lemonade-sdk/lemonade v10.4.0 on GitHub

Headline

vLLM ROCm is integrated as an experimental backend for Strix Halo and Strix Point devices (Linux only)
Completely overhauled documentation site at https://lemonade-server.ai/docs/
Improved organization and readability of the Model Manager in the GUI
Brand new contribution guide to help the project scale into the future

Lemonade Server

Operating System	Downloads
Windows	lemonade.msi (Server + App)
Ubuntu 24.04+	Launchpad PPA (Server + App)
Fedora 44	lemonade-server-10.4.0.x86_64.rpm (Server + App)
macOS (beta)	Lemonade-10.4.0-Darwin.pkg (Server + App)

lemonade-server-minimal.msi and the lemonade-server CLI are deprecated and will be removed in the next release.

Other platforms? See our Installation Options for Docker, Snap, Arch, Fedora, Debian, and more.

Embeddable Lemonade

Portable binaries for bundling into your own installer. Run lemond ./ as a subprocess.

Platform	Download
Ubuntu x64	lemonade-embeddable-10.4.0-ubuntu-x64.tar.gz
Windows x64	lemonade-embeddable-10.4.0-windows-x64.zip

What's Changed

Thanks @amd-pworfolk, @anditherobot, @jeremyfowers, @osimarr, @ramkrishna2910, @superm1, @theonlychant for your awesome contributions to this release!

Click to expand changelog

chore(linux): remove the AppImage build target by @jeremyfowers in #1756
docs: add llamacpp.md to nav and document rocm_channel in configuration reference by @Copilot in #1755
Npm security by @superm1 in #1665
Restructure the documentation by @jeremyfowers in #1776
Support /slots endpoint for llamacpp backend by @amd-pworfolk in #1722
feat: integrate Qwen2.5-Omni models with native audio input support by @ramkrishna2910 in #1581
New contribution guide and philosophy document by @jeremyfowers in #1793
Fix macOS dev build: drop Linux-only libdrm and ad-hoc codesign default by @jeremyfowers in #1796
Add vLLM as a wrapped server backend (ROCm) by @ramkrishna2910 in #1537
Update the docs onto the new design system by @jeremyfowers in #1798
Replace model label dots with icons by @anditherobot in #1800
Improve model manager naming and grouping by @anditherobot in #1803
Fix backend → backends typo in llamacpp docs by @Copilot in #1808
docs for vLLM backend by @ramkrishna2910 in #1802
vllm: wire --ctx-size and --vllm-args end-to-end by @ramkrishna2910 in #1827
Add static max context metadata to /models by @jeremyfowers in #1823
Warm model cache asynchronously by @jeremyfowers in #1829
fix(logs): build WebSocket URL from full server base URL by @theonlychant in #1837
docs: clarify that llamacpp.rocm_bin version tags are channel-specific by @Copilot in #1815
vllm: fix BackendManager download progress for split-archive installs by @ramkrishna2910 in #1832
Add vLLM ROCm news article by @jeremyfowers in #1844
Expose wrapped backend process IDs in /health by @anditherobot in #1838
Fix ollama tool calling by @osimarr in #1780

New Contributors

@theonlychant made their first contribution in #1837

Full Changelog: v10.3.0...v10.4.0

Windows installers are signed. Free code signing provided by SignPath.io, certificate by SignPath Foundation. See our Code Signing Policy.