lemonade-sdk/lemonade v8.1.1

on GitHub

Headline

• ROCm7 is now available as a llamacpp backend on supported Radeon GPUs @danielholanda
• Model build for custom NPU and Hybrid LLMs updated for RAI SW 1.5 @iswaryaalex
• Added gpt-oss-120b-GGUF and gpt-oss-20b-GGUF support to Lemonade Server @danielholanda

Additional Improvements

• --ctx-size option added to lemonade-server serve to allow adjusting the context length @danielholanda
• Support image input in web app LLM Chat @vgodsoe
• Improve server error handling in web UI @jeremyfowers
• Add a workflow for automatically publishing the website by @jeremyfowers @vgodsoe
• Add hot GGUF models: qwen3-coder and cogito-v2-109B @jeremyfowers
• Overhaul server_models.md and add NPU models @jeremyfowers

Bug Fixes

• Re-enable large model download from HF @jeremyfowers