From 6b98c8036f3495f7aaa51c1d8efe5fcbfe3c3fec Mon Sep 17 00:00:00 2001 From: Michal Harakal Date: Tue, 11 Aug 2026 10:25:48 +0200 Subject: [PATCH] docs(readme): point LLM users to SKaiNET-transformers (#923) A newcomer arriving for LLM inference reads GGUF/StreamingGGUFReader mentions here and reasonably assumes the LLM stack lives in this repo. Add a callout under Start-in-5-minutes naming the actual home (SKaiNET-transformers) and the artifacts/BOM to depend on. --- CHANGELOG.md | 8 ++++++++ README.md | 9 +++++++++ 2 files changed, 17 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index e03c6ac4e..8c8100492 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,6 +2,14 @@ ## [Unreleased] +### Documentation + +- **README points LLM users to SKaiNET-transformers** + ([#923](https://github.com/SKaiNET-developers/SKaiNET/issues/923)): a callout under + "Start in 5 minutes" says plainly that LLM inference lives in the + SKaiNET-transformers repository — this repo is the engine underneath — and names + the `sk.ainet.transformers` artifacts and BOM to depend on. + ## [0.39.0] - 2026-08-10 Headline: **on-device AI on Android becomes real.** A JNI NEON kernel backend diff --git a/README.md b/README.md index fb1db1056..c8cd4eef6 100644 --- a/README.md +++ b/README.md @@ -32,6 +32,15 @@ matches what you want to try first. Working in Java? SKaiNET ships first-class Java support — see the [Java getting-started guide](docs/modules/ROOT/pages/tutorials/java-getting-started.adoc). +> [!NOTE] +> **Looking for LLM inference?** Llama, Qwen, Gemma, Apertus, BERT embeddings and +> GGUF chat models live in +> [**SKaiNET-transformers**](https://github.com/SKaiNET-developers/SKaiNET-transformers) — +> this repository is the engine underneath it (tensors, NN DSL, compiler, CPU/native +> backends, GGUF/SafeTensors IO). Depend on the `sk.ainet.transformers` artifacts, +> pinned together by the +> [transformers BOM](https://central.sonatype.com/artifact/sk.ainet.transformers/skainet-transformers-bom). + Use the version shown in this README as the source of truth for first-run snippets. If another page shows a different version, please open an issue or PR.