Skip to content
HomeBriefFor youTrackersTopicsCompaniesGlossaryNewsletterSecurityHealth & medicineFinance & marketsRoboticsModels & researchPolicy & regulationEnterprise & businessDeveloper tools
Developer tools · Nov 14, 2026 · 3 min read

llama.cpp 1.0.0 after 3.5 years: semantic versioning, 35 deprecated functions gone, FP8 KV cache. What the stability promise changes for local AI

The engine under Ollama, LM Studio and most on-device inference now promises that breaking changes arrive only with a major version; for the teams that link libllama, that is the end of a fortnightly maintenance tax.

Why it matters
DevelopersPin to 1.x, migrate off anything that was marked deprecated, and read the changelog only on major bumps. If your product wraps libllama, this is the release that lets you stop vendoring a git commit hash.
ML engineersFP8 KV cache and a host-memory expert cache for MoE models are the two features that make this week's 594B open-weight releases plausible on a single box. Measure quality loss before you trust them.
ExecutivesThe main argument against running models on your own hardware was maintenance churn. A stability contract on the de facto local runtime weakens it; the GPU bill is now the whole decision.

On Thursday Georgi Gerganov's ggml-org released llama.cpp 1.0.0 and ggml 1.0.0, three and a half years after the project began as a weekend port of Meta's first Llama weights to a MacBook. The headline is not a feature. It is a promise: from now on, libllama and libggml follow semantic versioning. A major version means a breaking change to the public C API or ABI. A minor version adds backends, model architectures or new API without breaking old callers. A patch fixes bugs and changes nothing else. An official llama.cpp release is only tagged when its bundled ggml matches a released ggml, so system-wide installs from Debian or Homebrew stay consistent.

Why that matters more than it sounds

llama.cpp is the inference engine beneath a large share of local and on-device AI: Ollama, LM Studio, Jan and dozens of apps link it or shell out to it, and the GGUF format it introduced is how quantised open-weight models are distributed. Until now the project shipped a numbered build almost daily and reserved the right to change its API at any time. Teams that depended on it either froze a commit and fell behind on model support, or tracked the head and absorbed breakage. The release post acknowledges this directly, noting that many downstream applications depend on the work and that the maintainers will prioritise code quality and architectural control.

What is in 1.0.0

The deprecated public API is removed, 35 functions in all, so anything still calling them must migrate. The NextN speculative-decoding API moves from an extension header into the public llama.h. Memory handling gains FP8 KV caches and a host-memory cache for mixture-of-experts models with a configurable CPU share, which is the feature that lets a sparse model larger than video memory run by keeping cold experts in system RAM. New model support includes Kimi K3.1 Pro and vision for Kimi K3.1, a text-to-speech model and several text architectures, taking the supported count past 150 variants. The server fixes server-side request forgery, CORS and DNS-rebinding issues, restricts the HF_TOKEN to huggingface.co hosts, and adds an OpenAI-compatible speech endpoint. Pre-built packages cover Linux, macOS, Windows, Android and iOS through Docker, Debian, Homebrew, conda-forge, MacPorts, Winget and an XCFramework. Nvidia, AMD, Qualcomm, Arm, IBM and Intel supply self-hosted CI runners; Hugging Face infrastructure handles the rest.

The counter-argument

A version number is a developer commitment, not a code freeze. The release post is explicit that change continues; what changes is the signalling. End users of Ollama or LM Studio will notice nothing on Friday. And semantic versioning cuts both ways: a project that has moved fast for three years may find that the next genuinely necessary API break now requires a 2.0 and a migration guide, which is friction the daily-build era never had. Whether the maintainers hold the line through the next wave of architectures, this week alone brought a 594B NVFP4 model and a 1.6T MoE, is the test.

What to do

If you ship software that links libllama: move to the 1.0.0 tag, run your test suite against the removed deprecated functions, and set your dependency to 1.x with minor-version updates allowed. If you distribute GGUF models: nothing changes in the format, but check that your quantisation recipes still load. If you are evaluating on-device or on-premises inference for a product: the FP8 KV cache and MoE host cache are worth benchmarking against your current serving stack on the models you actually run, with attention to quality at long context, not only tokens per second. If you are an executive weighing self-hosting: the runtime's stability was the argument against; the GPU bill and the serving-stack gaps we described for Inkling 2 Small on Thursday are the arguments that remain.

Key terms in this story

  • Semantic versioning A version-number convention (MAJOR.MINOR.PATCH) in which breaking changes bump the first number, compatible additions the second and bug fixes the third.
  • Open-weight model A model whose trained parameters are published for anyone to download and run.
  • Inference Running a trained model to produce output. What you pay for when you call an API.
  • Token The unit models read and write; roughly three-quarters of an English word. Pricing and context limits are counted in tokens.
  • NVFP4 Nvidia's 4-bit floating-point weight format, used to train and serve very large models on Blackwell-class GPUs with roughly a quarter of the memory of 16-bit weights.
All 99 terms →
modelsinfrastructureresearch
Written in our own words from the linked sources · updated 2026-11-14 · corrections: corrections@aibriefing.io

Get the brief in your inbox

One email every morning: the stories that mattered in AI, each with a one-line "why it matters" for your role. Free, no ads, unsubscribe any time.

Published daily by AI Briefing. We never share your address.
Like this? Get tomorrow's brief by email, free.