wip: start architecture redesign for RunPod (no Docker)

Started redesigning architecture to run services directly without Docker:

**Completed:**
- Created new process-based orchestrator (orchestrator_subprocess.py)
- Uses subprocess instead of Docker SDK for process management
- Updated models.yaml to reference service_script paths
- vLLM server already standalone-ready

**Still needed:**
- Create/update Flux and MusicGen standalone servers
- Create systemd service files or startup scripts
- Update prepare-template script for Python deployment
- Remove Docker/Compose dependencies
- Test full stack on RunPod
- Update documentation

Reason for change: RunPod's containerized environment doesn't support
Docker-in-Docker (requires CAP_SYS_ADMIN). Direct Python execution is
simpler, faster, and more reliable for RunPod.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

model-orchestrator/models.yaml

@@ -6,7 +6,7 @@ models:
   qwen-2.5-7b:
     type: text
     framework: vllm
-    docker_service: vllm-qwen
+    service_script: vllm/server.py
     port: 8001
     vram_gb: 14
     startup_time_seconds: 120
@@ -17,7 +17,7 @@ models:
   flux-schnell:
     type: image
     framework: openedai-images
-    docker_service: flux
+    service_script: flux/server.py
     port: 8002
     vram_gb: 14
     startup_time_seconds: 60
@@ -28,7 +28,7 @@ models:
   musicgen-medium:
     type: audio
     framework: audiocraft
-    docker_service: musicgen
+    service_script: musicgen/server.py
     port: 8003
     vram_gb: 11
     startup_time_seconds: 45