Open source #Open models Nov 14, 2026 · Originally published Nov 13

llama.cpp and ggml reach v1.0.0: breaking changes to the public C API will now bump the major version

The most widely used base for local inference now promises a stable API. Versioning rules, model coverage and distribution channels, for teams that ship libllama inside their apps.

Image: Hugging Face blog
Primary source Hugging Face blog · huggingface.co Read the original ↗

// Key points

  • libllama (llama.cpp) and libggml (ggml) both ship v1.0.0; from now on API and ABI incompatibilities are signalled by a major-version bump.
  • Rules: a breaking change to the public C API in ./include bumps MAJOR; backward-compatible features, backend updates and new model support bump MINOR; fixes with no API change bump PATCH.
  • It supports more than 150 model architecture variants and all mainstream speculative decoding methods.
  • Distribution covers Docker, Debian, Homebrew, conda-forge, MacPorts, Winget and an XCFramework for iOS and macOS; CI runs on self-hosted hardware from NVIDIA, AMD, Qualcomm, Arm, IBM and Intel.

Builder's takeThe point here is not a new feature but being safe to depend on: shipping libllama in a desktop or mobile app used to mean re-checking the interface on every upgrade. I would pin to 1.x and let MINOR updates flow; for cases like AI Cloud Drive that want on-device file understanding, an offline path is now worth a serious look.

// Background · from #Open models

Full timeline →
  1. Nov 14 NVIDIA serves the 753B-parameter GLM-5.3 across two DGX Stations, peaking at 607.8 output tokens per second at concurrency 16
  2. Nov 13 IBM releases the LLMON markup language with Granite 4.1 3B and 8B preview models: reserved special tokens separate instructions from data, blocking 47% more injection attacks on OPI than the best frontier model tested
  3. Nov 13 DeepSeek V4-Pro, V4-Flash and V4.1-Flash arrive on SageMaker JumpStart: MIT-licensed MoE models with a 1M-token context

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →