# ggml: what I've logged

> ggml comes up in 2 posts of my AI log, from October 2026 to November 2026, and each item below links to the primary source. The releases I logged include llama.cpp b11645, filed under agents and coding, open weights and science.

## Items

1. **llama.cpp v1.0.0: A stronger foundation for the local AI ecosystem** (ggml-org, 12 Nov 2026): llama.cpp and ggml both reach v1.0.0, with semantic versioning so breaking changes to the public C API now show up as major-version bumps. [Primary source](https://huggingface.co/blog/ggml-org/llama-cpp-v1) · [Post](https://heyaliasif.com/ai/2026-11-13-llama-cpp-v1-antigravity-teamwork-glm-5-3-xybench#item-1)
2. **llama.cpp b11645** (ggml, 13 Oct 2026): A Metal BF16 flash attention kernel lands alongside a server fix that saves only restorable slot states to the prompt cache and a KV-cache fix for draft contexts. [Primary source](https://github.com/ggml-org/llama.cpp/releases/tag/b11645) · [Post](https://heyaliasif.com/ai/2026-10-15-liquid-lfm25-tokenspeed-llamacpp#item-3)

## Posts

- 2026-11-13 [llama.cpp v1.0.0, Antigravity /teamwork, GLM-5.3 on two DGX Stations](https://heyaliasif.com/ai/2026-11-13-llama-cpp-v1-antigravity-teamwork-glm-5-3-xybench)
- 2026-10-15 [Liquid's 24B on-device agent model, TokenSpeed, llama.cpp updates](https://heyaliasif.com/ai/2026-10-15-liquid-lfm25-tokenspeed-llamacpp)

Canonical: https://heyaliasif.com/ai/topics/ggml