Lemonade – v9.3.1
Lemonade v9.3.1 just dropped – your go‑to toolkit for running LLMs locally got a solid boost! 🚀
What Lemonade does:
Run large language models on‑premise, tapping NPUs (Ryzen AI) and GPUs via Vulkan for lightning‑fast inference. It speaks OpenAI’s API, supports GGUF & ONNX, and ships with a Python SDK + CLI for deep customization—all on Windows or Linux.
What’s fresh in 9.3.1
- Code‑signed Windows MSI installers
No more “unknown publisher” warnings—installers are now cryptographically signed via SignPath.
- Ryzen AI SW 1.7 fully integrated
The latest Ryzen AI stack works out‑of‑the‑box. (If you’re upgrading, check the migration guide – a few config keys have moved.)
- Marketplace baked into the app
Browse and install featured apps directly from Lemonade’s revamped UI.
- UI & UX tweaks
• Redesigned Marketplace for smoother browsing (`#1045`)
• Chat message width now stays consistent while editing (`#1040`)
- Under‑the‑hood improvements
• Backend refactor for better performance (`#1036`)
• `max_tokens` patch in llama.cpp to respect OpenAI limits (`#1044`)
- Extras
• Snap store badge now shows the latest stable version
• Mobile web‑app redirection added
Breaking change ⚠️
Ryzen AI 1.7 migration shifts some config keys—see the migration guide before you upgrade.
Quick install links
| OS | Server + App | Server‑Only |
|—-|————–|————|
| Windows | `lemonade.msi` | `lemonade-server-minimal.msi` |
| Ubuntu | `lemonade_9.3.1_amd64.deb` | `lemonade-server-minimal_9.3.1_amd64.deb` |
Other flavors (Docker, Arch, Fedora, Debian…) are listed in the Installation Options docs.
Full changelog: v9.3.0 → v9.3.1. Happy tinkering! 🎉