Ettore Di Giacinto 180cd4ccda

fix(llama.cpp-ggml): fixup max_tokens for old backend (#2094) ...

fix(llama.cpp-ggml): set 0 as default for `max_tokens`

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

2024-04-21 16:34:00 +02:00

..

backend

Add tensor_parallel_size setting to vllm setting items (#2085)

2024-04-20 14:37:02 +00:00

cli

models(gallery): add gallery (#2078)

2024-04-20 15:22:54 +02:00

clients

feat(store): add Golang client (#1977)

2024-04-16 15:54:14 +02:00

config

fix(llama.cpp-ggml): fixup max_tokens for old backend (#2094)

2024-04-21 16:34:00 +02:00

http

refactor(routes): split routes registration (#2077)

2024-04-21 01:19:57 +02:00

schema

feat(functions): support models with no grammar, add tests (#2068)

2024-04-18 22:43:12 +02:00

services

Revert #1963 (#2056)

2024-04-17 23:33:49 +02:00

startup

feat: fiber logs with zerlog and add trace level (#2082)

2024-04-20 10:43:37 +02:00