Ettore Di Giacinto fc5b9ebfcc feat(loader): enhance single active backend to support LRU eviction (#7535) ... * feat(loader): refactor single active backend support to LRU This changeset introduces LRU management of loaded backends. Users can set now a maximum number of models to be loaded concurrently, and, when setting LocalAI in single active backend mode we set LRU to 1 for backward compatibility. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore: add tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Update docs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>		2025-12-12 12:28:38 +01:00
..
endpoints	feat(loader): enhance single active backend to support LRU eviction (#7535)	2025-12-12 12:28:38 +01:00
middleware	fix: do not require auth for readyz/healthz endpoints (#7403)	2025-12-01 10:35:28 +01:00
routes	feat(ui): allow to order search results (#7507)	2025-12-11 00:11:33 +01:00
static	chore: refactor css, restyle to be slightly minimalistic (#7397)	2025-11-29 22:11:44 +01:00
views	feat(loader): enhance single active backend to support LRU eviction (#7535)	2025-12-12 12:28:38 +01:00
app.go	fix(paths): remove trailing slash from requests (#7451)	2025-12-07 21:45:09 +01:00
app_test.go	chore(ci): do not overload the apple tests	2025-12-04 14:15:15 +01:00
explorer.go	feat: migrate to echo and enable cancellation of non-streaming requests (#7270)	2025-11-14 22:57:53 +01:00
http_suite_test.go	fix(llama-cpp): correctly calculate embeddings (#6259)	2025-09-13 23:11:54 +02:00
openai_mapping_test.go	feat(api): OpenAI video create enpoint integration (#6777)	2025-10-27 10:06:57 +01:00
openai_videos_test.go	feat: migrate to echo and enable cancellation of non-streaming requests (#7270)	2025-11-14 22:57:53 +01:00
render.go	feat: migrate to echo and enable cancellation of non-streaming requests (#7270)	2025-11-14 22:57:53 +01:00