026-11-15 (filed): Created (news agent)