Mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-06-07 19:40:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: updates

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Ettore Di Giacinto 2023-12-08 15:11:44 +01:00 committed by GitHub
parent 4de2c6a421
commit 3822bd2369
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 12 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
docs/content/news/_index.en.md
View File

@ -10,18 +10,19 @@ url = '/basics/news/'
This release brings a major overhaul in some backends. This release brings a major overhaul in some backends.
Breaking changes: Breaking/important changes:
- Backend rename: `llama-stable` renamed to `llama-ggml` https://github.com/mudler/LocalAI/pull/1287 - Backend rename: `llama-stable` renamed to `llama-ggml` {{< pr "1287" >}}
- Prompt template changes: https://github.com/mudler/LocalAI/pull/1254 (extra space in roles) - Prompt template changes: {{< pr "1254" >}} (extra space in roles)
- Apple metal bugfixes: {{< pr "1365" >}}
New: New:
- Added support for LLaVa and OpenAI Vision API support ({{< pr "1254" >}})
- Added support for LLaVa and OpenAI Vision API support (https://github.com/mudler/LocalAI/pull/1254) - Python based backends are now using conda to track env dependencies ( {{< pr "1144" >}} )
- Python based backends are now using conda to track env dependencies ( https://github.com/mudler/LocalAI/pull/1144 ) - Support for parallel requests ( {{< pr "1290" >}} )
- Support for parallel requests (https://github.com/mudler/LocalAI/pull/1290) - Support for transformers-embeddings ( {{< pr "1308" >}})
- Support for transformers-embeddings (https://github.com/mudler/LocalAI/pull/1308) - Watchdog for backends ( {{< pr "1341" >}}). As https://github.com/ggerganov/llama.cpp/issues/3969 is hitting LocalAI's llama-cpp implementation, we have now a watchdog that can be used to make sure backends are not stalling. This is a generic mechanism that can be enabled for all the backends now.
- Watchdog for backends (https://github.com/mudler/LocalAI/pull/1341). As https://github.com/ggerganov/llama.cpp/issues/3969 is hitting LocalAI's llama-cpp implementation, we have now a watchdog that can be used to make sure backends are not stalling. This is a generic mechanism that can be enabled for all the backends now. - Whisper.cpp updates ( {{< pr "1302" >}} )
- Whisper.cpp updates (https://github.com/mudler/LocalAI/pull/1302) - Petals backend ( {{< pr "1350" >}} )
Due to the python dependencies size of images grew in size. Due to the python dependencies size of images grew in size.
If you still want to use smaller images without python dependencies, you can use the corresponding images tags ending with `-core`. If you still want to use smaller images without python dependencies, you can use the corresponding images tags ending with `-core`.
@ -38,7 +39,7 @@ This release now brings the `llama-cpp` backend which is a c++ backend tied to l
### Support for ROCm/HIPBLAS ### Support for ROCm/HIPBLAS
This release bring support for AMD thanks to @65a . See more details in https://github.com/mudler/LocalAI/pull/1100 This release bring support for AMD thanks to @65a . See more details in {{< pr "1100" >}}
### More CLI commands ### More CLI commands