Ettore Di Giacinto 697c769b64

fix(llama.cpp): enable cont batching when parallel is set (#1622) ...

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

2024-01-21 14:59:48 +01:00

..

cpp

fix(llama.cpp): enable cont batching when parallel is set (#1622)

2024-01-21 14:59:48 +01:00

go

Revert "[Refactor]: Core/API Split" (#1550)

2024-01-05 18:04:46 +01:00

python

feat(extra-backends): Improvements, adding mamba example (#1618)

2024-01-20 17:56:08 +01:00

backend.proto

feat: 🐍 add mamba support (#1589)

2024-01-19 23:42:50 +01:00