github lemonade-sdk/lemonade candidate-v2026.46.0
v2026.46.0 (release candidate)
on GitHub

latest release: v2026.45.3
pre-release5 hours ago

Headline

⚠️ These notes are AI generated and will be revised by a human ⚠️

  • AMD Strix Halo gets dedicated container backends for llama.cpp, ds4, gufo, rocmfpx, and halogen models.
  • SystemOne decision models accept typed questions via POST /v1/systemone, with a new router classifier type.
  • Zero-shot classification arrives at POST /v1/classify with a labels parameter and zero-shot classifier condition.
  • TheNoise image generation gains a CUDA backend for Linux x86_64 alongside existing ROCm support.

Breaking Changes

⚠️ These notes are AI generated and will be revised by a human ⚠️

  • The /models response no longer includes image_defaults or audio_defaults keys; their values moved under recipe_options, so external clients reading the old fields will find them absent.
  • The /models response now includes a user_configurable boolean flag on backend descriptor options; consumers that assumed all listed options are editable may show technical knobs like soft_pixel_cap, pcm_sample_rate, and pcm_channels to users.

Lemonade Server

Operating System Downloads
Windows lemonade.msi
Ubuntu 24.04+ Launchpad PPA
Debian 13 (x86_64) lemonade-server_2026.46.0-debian13_amd64.deb
Debian 13 (ARM64) lemonade-server_2026.46.0-debian13_arm64.deb
Fedora 43 (x86_64) lemonade-server-2026.46.0-fc43.x86_64.rpm
Fedora 43 (ARM64) lemonade-server-2026.46.0-fc43.aarch64.rpm
Fedora 44 (x86_64) lemonade-server-2026.46.0-fc44.x86_64.rpm
Fedora 44 (ARM64) lemonade-server-2026.46.0-fc44.aarch64.rpm
macOS Lemonade-2026.46.0-Darwin.pkg

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

Embeddable Lemonade

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

Platform Download
Ubuntu x64 lemonade-embeddable-2026.46.0-ubuntu-x64.tar.gz
Ubuntu arm64 lemonade-embeddable-2026.46.0-ubuntu-arm64.tar.gz
Windows x64 lemonade-embeddable-2026.46.0-windows-x64.zip
macOS arm64 lemonade-embeddable-2026.46.0-macos-arm64.tar.gz

What's Changed

Thanks @Zorro-Zhang, @bitgamma, @fl0rianr, @github-actions, @iswaryaalex, @jeremyfowers, @kenvandine, @lucbruni-amd, @meghsat, @mike2307, @pwilkin, @ramkrishna2910, @ramkrishs, @sawansri for your awesome contributions to this release!

Click to expand changelog
  • Test that model-optional classify keeps a routing helper's residency by @jeremyfowers in #3850
  • docs: add the server architecture spec by @jeremyfowers in #3762
  • GUI3 into Main by @meghsat in #3834
  • Fully refactor the HTTP server: route classes, core components, generated API docs by @jeremyfowers in #3771
  • docs: add ModelManager spec by @bitgamma in #3768
  • fix: name the gpt-oss-20b checkpoint file by @lucbruni-amd in #3939
  • fix(server): invalidate backend status cache after implicit installs by @fl0rianr in #3926
  • fix(docs): key recorded API examples on the recipe's Vulkan pin only by @jeremyfowers in #3946
  • Adding GRG Halo device into the allow list by @meghsat in #3954
  • fix(bench): select context size per scenario by @fl0rianr in #3942
  • docs: transcribe the policy for adding a new backend by @jeremyfowers in #3925
  • fix(ci): resolve ROCm llama.cpp architecture source correctly by @fl0rianr in #3950
  • fix(server): report unavailable ttft/tps as null when the backend reports no timing by @mike2307 in #3955
  • fix(web): prevent webpack from parsing vendored model-viewer by @fl0rianr in #3938
  • fix(app): preserve composer mode during microphone dictation by @fl0rianr in #3951
  • chore(app): rename Dashboard to Monitor by @fl0rianr in #3934
  • fix(gui): restore browser-local API key persistence by @fl0rianr in #3967
  • fix(app): model report shared GPU memory correctly by @fl0rianr in #3944
  • fix(cli): distinguish a closed connection from a server that is not running by @ramkrishs in #3972
  • Update llama.cpp to b11846 by @github-actions[bot] in #3964
  • fix(gui3): keep mobile conversation sheet hidden with reduced motion by @fl0rianr in #3962
  • Model Manager refactoring by @bitgamma in #3828
  • CI(GUI): fix flaky A34 test - wait for mobile sheet before drag assertion by @fl0rianr in #3981
  • test(app): add light theme contrast checks and fix accessibility issues by @fl0rianr in #3948
  • fix(app): consume navigation query params on route changes by @fl0rianr in #3978
  • Add Flint-GGUF by @sawansri in #3940
  • chore(app): make browser chat persistant by default by @fl0rianr in #3984
  • add pi to mkdocs nav by @jeremyfowers in #3989
  • fix(gui): sync model backend warnings after backend updates by @fl0rianr in #3977
  • models: add K2-Horizon llama.cpp catalog entries by @ramkrishna2910 in #3985
  • fix(auto-tune): never refuse a load over a context estimate by @jeremyfowers in #3986
  • (docs): Update Release Guide by @iswaryaalex in #3979
  • add --submit/--submit-file to bench by @bitgamma in #3284
  • fix(gui): missing translation gaps by @fl0rianr in #3990
  • fix(app): use server sync for individual and bulk model updates by @fl0rianr in #3957
  • grabbing rocm versions per build by @iswaryaalex in #3996
  • fix(gui): show chat readiness and automatic backend install progress by @fl0rianr in #3992
  • Adding zero-shot classifier support by @meghsat in #3952
  • feat(backends): add TheNoise CUDA support by @fl0rianr in #4001
  • fix(app): support Firefox chatbot sidebar prompts by @fl0rianr in #3973
  • fix(gui3): Chat showing the wrong model after loading one from the Models tab (issue #4011) by @meghsat in #4013
  • fix(server): add missing backend args by @fl0rianr in #4021
  • fix(server): Turning off saved chats will retain the already saved chat sessions by @meghsat in #4012
  • fix(gui3): honor saved ctx_size when loading custom models (#4019) by @mike2307 in #4020
  • fix(server): apply default_model_source to built-in model downloads by @Zorro-Zhang in #4002
  • fix(gui3): Fixed bugs in Model load banners by @meghsat in #4030
  • refactor(models): list every model file in server_models.json by @jeremyfowers in #4041
  • chore: bump pwilkin backend versions by @pwilkin in #3993
  • feat(images): support optional upscale factor for TheNoise by @fl0rianr in #4046
  • feat(backends): run container backends through ContainerManager, starting with llamacpp:nathanw by @jeremyfowers in #3709
  • feat(ds4): move ds4:rocm to a container backend by @jeremyfowers in #3710
  • feat(rocmfpx): add the ROCm FPX container backend by @jeremyfowers in #3711
  • feat(halogen): add the Halogen Flash container backend by @jeremyfowers in #3712
  • ci: keep container backend images on the newest build of their tags by @jeremyfowers in #3713
  • ci: Add cuda backend validation for llama.cpp on Linux using self-hosted amd64 and arm64 runners by @kenvandine in #3714
  • fix(gui): align chat toolbar controls (#4051) by @fl0rianr in #4053
  • feat(llamacpp): add the halobox container backend by @jeremyfowers in #4029
  • feat(gufo): add the Gufo container backend by @jeremyfowers in #4031
  • Add SystemOne decision models: /v1/systemone, GGUF zero-shot on /v1/classify, and the systemone router classifier by @meghsat in #3956
  • Remove image_defaults and audio_defaults by @bitgamma in #4049

New Contributors

Full Changelog: v2026.44.1...candidate-v2026.46.0

The Windows installers in this release candidate are not signed; Windows SmartScreen will warn before installing. Stable releases are signed.

Check out latest releases or
releases around lemonade-sdk/lemonade candidate-v2026.46.0

Don't miss a new lemonade release

NewReleases is sending notifications on new releases.

Get notifications