(The previous release of this version was mis-tagged - the release has been re-created and installers have been reuploaded.)
What's Changed
- Major new release supports GGUF models only!
- New models like Mistral Instruct, Replit 1.5, Rift Coder and more
- All previous version of ggml-based models are no longer supported
- Extensive changes to Vulkan support
- Prompt processing on the GPU
- chat: clearer CPU fallback messages (#1478)
- Restore state from text (#1493)
- Fix compatiblity with non-AVX2 CPUs (#1488)
- llmodel: print an error if the CPU does not support AVX (#1499)
- always save chats to disk, but save them as text by default (#1495)
New Contributors
- @kevinbazira made their first contribution in #1444
- @jphme made their first contribution in #1485
- @umarmnaq made their first contribution in #1446
- @lordofthejars made their first contribution in #1414
Full Changelog: v2.4.19...v2.5.0