From d038ac57248487e1fc18c249a92d6bc95ae95dac Mon Sep 17 00:00:00 2001 From: Timothy Wayne Gregg Date: Tue, 6 Oct 2026 14:49:55 -0400 Subject: [PATCH] Add About this fork note to README Co-Authored-By: Claude Sonnet 5.5 --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index dbe2c363a563..a85d279902f4 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,7 @@ +> **About this fork.** This is a fork of [ggml-org/llama.cpp](https://github.com/ggml-org/llama.cpp); the project and nearly all of its code belong to upstream. The fork's `master` carries a small set of changes on top of upstream as of its last sync: +> a fix to the Gemma 4 thinking generation prompt (chat templates and `tests/test-chat.cpp`), an audio transcription fallback for chat input in the server, and TurboQuant `turbo2`/`turbo3`/`turbo4` cache-type support including a Vulkan `SET_ROWS` path for `turbo4`. +> These changes are not part of upstream, have not been submitted upstream from here, and this fork is behind upstream's `master`. For releases, documentation and support, use the upstream project. + # llama.cpp ![llama](https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png)