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

..

embeddings.go

Revert #1963 (#2056)

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

image.go

Revert #1963 (#2056)

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

llm.go

Revert #1963 (#2056)

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

options.go

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

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

rerank.go

feat(rerankers): Add new backend, support jina rerankers API (#2121)

2024-04-25 00:19:02 +02:00

stores.go

feat(stores): Vector store backend (#1795)

2024-03-22 21:14:04 +01:00

transcript.go

refactor(application): introduce application global state (#2072)

2024-04-29 17:42:37 +00:00

tts.go

fix: reduce chmod permissions for created files and directories (#2137)

2024-04-26 00:47:06 +02:00