github lemonade-sdk/lemonade candidate-v2026.48.0
v2026.48.0 (release candidate)

latest release: v2026.47.1
pre-release2 hours ago

Headline

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

  • Automatic MTP speculative decoding is enabled for HRX models, improving throughput on supported model pairs.
  • A new multi-GPU monitor displays per-GPU utilization and memory usage with selectable GPU history charts for 2 to 4 GPUs.
  • GGUF zero-shot prompt-router models extend /v1/classify with a GPU-accelerated encoder and scoring vector.
  • Multi-image editing and explicit image selection let you edit specific images and send them to Vision LLMs within a single conversation.

Breaking Changes

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

  • Requests that previously succeeded without authentication on API and metrics routes now return 401 when LEMONADE_API_KEY is set and LEMONADE_ADMIN_API_KEY is explicitly empty.
  • Upgrading TheNoise shared backend from v0.12.1 to v0.15.0 may change inference behavior, sampler handling, or memory layout for existing models shipped with the release.

Lemonade Server

Operating System Downloads
Windows lemonade.msi
Ubuntu 24.04+ Launchpad PPA
Debian 13 (x86_64) lemonade-server_2026.48.0-debian13_amd64.deb
Debian 13 (ARM64) lemonade-server_2026.48.0-debian13_arm64.deb
Fedora 43 (x86_64) lemonade-server-2026.48.0-fc43.x86_64.rpm
Fedora 43 (ARM64) lemonade-server-2026.48.0-fc43.aarch64.rpm
Fedora 44 (x86_64) lemonade-server-2026.48.0-fc44.x86_64.rpm
Fedora 44 (ARM64) lemonade-server-2026.48.0-fc44.aarch64.rpm
macOS Lemonade-2026.48.0-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-2026.48.0-ubuntu-x64.tar.gz
Ubuntu arm64 lemonade-embeddable-2026.48.0-ubuntu-arm64.tar.gz
Windows x64 lemonade-embeddable-2026.48.0-windows-x64.zip
macOS arm64 lemonade-embeddable-2026.48.0-macos-arm64.tar.gz

What's Changed

Thanks @AaronStGeorge, @Bekhouche, @DigitalFlow, @MrAnayDongre, @apollo-2006, @bitgamma, @danielholanda, @festeraeb, @fl0rianr, @github-actions, @iswaryaalex, @itomek, @jeremyfowers, @julianxhokaxhiu, @meghsat, @pwilkin, @sawansri, @sreeram-11, @superm1 for your awesome contributions to this release!

Click to expand changelog
  • Add gfx117x ROCm targets by @superm1 in #4057
  • Fixes the GUI3 banner in the news page by @meghsat in #3959
  • docs(api): re-record API examples for llama.cpp b12109 by @jeremyfowers in #4064
  • Add GUI overhaul video to news page by @jeremyfowers in #4058
  • feat(backend): FLM 1.0.11 decision models support by @meghsat in #4037
  • test(mcp): cover model aliases in gateway tool calls by @Bekhouche in #3536
  • fix(images): prevent loading on-demand upscalers by @fl0rianr in #4047
  • fix(gui3): show CPU usage on macOS and KV cache usage on all platforms by @meghsat in #4069
  • feat(gui): add image download and user message copy actions by @fl0rianr in #4062
  • Add Phoronix Lemonade 2026.45.3 article to news page by @jeremyfowers in #4075
  • feat(gui): add Halogen, Gufo, DwarfStar4 and TheNoise backend logos by @jeremyfowers in #4072
  • Gate NVIDIA CUDA backends on a missing or outdated driver by @jeremyfowers in #4066
  • feat(backends): Add description and author metadata to backends for display in the CLI and GUI by @danielholanda in #4059
  • Update container backend image pins by @github-actions[bot] in #4083
  • Add LFM3-1.7B and LFM3-VL-2B by @sawansri in #4044
  • fix(gui): add multi GPU monitor by @fl0rianr in #4025
  • feat(gui): add conversation image references and direct Vision LLM analysis by @fl0rianr in #4082
  • feat(hrx): Enable MPT + add MTP capable model by @AaronStGeorge in #4014
  • Beacon fixes: share the beacon port, escape the hostname by @festeraeb in #4094
  • fix(test): Fix build for MSVC (Visual Studio 2026) by @julianxhokaxhiu in #4109
  • fix(gui): pack backend cards into an aligned grid by @danielholanda in #4084
  • Fix unhelpful API key error in the CLI by @MrAnayDongre in #4103
  • test: remove network and cleanup flakiness from Ollama, Whisper and endpoint tests by @sreeram-11 in #4116
  • fix(server): prevent auth bypass with an empty admin API key by @fl0rianr in #4122
  • fix(models): list every shard in model file inventory by @pwilkin in #4108
  • test: wait for DirectoryWatcher detection instead of fixed sleeps by @sreeram-11 in #4117
  • Add GGUF zero-shot routers on llama.cpp: encoder in llama-server, rule head in lemond by @meghsat in #4096
  • Fix rpm creation issues on OpenSUSE by @DigitalFlow in #4091
  • ci: harden workflows against tzdata hangs, artifact upload errors and unprovisioned runners by @sreeram-11 in #4115
  • fix(docs/api): describe optional image generation metadata by @fl0rianr in #4125
  • fix(gui3): Upgrading banners to GUI3 by @meghsat in #4130
  • fix(CI): Porting the SystemOne test model to Laya from Julia by @meghsat in #4156
  • repo-manager action: track lemonade-testing's runner instead of pinning by @jeremyfowers in #4151
  • Triage Dashboard Additional View by @iswaryaalex in #3807
  • fix(ollama): reject models that can't chat or generate before loading them by @sreeram-11 in #4155
  • Run linux embedded build on Ubuntu 24.04 by @superm1 in #4140
  • feat(ollama): report speech and decision capabilities in /api/show by @sreeram-11 in #4160
  • fix(ollama): end failed /api/chat and /api/generate streams with an error line by @sreeram-11 in #4157
  • Fix TheNoise custom image model registration by @fl0rianr in #4138
  • fix(ollama): pass images and audio through /api/generate and report audio by @sreeram-11 in #4163
  • fix(ollama): resolve model aliases in /api/show by @sreeram-11 in #4158
  • fix(docs): only re-commit API examples whose response shape changed by @jeremyfowers in #4114
  • fix(gui): Updating the ModelScope assets to GUI3 by @meghsat in #4135
  • Update llama.cpp to b12233 by @github-actions[bot] in #4118
  • fix(server): Fixes the autotune falling back to 4k context on iGPU and NPUs by @meghsat in #4182
  • ci: skip expensive jobs for small docs-only PRs by @fl0rianr in #2889
  • fix: keep WebSocket API keys out of URLs by @itomek in #4141
  • Bump TheNoise to v0.15.0, add MOSS-Image and H3-Image by @bitgamma in #4187
  • server: return 400 for repos with no supported model files by @apollo-2006 in #3673

New Contributors

Full Changelog: v2026.46.2...candidate-v2026.48.0


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

Don't miss a new lemonade release

NewReleases is sending notifications on new releases.