baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Fix changelog format

Browse source
This commit is contained in:
Andrei Betlen 2023-06-06 17:01:10 -04:00
parent d508573fb4
commit 0e156ffd66
1 changed files with 14 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
CHANGELOG.md
View file

@ -7,24 +7,31 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased] ## [Unreleased]
- Added: k-quants support ### Added
- (llama.cpp) k-quants support
- (server) mirostat sampling parameters to server
## [v0.1.58] ## [v0.1.58]
- Added: Metal Silicon support ### Added
- (llama.cpp) Metal Silicon support
## [v0.1.57] ## [v0.1.57]
- Added: OpenLlama 3B support ### Added
- (llama.cpp) OpenLlama 3B support
## [v0.1.56] ## [v0.1.56]
### Added ### Added
- Added first version of the changelog - (misc) Added first version of the changelog
- Server: Use async routes - (server) Use async routes
- Use numpy for internal buffers to reduce memory usage and improve performance. - (python-api) Use numpy for internal buffers to reduce memory usage and improve performance.
### Fixed ### Fixed
- Performance bug in stop sequence check slowing down streaming. - (python-api) Performance bug in stop sequence check slowing down streaming.