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architecture (nowadays it's superseded by llamav1) .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