Ettore Di Giacinto 18fcd8557c fix(llama.cpp): support gfx1200 (#6045) ...

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

2025-08-12 22:04:30 +02:00

..

cpp

fix(llama.cpp): support gfx1200 (#6045)

2025-08-12 22:04:30 +02:00

go

chore(build): Convert stablediffusion-ggml backend to Purego (#5989)

2025-08-12 16:42:15 +02:00

python

chore(deps): bump oneccl-bind-pt from 2.3.100+xpu to 2.8.0+xpu in /backend/python/common/template (#6016)

2025-08-12 18:57:20 +00:00

backend.proto

feat(stablediffusion-ggml): add support to ref images (flux Kontext) (#5935)

2025-07-30 22:42:34 +02:00

Dockerfile.golang

fix(intel): Set GPU vendor on Intel images and cleanup (#5945)

2025-07-31 19:44:46 +02:00

Dockerfile.llama-cpp

feat: do not bundle llama-cpp anymore (#5790)

2025-07-18 13:24:12 +02:00

Dockerfile.python

feat: Add backend gallery (#5607)

2025-06-15 14:56:52 +02:00

index.yaml

feat(diffusers): add builds for nvidia-l4t (#6004)

2025-08-08 22:48:38 +02:00