- New and more robust allocation strategy for non-integer bitrates
- Added
-hqargument to quantizer (explanation here) - Fix bug causing prompt caching to fail on recurrent models for certain combinations of prompt length and chunk size
- Fix broken output when using repetition penalties without decay range (affecting some OAI clients via TabbyAPI)
- Fix issue allowing recurrent state to fall out of sync with K/V cache
- Support more features in Nanochat, for some reason
- Other fixes and QoL improvements
Full Changelog: v0.0.26...v0.0.27