Skip to content

Enabling Lemonade related playbooks on Radeon dGPU #433

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
danielholanda merged 9 commits into from
Jun 30, 2026
Merged

Enabling Lemonade related playbooks on Radeon dGPU #433

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
ccc56ca
Enabling Lemonade related playbooks on Radeon dGPU
sreeram-11 Jun 23, 2026
4ee2784
Added rx7900xt and rx9070xt to min system memory note
sreeram-11 Jun 25, 2026
526af95
Adding r9700
sreeram-11 Jun 27, 2026
d3a4017
Merge branch 'main' into sreeram/radeon-lemonade
sreeram-11 Jun 27, 2026
9a6346b
Updating Radeon dGPUs to use Qwen3.5-4B-GGUF on both Windows and Linu…
sreeram-11 Jun 28, 2026
1581416
Removing Radeon devices from Open WebUI
sreeram-11 Jun 29, 2026
326678f
Merge branch 'main' into sreeram/radeon-lemonade
sreeram-11 Jun 29, 2026
76cce82
Added device tags for the NPU and Hybrid part
sreeram-11 Jun 30, 2026
df3e4a1
Merge branch 'sreeram/radeon-lemonade' of https://github.com/amd/play…
sreeram-11 Jun 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions playbooks/dependencies/gaia.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ pip install amd-gaia
<!-- @device:end -->


<!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
<!-- @device:halo,stx,krk,rx7900xt,rx9070xt,r9700 -->
<!-- @os:windows -->
1. On Windows, open a terminal in the directory of your choice and follow the commands to create a venv.
<!-- @test:id=create-venv-windows timeout=60 -->
Expand Down Expand Up @@ -113,7 +113,7 @@ sudo apt install -y pciutils
fi

command -v lspci >/dev/null 2>&1
lspci | head -n 5
lspci | head -n 5 || true
echo "OK: lspci is available"
```
<!-- @test:end -->
Expand Down
88 changes: 68 additions & 20 deletions playbooks/supplemental/gaia-agents/playbook.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,11 @@
"description": "Build a 100% local AI agent \u2014 no cloud APIs needed. Use the GAIA SDK to create a hardware advisor on your AMD Ryzen\u2122 AI",
"time": 15,
"supported_platforms": {
"halo": [
"halo_box": [
"linux",
"windows"
],
"halo_box": [
"halo": [
"linux",
"windows"
],
Expand All @@ -19,26 +19,50 @@
"krk": [
"linux",
"windows"
],
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"tested_platforms": {
"halo": [
"windows",
"linux"
"linux",
"windows"
],
"stx": [
"windows",
"linux"
"linux",
"windows"
],
"krk": [
"windows",
"linux"
"linux",
"windows"
],
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"required_platforms": {
"halo": [
"windows",
"linux"
"linux",
"windows"
],
"stx": [
"linux",
Expand All @@ -47,24 +71,48 @@
"krk": [
"linux",
"windows"
],
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"published_platforms": {
"halo": [
"windows",
"linux"
],
"halo_box": [
"windows",
"linux"
"linux",
"windows"
],
"halo": [
"linux",
"windows"
],
"stx": [
"windows",
"linux"
"linux",
"windows"
],
"krk": [
"windows",
"linux"
"linux",
"windows"
],
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"difficulty": "beginner",
Expand Down
12 changes: 10 additions & 2 deletions playbooks/supplemental/lemonade-getting-started/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -520,6 +520,7 @@ These same patterns scale to any application such as chatbots, code assistants,

---

<!-- @device:halo_box,halo,stx,krk -->
## Running Models on the NPU (Optional)

If you have a Ryzen AI 300/400/Max 300 series or Z2 Extreme, your device has a built-in **Neural Processing Unit (NPU)**, a dedicated chip designed specifically for AI workloads. Running models on the NPU is more power-efficient than using the GPU, which makes it ideal for background AI tasks, longer sessions, and battery-powered use.
Expand Down Expand Up @@ -562,8 +563,10 @@ To enable `FastFlowLM` on Windows:
* Click Install NPU.
* Once installation is complete, ~36 defaults models will be available under the FFLM dropdown menu.
<!-- @os:end -->
<!-- @device:end -->

<!-- @os:linux -->
<!-- @device:halo_box,halo,stx,krk -->
When the `Lemonade` App is launched for the first time, the `FastFlowNPU` backend is not enabled by default.
The local app will open the installation page to guide you through setup.

Expand All @@ -572,7 +575,9 @@ To enable `FastFlowLM` on Linux:
* Open the `Lemonade` App.
* Visit the [official FLM](https://lemonade-server.ai/flm_npu_linux.html) documentation and follow the installation steps for FLM by selecting your Linux distribution.
* Enable backports as instructed on the installation page.
* Download the latest `v0.9.x` release from the [tags page](https://github.com/FastFlowLM/FastFlowLM/tags).
* Download the latest `v0.9.x` release from the [tags page](https://github.com/FastFlowLM/FastFlowLM/tags).'
<!-- @device:end -->

<!-- @device:halo_box -->
>[!Note]
For AMD Halo Developer Platform, make sure to choose Debian 13.
Expand All @@ -581,16 +586,18 @@ fastflowlm_0.9.X_debian13_amd64.deb
```
<!-- @device:end -->

<!-- @device:halo,sx,krk,rx7900xt,rx9070xt -->
<!-- @device:halo,stx,krk -->
```
fastflowlm_0.9.X_ubuntuY.Z_amd64.deb
```
<!-- @device:end -->
* Install the downloaded `.deb` package.
* Recommended: Quit the `Lemonade App` and open it again so the changes are detected.
* Recommended: Open `Backends Manager` and click Install `FastFlowNPU` Backend.
<!-- @device:end -->
<!-- @os:end -->

<!-- @device:halo_box,halo,stx,krk -->
After a successful installation, you should see that `flm:npu` completed in the **Download Manager** inside the **Lemonade Desktop App**.
<p align="center">
<img width="400" height="400" src="assets/FFLM-installationWizard.png" />
Expand Down Expand Up @@ -628,6 +635,7 @@ response = client.chat.completions.create(
messages=messages,
)
```
<!-- @device:end -->

## Next Steps

Expand Down
70 changes: 59 additions & 11 deletions playbooks/supplemental/lemonade-getting-started/playbook.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,11 @@
"description": "Learn to run Gen AI models locally with Lemonade, an open-source local AI server.",
"time": 30,
"supported_platforms": {
"halo": [
"halo_box": [
"linux",
"windows"
],
"halo_box": [
"halo": [
"linux",
"windows"
],
Expand All @@ -19,12 +19,24 @@
"krk": [
"linux",
"windows"
],
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"tested_platforms": {
"halo": [
"windows",
"linux"
"linux",
"windows"
],
"stx": [
"linux",
Expand All @@ -33,12 +45,24 @@
"krk": [
"linux",
"windows"
],
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"required_platforms": {
"halo": [
"windows",
"linux"
"linux",
"windows"
],
"stx": [
"linux",
Expand All @@ -47,12 +71,28 @@
"krk": [
"linux",
"windows"
],
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"published_platforms": {
"halo_box": [
"linux",
"windows"
],
"halo": [
"windows",
"linux"
"linux",
"windows"
],
"stx": [
"linux",
Expand All @@ -62,9 +102,17 @@
"linux",
"windows"
],
"halo_box": [
"windows",
"linux"
"rx7900xt": [
"linux",
"windows"
],
"rx9070xt": [
"linux",
"windows"
],
"r9700": [
"linux",
"windows"
]
},
"difficulty": "beginner",
Expand Down
Loading
Loading