Skip to content

Router that virtually distributes inference across connected devices in the home.

Go

Add release notes and an upgrade guide to the docs (#157)

ckelseynvbf9759720013
diff --git a/README.md b/README.md
index 3a32706..5f8092c 100644
--- a/README.md
+++ b/README.md
@@ -230,7 +230,9 @@ Each entry assumes the ones before it.
together. Start here so the vocabulary in every other document makes sense.
2. **[Getting started](docs/getting-started.mdx)** — install it, pair two
machines, prepare a model, and send a first request. This is the only document
- most users need.
+ most users need. When you update, **[Release notes](docs/release-notes.mdx)**
+ lists what changed and the **[Upgrade guide](docs/upgrade-guide.mdx)** covers
+ any steps the update needs.
3. **[Managing engines](docs/engine-lifecycle.mdx)** — install, start, stop,
update, and uninstall engines; what PAIR restores after you quit or relaunch.
4. **[Engine settings](docs/engine-settings.mdx)** — change an engine's ports and
diff --git a/docs/getting-started.mdx b/docs/getting-started.mdx
index 69a8c03..66bcf45 100644
--- a/docs/getting-started.mdx
+++ b/docs/getting-started.mdx
@@ -598,6 +598,11 @@ because they belong to the engine rather than to PAIR. Updating PAIR does not
update its inference engines — engines are updated separately from **Engine
settings**, described in [Managing engines](engine-lifecycle.mdx).
+If you are updating from a version before 1.0.0, a few setups have a small extra
+step, such as tidying up the old app on macOS. The
+[Upgrade Guide](upgrade-guide.mdx) walks through them, and
+[Release Notes](release-notes.mdx) lists what changed.
+
You update each machine from that machine. PAIR never updates a peer for you,
and it cannot be driven remotely, so a cluster is updated one node at a time.
@@ -624,6 +629,8 @@ endpoint, routing, and service-startup issues.
Refer to these resources for related information:
+- [Release notes](release-notes.mdx)
+- [Upgrade guide](upgrade-guide.mdx)
- [Troubleshooting](troubleshooting.mdx)
- [Project overview](overview.mdx)
- [Architecture, data flow, and trust boundaries](architecture.mdx)
diff --git a/docs/known-issues.mdx b/docs/known-issues.mdx
index 741d76a..dd7b0c8 100644
--- a/docs/known-issues.mdx
+++ b/docs/known-issues.mdx
@@ -80,6 +80,15 @@ This matters most for a genuinely headless deployment, where those operations ha
no other route on that machine. Refer to
[What the Terminal Interface Cannot Do](terminal-interface.mdx#what-the-terminal-interface-cannot-do).
+## PAIR Does Not Remove an LM Studio That It Installed Before Version 1.0.0
+
+PAIR removes only the engines it has a record of installing, and versions before
+1.0.0 kept no record. An LM Studio installed by one of those versions is treated
+as your own: **Uninstall**, **Reset app data**, and uninstalling PAIR all leave
+it and `~/.lmstudio` in place. It keeps working with PAIR. To remove it, or to
+let PAIR manage it from now on, refer to
+[If an Earlier PAIR Installed LM Studio for You](upgrade-guide.mdx#if-an-earlier-pair-installed-lm-studio-for-you).
+
## Engine Binaries Are Not on Your PATH
PAIR does not add the engines it installs to your `PATH`, so running an engine's
diff --git a/docs/release-notes.mdx b/docs/release-notes.mdx
new file mode 100644
index 0000000..c9a59bd
--- /dev/null
+++ b/docs/release-notes.mdx
@@ -0,0 +1,103 @@
+{/*
+SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+SPDX-License-Identifier: Apache-2.0
+*/}
+
+# Release Notes
+
+What changed in each release of PAIR. If you are updating from an earlier
+version, read the [Upgrade Guide](upgrade-guide.mdx) as well: it covers the
+steps some machines need.
+
+Notes for releases before 1.0.0 are on
+[GitHub Releases](https://github.com/NVIDIA/Personal-AI-Router/releases).
+
+## 1.0.0
+
+This release brings llama.cpp and RTX Spark support to PAIR, and establishes
+its public development and contribution workflow on GitHub.
+
+### What's New
+
+- **llama.cpp support.** Install and manage llama.cpp directly from PAIR,
+ download compatible GGUF models from Hugging Face, and route inference
+ requests across paired devices. Refer to
+ [Managing Engines](engine-lifecycle.mdx).
+- **Engine launch options.** Customize the launch arguments and environment
+ variables of PAIR-managed engines, on this device or a paired one. Tune
+ settings such as context size where the engine supports them. Refer to
+ [Engine Settings](engine-settings.mdx).
+- **RTX Spark support.** PAIR's Windows on ARM build has been validated with
+ llama.cpp and CUDA on RTX Spark N1X hardware.
+- **Improved terminal experience.** The terminal interface has a redesigned
+ layout organized around each device, so you can manage engines, download
+ models, and pair devices from one place. A new **Jobs** tab follows inference
+ work across paired devices and runs the Inference Demo, giving headless
+ machines the same core tools as the desktop app. Refer to
+ [Terminal Interface](terminal-interface.mdx).
+
+### Compatibility Notes
+
+- **Browser clients.** PAIR's local endpoints now follow each engine's CORS
+ policy instead of allowing every browser origin. A browser-based client may
+ need the engine configured to allow it — for Ollama, set `OLLAMA_ORIGINS` in
+ the engine's launch options.
+- **The macOS app is now NVIDIA PAIR.** The new `NVIDIA PAIR.app` installs
+ beside the old `PAIR.app`, so remove the old one to keep just one copy. Your
+ settings, cluster membership, and downloaded models carry over.
+- **LM Studio installed by an earlier PAIR.** It keeps working as before. PAIR
+ now removes only engines it has a record of installing, and earlier versions
+ kept no record, so uninstalling or resetting PAIR leaves that LM Studio in
+ place. You can remove it from `~/.lmstudio` yourself if you no longer want it.
+
+The [Upgrade Guide](upgrade-guide.mdx) walks through each of these.
+
+### Targeted Bug Fixes
+
+- Uninstalling LM Studio from PAIR, or uninstalling PAIR with its data, no
+ longer deletes the models you downloaded. They stay in `~/.lmstudio/models`,
+ just as Ollama's stay in `~/.ollama` and llama.cpp's in `~/.llamacpp`.
+
+### Community Contributions
+
+- Added Anthropic Messages API routing through Ollama and LM Studio, so
+ compatible clients such as Claude Code can use PAIR's model-aware routing and
+ failover. Thanks [@Ratherrayees](https://github.com/Ratherrayees)!
+ ([#27](https://github.com/NVIDIA/Personal-AI-Router/pull/27))
+- Made engine monitoring more efficient by reusing HTTP connections for health
+ checks. Thanks [@Psych0h3ad](https://github.com/Psych0h3ad)!
+ ([#37](https://github.com/NVIDIA/Personal-AI-Router/pull/37))
+- Fixed unnecessary cluster trust refreshes: notifications are now sent only
+ after new peer endorsements are saved. Thanks [@RecursiveIntell](https://github.com/RecursiveIntell)!
+ ([#62](https://github.com/NVIDIA/Personal-AI-Router/pull/62))
+- Fixed workload synchronization between nodes: broadcasts preserve event
+ order, and a failed broker notification stays eligible for retry. Thanks
+ [@mkalkere](https://github.com/mkalkere)! ([#80](https://github.com/NVIDIA/Personal-AI-Router/pull/80))
+- Fixed scheduler priority updates being marked as delivered after a failed
+ notification, so they are retried and the status stays accurate. Thanks
+ [@sylvesterkaczmarek](https://github.com/sylvesterkaczmarek)!
+ ([#122](https://github.com/NVIDIA/Personal-AI-Router/pull/122))
+- Isolated the service integration and proxy failover tests from local PAIR
+ settings, so tests no longer read or overwrite a developer's configuration.
+ Thanks [@somtri](https://github.com/somtri)! ([#95](https://github.com/NVIDIA/Personal-AI-Router/pull/95))
+- Corrected the release-intent examples to use the required services version
+ key. Thanks [@somtri](https://github.com/somtri)!
+ ([#120](https://github.com/NVIDIA/Personal-AI-Router/pull/120))
+- Updated the contributor instructions to branch from and rebase onto
+ `develop`. Thanks [@somtri](https://github.com/somtri)!
+ ([#126](https://github.com/NVIDIA/Personal-AI-Router/pull/126))
+- Fixed node cards showing only the first GPU on multi-GPU systems; they now
+ show every GPU. Thanks [@CryptoJones](https://github.com/CryptoJones)!
+ ([#34](https://github.com/NVIDIA/Personal-AI-Router/pull/34))
+
+### Special Thanks
+
+Thank you to these community members for sharing ideas, submitting proposals
+and fixes, investigating issues, and testing PAIR:
+
+[@XxSilentStormIxX](https://github.com/XxSilentStormIxX), [@agenticocho](https://github.com/agenticocho), [@Mayimbe07](https://github.com/Mayimbe07), [@cruzanstx](https://github.com/cruzanstx), [@pettersandvand](https://github.com/pettersandvand),
+[@cguldogan](https://github.com/cguldogan), [@mkalkere](https://github.com/mkalkere), [@CryptoJones](https://github.com/CryptoJones), [@woodsonl](https://github.com/woodsonl), [@stevbev](https://github.com/stevbev), [@habakan](https://github.com/habakan), [@arcaven](https://github.com/arcaven),
+[@somtri](https://github.com/somtri), [@imluffy000](https://github.com/imluffy000), [@ndizazzo](https://github.com/ndizazzo), and [@fpvo](https://github.com/fpvo).
+
+We are grateful for every contribution, and for the warm welcome from the local
+AI community.
diff --git a/docs/upgrade-guide.mdx b/docs/upgrade-guide.mdx
new file mode 100644
index 0000000..9c2e5fd
--- /dev/null
+++ b/docs/upgrade-guide.mdx
@@ -0,0 +1,127 @@
+{/*
+SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+SPDX-License-Identifier: Apache-2.0
+*/}
+
+# Upgrade Guide
+
+Updating to PAIR 1.0.0 works the same way as any other update. Your settings,
+cluster membership, and downloaded models all carry over, so for most machines
+there is nothing extra to do. Install the update as described in
+[Keeping PAIR Up to Date](getting-started.mdx#keeping-pair-up-to-date), and
+update each machine in your cluster so they all run the same version.
+
+A few situations call for a small extra step. Each section below says who it
+applies to, so you can skip the ones that do not:
+
+- [On macOS, tidy up the old app](#on-macos-tidy-up-the-old-app)
+- [If an earlier PAIR installed LM Studio for you](#if-an-earlier-pair-installed-lm-studio-for-you)
+- [If you use PAIR from a web page or browser extension](#if-you-use-pair-from-a-web-page-or-browser-extension)
+
+For everything that is new in this release, refer to
+[Release Notes](release-notes.mdx).
+
+## On macOS, Tidy Up the Old App
+
+The macOS application is now called **NVIDIA PAIR**. Earlier versions were
+installed as `PAIR.app`, and because the name changed, the new disk image adds
+`NVIDIA PAIR.app` beside the old app instead of replacing it. Keep just one by
+removing the old app with the uninstaller it includes. The uninstaller keeps
+your settings, cluster membership, engines, and models.
+
+1. Quit PAIR.
+2. In Terminal, run the old app's uninstaller:
+
+ ```bash
+ sudo /Applications/PAIR.app/Contents/Resources/installer-tools/uninstall-macos.sh
+ ```
+
+ It finishes with `User data preserved`. Leave off the `--purge` option, which
+ is only for removing PAIR's data as well.
+3. Open the new disk image, drag **NVIDIA PAIR** to **Applications**, and launch
+ it from there.
+
+The uninstaller is a better choice than dragging the old app to the Trash,
+because it also removes PAIR's firewall rules and the helper that manages them.
+
+If you updated from within PAIR using **Restart & install**, the update was
+applied to your existing app, which keeps working under the `PAIR.app` name.
+PAIR finds its files and data from wherever the app is, not by its name, so
+there is nothing more to do unless you also install `NVIDIA PAIR.app` from the
+disk image, in which case remove `PAIR.app` as above. If PAIR does not reopen
+after **Restart & install**, open it from **Applications**.
+
+## If an Earlier PAIR Installed LM Studio for You
+
+This applies only if you used an earlier version of PAIR to install LM Studio.
+That LM Studio keeps working with PAIR 1.0.0 exactly as before.
+
+What is different is how PAIR cleans up. PAIR now keeps a record of the engines
+it installs, so that removing PAIR, or resetting its data, only ever removes
+engines PAIR put there itself. Earlier versions did not keep that record, so
+PAIR treats an LM Studio they installed as one you installed yourself, and
+leaves it in place. **Uninstall** in LM Studio's **Engine settings** says so,
+and **Reset app data** and uninstalling PAIR skip it.
+
+If you are happy to keep LM Studio, you do not need to do anything. If you would
+rather remove it, or have PAIR manage it from now on, follow these steps. They
+keep the models you downloaded.
+
+1. If you also use the LM Studio desktop application, remove LM Studio through
+ that application instead, since it shares the same `.lmstudio` folder.
+2. Quit PAIR, which stops the LM Studio server it started.
+3. Stop LM Studio and delete everything in `.lmstudio` except the `models`
+ folder.
+
+ On macOS or Linux:
+
+ ```bash
+ ~/.lmstudio/bin/lms server stop
+ find ~/.lmstudio -mindepth 1 -maxdepth 1 ! -name models -exec rm -rf {} +
+ ```
+
+ On Windows, in PowerShell:
+
+ ```powershell
+ & "$env:USERPROFILE\.lmstudio\bin\lms.exe" server stop
+ Get-ChildItem "$env:USERPROFILE\.lmstudio" -Force |
+ Where-Object Name -ne 'models' |
+ Remove-Item -Recurse -Force
+ ```
+
+ To remove your downloaded LM Studio models too, delete the whole `.lmstudio`
+ folder instead.
+
+To have PAIR manage LM Studio from now on, install it again from
+**Engine settings** after these steps. PAIR keeps a record of that install, and
+your kept `models` folder is still there for it to use.
+
+## If You Use PAIR from a Web Page or Browser Extension
+
+This applies only to browser-based clients. Command-line tools, IDEs, agents,
+and desktop applications are not affected.
+
+PAIR's local endpoints now use each engine's own browser access setting, known
+as CORS, rather than allowing every website. That means a web page can reach
+your models through PAIR only if you have allowed it in the engine. If a
+browser-based client stopped connecting after the update, add its address in
+the engine's launch options:
+
+| Engine | Setting |
+| --- | --- |
+| Ollama | `OLLAMA_ORIGINS`, for example `OLLAMA_ORIGINS="https://example.com"` |
+| LM Studio | The `--cors` switch |
+| llama.cpp | `--cors-origins` |
+
+Make the change on the machine that runs the engine. Include the address's
+scheme, such as `https://`; a wildcard on its own (`*`) or a bare `localhost`
+is not accepted. If requests can be routed to other machines in your cluster,
+allow the address on each of them. [Engine Settings](engine-settings.mdx) has
+the details.
+
+## Checking Everything Is Working
+
+After updating each machine, you can confirm that **Settings → Service** shows
+the new version, its engines are running in **Overview**, and its paired
+machines are still listed. If anything looks wrong,
+[Troubleshooting](troubleshooting.mdx) can help.
diff --git a/fern/docs.yml b/fern/docs.yml
index 956b988..f3f5896 100644
--- a/fern/docs.yml
+++ b/fern/docs.yml
@@ -28,6 +28,12 @@ navigation:
- page: Getting Started
path: ../docs/getting-started.mdx
slug: getting-started
+ - page: Release Notes
+ path: ../docs/release-notes.mdx
+ slug: release-notes
+ - page: Upgrade Guide
+ path: ../docs/upgrade-guide.mdx
+ slug: upgrade-guide
- page: Managing Engines
path: ../docs/engine-lifecycle.mdx
slug: engine-lifecycle