Headline
- Create, save, and share custom model recipes: https://lemonade-server.ai/docs/server/server_spec/#per-model-options
- Full NPU and ROCm support for the ROG Ally X handheld and RAI Z2 Extreme chip
- Full compatibility with LM Studio's GGUF library using
--extra-models-dir - FastFlowLM 0.9.24 support with improved ease-of-use
What's Changed
- Update GitHub/Website for early 2026 by @jeremyfowers in #716
- Add nemotron 3 nano model by @jeremyfowers in #751
- Touch up the documentation by @jeremyfowers in #753
- Adding instructions on how to build and run Lemonade CPP in a docker container by @siavashhub in #723
- Fix index.html responsive design by @jeremyfowers in #755
- Center website subtitle by @jeremyfowers in #756
- Add Ryzen AI Z2 support and LEMONADE_DISABLE_MODEL_FILTERING env var by @jeremyfowers in #764
- Upgrade FLM to 0.9.24 by @ramkrishna2910 in #781
- Steamline the new user experience by @jeremyfowers in #788
- add support for recipe options by @bitgamma in #775
- Lemonade API key by @bitgamma in #774
- Extra models dir models have an extra. prefix by @jeremyfowers in #793
- Improve the UX when FLM updates invalidate models by @jeremyfowers in #796
- Fix logprob calculation for hybrid by @ramkrishna2910 in #777
- Make some llamacpp-server args optional defaults by @bitgamma in #763
Full Changelog: v9.1.1...v9.1.2