Ettore Di Giacinto e502e51d78 feat(llama.cpp): add turboquant support ...

This PR adds patchset from the great work of @TheTom in
https://github.com/TheTom/llama-cpp-turboquant and creates a pipeline
that updates the patches against upstream automatically.

It also creates necessary scaffolding for doing this with other patches
sources.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-04-01 17:57:03 +00:00

..

build

chore(backends): do not bundle cuda target directory (#7982)

2026-01-12 07:51:09 +01:00

patch_utils

feat(llama.cpp): add turboquant support

2026-04-01 17:57:03 +00:00

changed-backends.js

chore(ci): Scope tests extras backend tests (#9170)

2026-03-30 17:46:07 +00:00

latest_hf.py

fix(scripts): minor fixup to gallery scripts

2024-07-13 11:36:20 +02:00

model_gallery_info.py

chore(scripts): allow to specify quants (#5430)

2025-05-22 11:53:30 +02:00

prepare-libs.sh

ci(Makefile): adds tts in binary releases (#2695)

2024-07-05 23:19:24 +02:00