Ettore Di Giacinto 739573e41b feat(flash_attention): set auto for flash_attention in llama.cpp (#6168) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>		2025-08-31 17:59:09 +02:00
..
application	fix: register backends to model-loader during installation (#6159)	2025-08-28 19:11:02 +02:00
backend	feat(flash_attention): set auto for flash_attention in llama.cpp (#6168)	2025-08-31 17:59:09 +02:00
cli	fix: register backends to model-loader during installation (#6159)	2025-08-28 19:11:02 +02:00
clients	feat(store): add Golang client (#1977)	2024-04-16 15:54:14 +02:00
config	feat(flash_attention): set auto for flash_attention in llama.cpp (#6168)	2025-08-31 17:59:09 +02:00
dependencies_manager	fix: be consistent in downloading files, check for scanner errors (#3108)	2024-08-02 20:06:25 +02:00
explorer	feat(p2p): automatically sync installed models between instances (#6108)	2025-08-19 19:37:46 +02:00
gallery	fix: register backends to model-loader during installation (#6159)	2025-08-28 19:11:02 +02:00
http	feat(gallery): Add 'Get Config' button for models (#6154)	2025-08-28 18:32:49 +02:00
p2p	feat(p2p): automatically sync installed models between instances (#6108)	2025-08-19 19:37:46 +02:00
schema	feat(diffusers): add support for wan2.2 (#6153)	2025-08-28 10:26:42 +02:00
services	fix: register backends to model-loader during installation (#6159)	2025-08-28 19:11:02 +02:00
startup	fix: register backends to model-loader during installation (#6159)	2025-08-28 19:11:02 +02:00
templates	feat(backends): add system backend, refactor (#6059)	2025-08-14 19:38:26 +02:00