add qwen3 base and coder

active/device_framework_desktop/framework_desktop.md

@@ -0,0 +1,297 @@
+# Framework Desktop
+
+- [Framework Desktop](#framework-desktop)
+  - [BIOS](#bios)
+  - [References](#references)
+  - [Notes](#notes)
+    - [Volume Locations](#volume-locations)
+  - [Setup](#setup)
+    - [Create the AI user](#create-the-ai-user)
+    - [Helper aliases](#helper-aliases)
+    - [Create the models dir](#create-the-models-dir)
+    - [Install the Hugging Face CLI](#install-the-hugging-face-cli)
+    - [Download models](#download-models)
+      - [Text models](#text-models)
+      - [Image models](#image-models)
+    - [Create the systemd-ai pod](#create-the-systemd-ai-pod)
+  - [llama.cpp](#llamacpp)
+  - [stable-diffusion.cpp](#stable-diffusioncpp)
+  - [open-webui](#open-webui)
+  - [Install the whole thing with quadlets (TM)](#install-the-whole-thing-with-quadlets-tm)
+    - [Install the update script](#install-the-update-script)
+
+## BIOS
+
+<https://knowledgebase.frame.work/en_us/changing-memory-allocation-amd-ryzen-ai-max-300-series-By1LG5Yrll>
+
+1. Set GPU memory to 512MB
+
+## References
+
+<https://docs.podman.io/en/latest/markdown/podman-systemd.unit.5.html>
+
+## Notes
+
+### Volume Locations
+
+`~/.local/share/containers/storage/volumes/`
+
+## Setup
+
+### Create the AI user
+
+```bash
+# Create your local ai user. This will be the user you launch podman processes from.
+useradd -m ai
+loginctl enable-linger ai
+su -l ai
+mkdir -p ~/.config/containers/systemd/
+```
+
+Models are big. You'll want some tools to help find large files quickly when space runs out.
+
+### Helper aliases
+
+Add these to your .bashrc:
+
+```bash
+# Calculate all folder sizes in current dir 
+alias {dudir,dud}='du -h --max-depth 1 | sort -h'
+
+# Calculate all file sizes in current dir
+alias {dufile,duf}='ls -lhSr'
+
+# Restart llama-server / follow logs
+alias llama-reload="systemctl --user daemon-reload && systemctl --user restart llama-server.service"
+alias llama-logs="journalctl --user -fu llama-server"
+
+# Restart stable diffusion gen and edit server / follow logs
+alias sd-gen-reload='systemctl --user daemon-reload && systemctl --user restart stable-diffusion-gen-server'
+alias sd-gen-logs='journalctl --user -xeu stable-diffusion-gen-server'
+alias sd-edit-reload='systemctl --user daemon-reload && systemctl --user restart stable-diffusion-edit-server'
+alias sd-edit-logs='journalctl --user -xeu stable-diffusion-edit-server'
+```
+
+### Create the models dir
+
+```bash
+mkdir -p /home/ai/models/{text,image,video}
+```
+
+### Install the Hugging Face CLI
+
+<https://huggingface.co/docs/huggingface_hub/en/guides/cli#getting-started>
+
+```bash
+# Install
+curl -LsSf https://hf.co/cli/install.sh | bash
+
+# Login
+hf auth login
+```
+
+### Download models
+
+#### Text models
+
+<https://huggingface.co/ggml-org/collections>
+
+```bash
+# gpt-oss-120b
+mkdir /home/ai/models/text/gpt-oss-120b
+hf download --local-dir /home/ai/models/text/gpt-oss-120b ggml-org/gpt-oss-120b-GGUF
+
+# gpt-oss-20b
+mkdir /home/ai/models/text/gpt-oss-20b
+hf download --local-dir /home/ai/models/text/gpt-oss-20b ggml-org/gpt-oss-20b-GGUF
+
+# devstral-2-123b
+mkdir /home/ai/models/text/devstral-2-123b
+hf download --local-dir /home/ai/models/text/devstral-2-123b unsloth/Devstral-2-123B-Instruct-2512-GGUF Q4_K_M/Devstral-2-123B-Instruct-2512-Q4_K_M-00001-of-00002.gguf
+hf download --local-dir /home/ai/models/text/devstral-2-123b unsloth/Devstral-2-123B-Instruct-2512-GGUF Q4_K_M/Devstral-2-123B-Instruct-2512-Q4_K_M-00002-of-00002.gguf
+
+# devstral-small-2-24b
+mkdir /home/ai/models/text/devstral-small-2-24b
+hf download --local-dir /home/ai/models/text/devstral-small-2-24b unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF Devstral-Small-2-24B-Instruct-2512-Q4_K_M.gguf
+
+# ministral-3-14b
+mkdir /home/ai/models/text/ministral-3-14b
+hf download --local-dir /home/ai/models/text/ministral-3-14b ggml-org/Ministral-3-14B-Reasoning-2512-GGUF
+
+# ministral-3-3b-instruct
+mkdir /home/ai/models/text/ministral-3-3b-instruct
+hf download --local-dir /home/ai/models/text/ministral-3-3b-instruct ggml-org/Ministral-3-3B-Instruct-2512-GGUF
+
+# nemotron-nano-30b
+mkdir /home/ai/models/text/nemotron-nano-30b
+hf download --local-dir /home/ai/models/text/nemotron-nano-30b ggml-org/Nemotron-Nano-3-30B-A3B-GGUF Nemotron-Nano-3-30B-A3B-Q4_K_M.gguf
+
+# qwen3-30b-a3b-instruct
+mkdir /home/ai/models/text/qwen3-30b-a3b-instruct
+hf download --local-dir /home/ai/models/text/qwen3-30b-a3b-instruct ggml-org/Qwen3-30B-A3B-Instruct-2507-Q8_0-GGUF
+
+# qwen3-coder-30b-a3b-instruct
+mkdir /home/ai/models/text/qwen3-coder-30b-a3b-instruct
+hf download --local-dir /home/ai/models/text/qwen3-coder-30b-a3b-instruct ggml-org/Qwen3-Coder-30B-A3B-Instruct-Q8_0-GGUF
+```
+
+#### Image models
+
+```bash
+# z-turbo
+mkdir /home/ai/models/image/z-turbo
+hf download --local-dir /home/ai/models/image/z-turbo QuantStack/FLUX.1-Kontext-dev-GGUF flux1-kontext-dev-Q4_K_M.gguf
+hf download --local-dir /home/ai/models/image/z-turbo black-forest-labs/FLUX.1-schnell ae.safetensors
+hf download --local-dir /home/ai/models/image/z-turbo unsloth/Qwen3-4B-Instruct-2507-GGUF Qwen3-4B-Instruct-2507-Q4_K_M.gguf
+
+# flux-1-kontext
+mkdir /home/ai/models/image/flux-1-kontext
+hf download --local-dir /home/ai/models/image/flux-1-kontext leejet/Z-Image-Turbo-GGUF z_image_turbo-Q4_K.gguf
+hf download --local-dir /home/ai/models/image/flux-1-kontext black-forest-labs/FLUX.1-dev ae.safetensors
+hf download --local-dir /home/ai/models/image/flux-1-kontext comfyanonymous/flux_text_encoders clip_l.safetensors
+hf download --local-dir /home/ai/models/image/flux-1-kontext comfyanonymous/flux_text_encoders t5xxl_fp16.safetensors
+```
+
+### Create the systemd-ai pod
+
+You'll at least want the ai pod and network. Copy `ai.pod` and `ai.network` out
+of `quadlets` into `~/.config/containers/systemd`.
+
+Then run `systemctl --user daemon-reload && systemctl --user start ai-pod`
+
+## llama.cpp
+
+<https://github.com/ggml-org/llama.cpp/tree/master/tools/server>
+
+```bash
+# Build the llama.cpp container image
+git clone https://github.com/ggml-org/llama.cpp.git
+cd llama.cpp
+export BUILD_TAG=$(date +"%Y-%m-%d-%H-%M-%S")
+
+# Vulkan
+podman build -f .devops/vulkan.Dockerfile -t llama-cpp-vulkan:${BUILD_TAG} -t llama-cpp-vulkan:latest .
+
+# Run llama server (Available on port 8000)
+# Add `--n-cpu-moe 32` to gpt-oss-120b to keep minimal number of expert in GPU
+podman run \
+--rm \
+--name llama-server-demo \
+--pod systemd-ai \
+--device=/dev/kfd \
+--device=/dev/dri \
+-v /home/ai/models/text:/models:z \
+localhost/llama-cpp-vulkan:latest \
+--port 8000 \
+-c 64000 \
+-b 64000 \
+-ub 500 \
+--perf \
+--n-gpu-layers all \
+--jinja \
+--models-max 1 \
+--models-dir /models
+```
+
+## stable-diffusion.cpp
+
+Server: <https://github.com/leejet/stable-diffusion.cpp/tree/master/examples/server>
+
+CLI: <https://github.com/leejet/stable-diffusion.cpp/tree/master/examples/cli>
+
+```bash
+git clone https://github.com/leejet/stable-diffusion.cpp.git
+cd stable-diffusion.cpp
+git submodule update --init --recursive
+export BUILD_TAG=$(date +"%Y-%m-%d-%H-%M-%S")
+
+# Vulkan
+podman build -f Dockerfile.vulkan -t stable-diffusion-cpp:${BUILD_TAG} -t stable-diffusion-cpp:latest .
+```
+
+```bash
+# z-turbo
+podman run --rm \
+-v /home/ai/models:/models:z \
+-v /home/ai/output:/output:z \
+--device /dev/kfd \
+--device /dev/dri \
+localhost/stable-diffusion-cpp:latest \
+--diffusion-model /models/image/z-turbo/z_image_turbo-Q4_K.gguf \
+--vae /models/image/z-turbo/ae.safetensors  \
+--llm /models/image/z-turbo/Qwen3-4B-Instruct-2507-Q4_K_M.gguf \
+--cfg-scale 1.0 \
+-v \
+-H 1024 \
+-W 1024 \
+--seed -1 \
+--steps 8 \
+--vae-conv-direct \
+-o /output/output.png \
+-p "A photorealistic dragon"
+
+# Edit with flux kontext
+podman run --rm \
+-v /home/ai/models:/models:z \
+-v /home/ai/output:/output:z \
+--device /dev/kfd \
+--device /dev/dri \
+localhost/stable-diffusion-cpp:latest \
+--diffusion-model /models/image/flux-1-kontext/flux1-kontext-dev-Q4_K_M.gguf \
+--vae /models/image/flux-1-kontext/ae.safetensors \
+--clip_l /models/image/flux-1-kontext/clip_l.safetensors \
+--t5xxl /models/image/flux-1-kontext/t5xxl_fp16.safetensors \
+--cfg-scale 1.0 \
+--sampling-method euler \
+--seed -1 \
+--steps 28 \
+--vae-conv-direct \
+-v \
+-H 512 \
+-W 512 \
+-o /output/output.png \
+-r /output/everquest_logo.png \
+-p "Add the text 'EverQuest'"
+```
+
+## open-webui
+
+```bash
+mkdir /home/ai/.env
+# Create a file called open-webui-env with `WEBUI_SECRET_KEY="some-random-key"
+scp active/device_framework_desktop/secrets/open-webui-env deskwork-ai:.env/
+
+# Will be available on port 8080
+podman run \
+-d \
+--pod ai \
+-v open-webui:/app/backend/data \
+--name open-webui \
+--restart always \
+ghcr.io/open-webui/open-webui:main
+```
+
+## Install the whole thing with quadlets (TM)
+
+```bash
+# Installs and runs all services in `quadlets/`
+scp -r active/device_framework_desktop/quadlets/* deskwork-ai:.config/containers/systemd/
+ssh deskwork-ai
+systemctl --user daemon-reload
+systemctl --user restart ai-pod.service
+```
+
+Note, all services will be available at `host.containers.internal`. So llama.cpp
+will be up at `http://host.containers.internal:8000`.
+
+### Install the update script
+
+```bash
+# 1. Builds the latest llama.cpp and stable-diffusion.cpp
+# 2. Pulls the latest open-webui
+# 3. Restarts all services
+scp active/device_framework_desktop/update-script.sh deskwork:
+ssh deskwork-ai
+chmod +x update-script.sh
+./update-script.sh
+```

active/device_framework_desktop/quadlets/ai.network

@@ -0,0 +1,2 @@
+[Network]
+IPv6=true

active/device_framework_desktop/quadlets/ai.pod

@@ -0,0 +1,8 @@
+[Pod]
+Network=ai.network
+# llama.cpp
+PublishPort=8000:8000/tcp
+# open-webui
+PublishPort=8080:8080/tcp
+# stable-diffusion.cpp
+PublishPort=1234:1234/tcp

active/device_framework_desktop/quadlets/llama-server.container

@@ -0,0 +1,44 @@
+[Unit]
+Description=A Llama CPP Server Running GPT OSS 120b
+
+[Container]
+# Shared AI pod
+Pod=ai.pod
+
+# Image is built locally via podman build
+Image=localhost/llama-cpp-vulkan:latest
+
+# Downloaded models volume
+Volume=/home/ai/models/text:/models:z
+
+# GPU Device
+AddDevice=/dev/kfd
+AddDevice=/dev/dri
+
+# Server command
+Exec=--port 8000 \
+    -c 48000 \
+    -b 48000 \
+    -ub 500 \
+    --perf \
+    --n-gpu-layers all \
+    --jinja \
+    --models-max 1 \
+    --models-dir /models
+
+# Health Check
+HealthCmd=CMD-SHELL curl --fail http://127.0.0.1:8000/props?model=gpt-oss-120b || exit 1
+HealthInterval=10s
+HealthRetries=3
+HealthStartPeriod=10s
+HealthTimeout=30s
+HealthOnFailure=kill
+
+[Service]
+Restart=always
+# Extend Timeout to allow time to pull the image
+TimeoutStartSec=900
+
+[Install]
+# Start by default on boot
+WantedBy=multi-user.target default.target

active/device_framework_desktop/quadlets/open-webui.container

@@ -0,0 +1,24 @@
+[Unit]
+Description=An Open Webui Frontend for Local AI Services
+
+[Container]
+# Shared AI pod
+Pod=ai.pod
+
+# Open Webui base image
+Image=ghcr.io/open-webui/open-webui:main
+
+# Nothing too complicated here. Open Webui will basically configure itself.
+Volume=open-webui-data:/app/backend/data
+
+# WEBUI_SECRET_KEY is required to prevent logout on Restart
+EnvironmentFile=/home/ai/.env/open-webui-env
+
+[Service]
+Restart=always
+# Extend Timeout to allow time to pull the image
+TimeoutStartSec=900
+
+[Install]
+# Start by default on boot
+WantedBy=multi-user.target default.target

active/device_framework_desktop/quadlets/stable-diffusion-edit-server.container

@@ -0,0 +1,42 @@
+[Unit]
+Description=A Stable Diffusion CPP Server for Editing Images
+
+[Container]
+# Shared AI pod
+Pod=ai.pod
+
+# Vulkan image for AMD GPU
+Image=localhost/stable-diffusion-cpp:latest
+
+# Shared models directory
+Volume=/home/ai/models:/models:z
+
+# GPU Device
+AddDevice=/dev/kfd
+AddDevice=/dev/dri
+
+# Override entrypoint to use server
+Entrypoint=/sd-server
+
+# Server args
+Exec=-l 0.0.0.0 \
+    --listen-port 1235 \
+    --diffusion-model /models/image/flux-1-kontext/flux1-kontext-dev-Q4_K_M.gguf \
+    --vae /models/image/flux-1-kontext/ae.safetensors \
+    --clip_l /models/image/flux-1-kontext/clip_l.safetensors \
+    --t5xxl /models/image/flux-1-kontext/t5xxl_fp16.safetensors \
+    --cfg-scale 1.0 \
+    --sampling-method euler \
+    --vae-conv-direct \
+    --seed -1 \
+    --steps 28 \
+    -v
+
+[Service]
+Restart=always
+# Extend Timeout to allow time to pull the image
+TimeoutStartSec=900
+
+[Install]
+# Start by default on boot
+WantedBy=multi-user.target default.target

active/device_framework_desktop/quadlets/stable-diffusion-gen-server.container

@@ -0,0 +1,42 @@
+[Unit]
+Description=A Stable Diffusion CPP Server for Generating Images
+
+[Container]
+# Shared AI pod
+Pod=ai.pod
+
+# Vulkan image for AMD GPU
+Image=localhost/stable-diffusion-cpp:latest
+
+# Shared models directory
+Volume=/home/ai/models:/models:z
+
+# GPU Device
+AddDevice=/dev/kfd
+AddDevice=/dev/dri
+
+# Override entrypoint to use server
+Entrypoint=/sd-server
+
+# Server args
+Exec=-l 0.0.0.0 \
+    --listen-port 1234 \
+    --diffusion-model /models/image/z-turbo/z_image_turbo-Q4_K.gguf \
+    --vae /models/image/z-turbo/ae.safetensors  \
+    --llm /models/image/z-turbo/qwen_3_4b.safetensors \
+    -l 0.0.0.0 \
+    --listen-port 1234 \
+    --cfg-scale 1.0 \
+    --vae-conv-direct \
+    -v \
+    --seed -1 \
+    --steps 8
+
+[Service]
+Restart=always
+# Extend Timeout to allow time to pull the image
+TimeoutStartSec=900
+
+[Install]
+# Start by default on boot
+WantedBy=multi-user.target default.target

active/device_framework_desktop/update-script.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+
+set -x
+
+export BUILD_TAG=$(date +"%Y-%m-%d-%H-%M-%S")
+
+echo "Updates stable-diffusion.cpp, llama.cpp, and open-webui"
+
+cd /home/ai/llama.cpp
+git pull
+podman build -t llama-cpp-vulkan:${BUILD_TAG} -t llama-cpp-vulkan:latest -f .devops/vulkan.Dockerfile .
+
+cd /home/ai/stable-diffusion.cpp
+git pull
+git submodule update --init --recursive
+podman build -f Dockerfile.vulkan -t stable-diffusion-cpp:${BUILD_TAG} -t stable-diffusion-cpp:latest .
+
+podman image pull ghcr.io/open-webui/open-webui:main
+
+systemctl --user restart ai-pod

active/software_osbuild/fedora43-base.toml

@@ -9,16 +9,11 @@ groups = []
 hostname = "f43-base"
 
 [[customizations.disk.partitions]]
-type = "btrfs"
+type = "plain"
-minsize = "32 GiB"
+label = "root"
-
-[[customizations.disk.partitions.subvolumes]]
-name = "root"
 mountpoint = "/"
-
+fs_type = "ext4"
-[[customizations.disk.partitions.subvolumes]]
+minsize = "128 GiB"
-name = "home"
-mountpoint = "/home"
 
 [customizations.timezone]
 timezone = "America/New_York"
@@ -70,8 +65,8 @@ data = """
 [[customizations.files]]
 path = "/home/ducoterra/.inputrc"
 mode = "0644"
-user = "root"
+user = "ducoterra"
-group = "root"
+group = "ducoterra"
 data = """
 "\\C-h": backward-kill-word
 """

active/software_osbuild/image_builder.md

@@ -33,18 +33,21 @@ sudo usermod -aG weldr $USER
 
 # Optional: cockpit dependency
 dnf install -y cockpit-composer
+
+# Optional: allow security profiles
+dnf install openscap-scanner scap-security-guide
 ```
 
 ## Building Images
 
 1. Create a toml file describing your image
 
-    See `fedora-42-base.toml` for an example.
+    See `fedora42-base.toml` for an example.
 
 2. Push the toml to composer
 
     ```bash
-    composer-cli blueprints push active/software_osbuild/fedora-42-base.toml
+    composer-cli blueprints push active/software_osbuild/fedora42-base.toml
     
     # List blueprints
     composer-cli blueprints list
@@ -57,13 +60,13 @@ dnf install -y cockpit-composer
     composer-cli compose types
 
     # Build the image
-    composer-cli compose start fedora-42-base qcow2
+    composer-cli compose start fedora42-base qcow2
 
     # Check status
     watch composer-cli compose status
 
     # Download logs if error
-    cd /tmp && composer-cli compose logs f91a12b6-01fd-4f94-91cc-9d5fb68b8129
+    cd /tmp && composer-cli compose logs 52963ac9-b680-4def-baaf-252845f0e3fe
 
     # Delete failed images
     composer-cli compose list failed -j | jq '.[].body.failed.[]?.id' | xargs -I '%' composer-cli compose delete '%'
@@ -79,16 +82,25 @@ dnf install -y cockpit-composer
     composer-cli compose list finished
 
     # Download the image
-    composer-cli compose image --filename /var/lib/libvirt/images/fedora-42-base.qcow2 image-uuid
+    composer-cli compose image --filename active/software_osbuild/secrets/fedora43-base.qcow2 image-uuid
 
     # Test with qemu
-    qemu-kvm --name test-fedora-42-base -m 4096 -hda ~/Downloads/fedora-42-base.qcow2
+    virt-install \
+    --name "fedora43-base" \
+    --boot uefi,firmware.feature0.name=secure-boot,firmware.feature0.enabled=no \
+    --cpu host-passthrough --vcpus sockets=1,cores=8,threads=2 \
+    --ram=8192 \
+    --os-variant=fedora41 \
+    --network bridge:virbr0 \
+    --graphics none \
+    --console pty,target.type=virtio \
+    --import --disk "path=active/software_osbuild/secrets/fedora43-base.qcow2,bus=virtio"
     ```
 
 ### Image Build and Watch One Liner
 
 ```bash
-composer-cli blueprints push active/software_osbuild/fedora-43-base.toml && \
+composer-cli blueprints push active/software_osbuild/fedora43-base.toml && \
-composer-cli compose start fedora-43-base qcow2 && \
+composer-cli compose start fedora43-base qcow2 && \
 watch composer-cli compose status
 ```