Ettore Di Giacinto e49ea0123b feat(llama.cpp): add flash_attention and no_kv_offloading (#2310) ...

feat(llama.cpp): add flash_attn and no_kv_offload

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

2024-05-13 19:07:51 +02:00

..

backend

feat(llama.cpp): add flash_attention and no_kv_offloading (#2310)

2024-05-13 19:07:51 +02:00

cli

feat(ux): Add chat, tts, and image-gen pages to the WebUI (#2222)

2024-05-02 21:14:10 +02:00

clients

…

config

feat(llama.cpp): add flash_attention and no_kv_offloading (#2310)

2024-05-13 19:07:51 +02:00

http

feat(ui): display number of available models for installation (#2298)

2024-05-12 14:24:36 +02:00

schema

feat(grammar): support models with specific construct (#2291)

2024-05-12 01:13:22 +02:00

services

feat(webui): ux improvements (#2247)

2024-05-07 01:17:07 +02:00

startup

feat(startup): show CPU/GPU information with --debug (#2241)

2024-05-05 09:10:23 +02:00

application.go

…