transition to container_ over podman_

2026-02-16 10:44:38 -05:00
parent d4fbbb185f
commit 52c6dac263
39 changed files with 1038 additions and 159 deletions
--- a/active/device_framework_desktop/framework_desktop.md
+++ b/active/device_framework_desktop/framework_desktop.md
@@ -35,7 +35,7 @@
  - [VLLM](#vllm)
  - [Install the whole thing with quadlets (TM)](#install-the-whole-thing-with-quadlets-tm)
    - [Install the update script](#install-the-update-script)
-  - [Voice Cloning](#voice-cloning)
+  - [Install Guest Open Webui with Start/Stop Services](#install-guest-open-webui-with-startstop-services)

 ## BIOS

@@ -208,7 +208,7 @@ hf download --local-dir /home/ai/models/text/qwen3-coder-30b-a3b-instruct ggml-o

 # qwen3-coder-next
 mkdir /home/ai/models/text/qwen3-coder-next
-hf download --local-dir /home/ai/models/text/qwen3-coder-next --include "unsloth/Qwen3-Coder-Next-GGUF Q5_K_M/*.gguf"
+hf download --local-dir /home/ai/models/text/qwen3-coder-next unsloth/Qwen3-Coder-Next-GGUF --include " 5_K_M/*.gguf"

 # qwen3-vl-30b-thinking
 mkdir /home/ai/models/text/qwen3-vl-30b-thinking
@@ -223,6 +223,10 @@ hf download --local-dir /home/ai/models/text/qwen3-vl-8b-instruct Qwen/Qwen3-VL-
 # qwen3-4b-2507-abliterated
 mkdir /home/ai/models/text/qwen3-4b-2507-abliterated
 hf download --local-dir /home/ai/models/text/qwen3-4b-2507-abliterated prithivMLmods/Qwen3-4B-2507-abliterated-GGUF Qwen3-4B-Thinking-2507-abliterated-GGUF/Qwen3-4B-Thinking-2507-abliterated.Q4_K_M.gguf
+
+# qwen3-48b-a4b-abliterated
+mkdir /home/ai/models/text/qwen3-48b-a4b-abliterated
+hf download --local-dir /home/ai/models/text/qwen3-48b-a4b-abliterated DavidAU/Qwen3-48B-A4B-Savant-Commander-Distill-12X-Closed-Open-Heretic-Uncensored-GGUF Qwen3-48B-A4B-Savant-Commander-Dstll-12X-Cl-Op-Hrtic-Uncen-Q4_K_M.gguf
 ```

 ##### GLM
@@ -231,6 +235,16 @@ hf download --local-dir /home/ai/models/text/qwen3-4b-2507-abliterated prithivML
 # glm-4.7-flash-30b
 mkdir /home/ai/models/text/glm-4.7-flash-30b
 hf download --local-dir /home/ai/models/text/glm-4.7-flash-30b unsloth/GLM-4.7-Flash-GGUF GLM-4.7-Flash-Q4_K_M.gguf
+
+# glm-4.6v
+mkdir /home/ai/models/text/glm-4.6v
+hf download --local-dir /home/ai/models/text/glm-4.6v unsloth/GLM-4.6V-GGUF --include "Q4_K_M/*.gguf"
+hf download --local-dir /home/ai/models/text/glm-4.6v unsloth/GLM-4.6V-GGUF mmproj-F16.gguf
+
+# glm-4.6v-flash
+mkdir /home/ai/models/text/glm-4.6v-flash
+hf download --local-dir /home/ai/models/text/glm-4.6v-flash unsloth/GLM-4.6V-Flash-GGUF GLM-4.6V-Flash-Q4_K_M.gguf
+hf download --local-dir /home/ai/models/text/glm-4.6v-flash unsloth/GLM-4.6V-Flash-GGUF mmproj-F16.gguf
 ```

 ##### Llama
@@ -556,4 +570,12 @@ chmod +x update-script.sh
 ./update-script.sh
 ```

-## Voice Cloning
+## Install Guest Open Webui with Start/Stop Services
+
+```bash
+scp -r active/device_framework_desktop/systemd/. deskwork-ai:.config/systemd/user/
+ssh deskwork-ai
+systemctl --user daemon-reload
+systemctl --user enable open-webui-guest-start.timer
+systemctl --user enable open-webui-guest-stop.timer
+```
--- a/active/device_framework_desktop/quadlets/stable-diffusion-edit-server.container
+++ b/active/device_framework_desktop/quadlets/stable-diffusion-edit-server.container
@@ -24,11 +24,14 @@ Exec=-l 0.0.0.0 \
    --diffusion-model /models/image/flux2-klein/flux-2-klein-9b-Q4_0.gguf \
    --vae /models/image/flux2-klein/ae.safetensors \
    --llm /models/image/flux2-klein/Qwen3-8B-Q4_K_M.gguf \
+    -v \
    --cfg-scale 1.0 \
    --sampling-method euler \
-    -v \
-    --steps 4 \
-    --vae-conv-direct
+    --vae-conv-direct \
+    --offload-to-cpu \
+    --diffusion-conv-direct \
+    --seed -1 \
+    --steps 5

 [Service]
 Restart=always
--- a/active/device_framework_desktop/quadlets/stable-diffusion-gen-server.container
+++ b/active/device_framework_desktop/quadlets/stable-diffusion-gen-server.container
@@ -24,9 +24,9 @@ Exec=-l 0.0.0.0 \
    --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 \
+    -v \
    --cfg-scale 1.0 \
    --vae-conv-direct \
-    -v \
    --seed -1 \
    --steps 8

--- a/active/device_framework_desktop/quadlets_beta/open-webui-guest.container
+++ b/active/device_framework_desktop/quadlets_beta/open-webui-guest.container
@@ -0,0 +1,32 @@
+[Unit]
+Description=An Open Webui Frontend for Local AI Services for Guests
+
+[Container]
+# Shared AI external pod
+Pod=ai-external.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-guest:/app/backend/data
+
+# WEBUI_SECRET_KEY is required to prevent logout on Restart
+EnvironmentFile=/home/ai/.env/open-webui-env-guest
+
+# ai-external is the primary network
+Network=ai-external.network
+Network=ai-internal.network
+
+# open-webui
+PublishPort=8081:8081/tcp
+
+[Service]
+Restart=on-failure
+RestartSec=5
+# Extend Timeout to allow time to pull the image
+TimeoutStartSec=900
+
+[Install]
+# Start by default on boot
+WantedBy=multi-user.target default.target
--- a/active/device_framework_desktop/quadlets_beta/stable-diffusion-edit-server.container
+++ b/active/device_framework_desktop/quadlets_beta/stable-diffusion-edit-server.container
@@ -1,42 +0,0 @@
-[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
--- a/active/device_framework_desktop/systemd/open-webui-guest-start.service
+++ b/active/device_framework_desktop/systemd/open-webui-guest-start.service
@@ -0,0 +1,8 @@
+[Unit]
+Description=Start open-webui-guest on schedule
+Wants=open-webui-guest.service
+After=open-webui-guest.service
+
+[Service]
+Type=oneshot
+ExecStart=/bin/systemctl --user start open-webui-guest.service
--- a/active/device_framework_desktop/systemd/open-webui-guest-start.timer
+++ b/active/device_framework_desktop/systemd/open-webui-guest-start.timer
@@ -0,0 +1,10 @@
+[Unit]
+Description=Timer to start open-webui-guest at 08:00 Mon‑Fri
+
+[Timer]
+OnCalendar=Mon..Fri *-*-* 08:00:00
+Persistent=true
+Unit=open-webui-guest-start.service
+
+[Install]
+WantedBy=timers.target
--- a/active/device_framework_desktop/systemd/open-webui-guest-stop.service
+++ b/active/device_framework_desktop/systemd/open-webui-guest-stop.service
@@ -0,0 +1,7 @@
+[Unit]
+Description=Stop open-webui-guest on schedule
+After=open-webui-guest.service
+
+[Service]
+Type=oneshot
+ExecStart=/bin/systemctl --user stop open-webui-guest.service
--- a/active/device_framework_desktop/systemd/open-webui-guest-stop.timer
+++ b/active/device_framework_desktop/systemd/open-webui-guest-stop.timer
@@ -0,0 +1,10 @@
+[Unit]
+Description=Timer to stop open-webui-guest at 18:00 Mon‑Fri
+
+[Timer]
+OnCalendar=Mon..Fri *-*-* 18:00:00
+Persistent=true
+Unit=open-webui-guest-stop.service
+
+[Install]
+WantedBy=timers.target