Ettore Di Giacinto a9b0e264f2 chore(exllama): drop exllama backend ... For polishing and cleaning up it makes now sense to drop exllama which is completely unmaintained, and was only supporting the llamav1 architecture (nowadays it's superseded by llamav1) . Signed-off-by: Ettore Di Giacinto <mudler@localai.io>		2024-09-13 19:09:43 +02:00
..
cpp	chore(deps): update llama.cpp (#3497)	2024-09-12 20:55:27 +02:00
go	fix: untangle pkg/grpc and core/schema for Transcription (#3419)	2024-09-02 15:48:53 +02:00
python	chore(exllama): drop exllama backend	2024-09-13 19:09:43 +02:00
backend.proto	feat: elevenlabs sound-generation api (#3355)	2024-08-24 00:20:28 +00:00