update ai stack with turbo

active/software_ai_stack/ai-internal.pod

@@ -6,7 +6,7 @@ PublishPort=8000:8000/tcp
 PublishPort=8001:8001/tcp
 # llama.cpp instruct
 PublishPort=8002:8002/tcp
-# llama.cpp code
+# llama.cpp tool
 PublishPort=8003:8003/tcp
 # stable-diffusion.cpp gen
 PublishPort=1234:1234/tcp

active/software_ai_stack/ai_stack.md

@@ -31,7 +31,10 @@
         - [Nomic Embedding](#nomic-embedding)
   - [llama.cpp](#llamacpp)
   - [stable-diffusion.cpp](#stable-diffusioncpp)
+  - [STT whisper.cpp](#stt-whispercpp)
+  - [TTS coqui-tts](#tts-coqui-tts)
   - [open-webui](#open-webui)
+    - [Upgrade Open Webui](#upgrade-open-webui)
   - [lite-llm](#lite-llm)
   - [Install Services with Quadlets](#install-services-with-quadlets)
     - [API Keys](#api-keys)
@@ -526,6 +529,28 @@ localhost/stable-diffusion-cpp:latest \
 -p "A normal business meeting. People discuss business for 2 seconds. Suddenly, a horde of furries carrying assault rifles bursts into the room and causes a panic. Hatsune Miku leads the charge screaming in rage."
 ```
 
+## STT whisper.cpp
+
+Whisper stt service.
+
+```bash
+podman run -it --rm -p "8081:8080" \
+-v /home/ai/models/stt:/models:z \
+--device /dev/kfd \
+--device /dev/dri \
+ghcr.io/ggml-org/whisper.cpp:main-vulkan \
+"whisper-server \
+--host 0.0.0.0 \
+-m /models/ggml-large-v3-turbo/ggml-large-v3-turbo-q5_0.bin \
+--convert"
+```
+
+## TTS coqui-tts
+
+```bash
+podman run --rm -it -p 5002:5002 --entrypoint /bin/bash ghcr.io/coqui-ai/tts-cpu
+```
+
 ## open-webui
 
 ```bash
@@ -552,6 +577,13 @@ Use the following connections:
 | stable-diffusion.cpp      | <http://host.containers.internal:1234/v1> |
 | stable-diffusion.cpp edit | <http://host.containers.internal:1235/v1> |
 
+### Upgrade Open Webui
+
+```bash
+podman image pull ghcr.io/open-webui/open-webui:main
+systemctl --user restart open-webui.service
+```
+
 ## lite-llm
 
 <https://docs.litellm.ai/docs/proxy/configs>

active/software_ai_stack/install_ai_instruct_stack.yaml

@@ -15,7 +15,7 @@
         - ai-internal.pod
         - llama-embed.container
         - llama-instruct.container
-        - llama-code.container
+        - llama-tool.container
     - name: Reload and start the ai-internal-pod service
       ansible.builtin.systemd_service:
         state: restarted

active/software_ai_stack/install_ai_turbo_stack.yaml

@@ -13,7 +13,7 @@
       loop:
         - ai-internal.network
         - ai-internal.pod
-        - llama-think.container
+        - llama-turbo.container
     - name: Reload and start the ai-internal-pod service
       ansible.builtin.systemd_service:
         state: restarted

active/software_ai_stack/llama-embed.container

@@ -33,7 +33,8 @@ HealthRetries=3
 HealthStartPeriod=10s
 HealthTimeout=30s
 HealthOnFailure=kill
-EnvironmentFile=/home/ai/.llama-api/keys.env
+
+# EnvironmentFile=/home/ai/.llama-api/keys.env
 
 [Service]
 Restart=always

active/software_ai_stack/llama-instruct.container

@@ -21,17 +21,17 @@ Exec=--port 8002 \
     -n 32768 \
     --temp 0.7 \
     --top-p 0.8 \
-    --min-p 0.0 \
     --top-k 20 \
-    --repeat-penalty 1.0 \
     --presence-penalty 1.5 \
-    --reasoning-budget 0 \
+    --min-p 0.00 \
     --perf \
     --n-gpu-layers all \
+    -fa on \
+    --spec-type draft-mtp --spec-draft-n-max 2 \
     --jinja \
-    -m /models/qwen3.6-35b-a3b/Qwen3.6-35B-A3B-UD-Q5_K_M.gguf \
+    --chat-template-kwargs '{"preserve_thinking": false, "enable_thinking": false}' \
-    --mmproj /models/qwen3.6-35b-a3b/mmproj-F16.gguf \
+    -m /models/qwen3.6-35b-a3b-mtp/Qwen3.6-35B-A3B-UD-Q5_K_M.gguf \
-    --chat-template-kwargs '{"enable_thinking": false}' \
+    --mmproj /models/qwen3.6-35b-a3b-mtp/mmproj-F16.gguf \
     --alias instruct
 
 # Health Check
@@ -41,7 +41,8 @@ HealthRetries=3
 HealthStartPeriod=10s
 HealthTimeout=30s
 HealthOnFailure=kill
-EnvironmentFile=/home/ai/.llama-api/keys.env
+
+# EnvironmentFile=/home/ai/.llama-api/keys.env
 
 [Service]
 Restart=always

active/software_ai_stack/llama-tool.container

@@ -1,11 +1,13 @@
 [Unit]
-Description=A Llama CPP Server Running a Coding Model
+Description=A Llama CPP Server Running a Reasoning Model
 
 [Container]
 # Shared AI internal pod without internet access
 Pod=ai-internal.pod
 
 # Image is built locally via podman build
+# latest-mtp is for mtp testing
+# latest is main branch
 Image=localhost/llama-cpp-vulkan:latest
 
 # Downloaded models volume
@@ -17,17 +19,25 @@ AddDevice=/dev/dri
 
 # Server command
 Exec=--port 8003 \
-    -c 256000 \
+    -c 262144 \
-    -n 65536 \
+    -n 32768 \
-    --temp 0.7 \
+    --temp 0.6 \
-    --top-p 0.8 \
+    --top-p 0.95 \
     --top-k 20 \
-    --repeat-penalty 1.05 \
+    --min-p 0.0 \
+    --presence-penalty 0.0 \
+    --repeat-penalty 1.0 \
+    --reasoning-budget 4096 \
     --perf \
     --n-gpu-layers all \
+    -fa on \
+    --spec-type draft-mtp --spec-draft-n-max 2 \
     --jinja \
-    -m /models/qwen3-coder-30b-a3b/Qwen3-Coder-30B-A3B-Instruct-Q5_K_M.gguf \
+    --chat-template-kwargs '{"preserve_thinking": false}' \
-    --alias code
+    --chat-template-file /models/qwen3.6-35b-a3b-mtp/chat_template.jinja \
+    -m /models/qwen3.6-35b-a3b-mtp/Qwen3.6-35B-A3B-UD-Q5_K_M.gguf \
+    --mmproj /models/qwen3.6-35b-a3b-mtp/mmproj-F16.gguf \
+    --alias tool
 
 # Health Check
 HealthCmd=CMD-SHELL curl --fail http://127.0.0.1:8003/health || exit 1
@@ -37,8 +47,6 @@ HealthStartPeriod=10s
 HealthTimeout=30s
 HealthOnFailure=kill
 
-EnvironmentFile=/home/ai/.llama-api/keys.env
-
 [Service]
 Restart=always
 # Extend Timeout to allow time to pull the image

active/software_ai_stack/llama-turbo.container

@@ -6,6 +6,8 @@ Description=A Llama CPP Server Running a Reasoning Model
 Pod=ai-internal.pod
 
 # Image is built locally via podman build
+# latest-mtp is for mtp testing
+# latest is main branch
 Image=localhost/llama-cpp-vulkan:latest
 
 # Downloaded models volume
@@ -19,20 +21,23 @@ AddDevice=/dev/dri
 Exec=--port 8000 \
     -c 262144 \
     -n 32768 \
-    --temp 0.7 \
+    --temp 0.6 \
     --top-p 0.95 \
     --top-k 20 \
     --min-p 0.0 \
     --presence-penalty 0.0 \
     --repeat-penalty 1.0 \
-    --reasoning-budget 5000 \
+    --reasoning-budget 4096 \
-    -fa on \
     --perf \
     --n-gpu-layers all \
+    -fa on \
+    --spec-type draft-mtp --spec-draft-n-max 2 \
     --jinja \
-    -m /models/qwen3.6-35b-a3b/Qwen3.6-35B-A3B-UD-Q5_K_M.gguf \
+    --chat-template-kwargs '{"preserve_thinking": true}' \
-    --mmproj /models/qwen3.6-35b-a3b/mmproj-F16.gguf \
+    --chat-template-file /models/qwen3.6-35b-a3b-mtp/chat_template.jinja \
-    --alias think
+    -m /models/qwen3.6-35b-a3b-mtp/Qwen3.6-35B-A3B-UD-Q5_K_M.gguf \
+    --mmproj /models/qwen3.6-35b-a3b-mtp/mmproj-F16.gguf \
+    --alias turbo
 
 # Health Check
 HealthCmd=CMD-SHELL curl --fail http://127.0.0.1:8000/health || exit 1