- Add OpenAI-compatible /v1/models endpoint to list available models
- Create systemd service file for proper service management
- Service runs as root with automatic restart on failure
- Logs to systemd journal for easy debugging
The orchestrator was calling response.json() which buffered the entire
streaming response before returning it. This caused LiteLLM to receive
only one chunk with empty content instead of token-by-token streaming.
Changes:
- Detect streaming requests by parsing request body for 'stream': true
- Use client.stream() with aiter_bytes() for streaming requests
- Return StreamingResponse with proper SSE headers
- Keep original JSONResponse behavior for non-streaming requests
This fixes streaming from vLLM → orchestrator → LiteLLM chain.
- Updated qwen-2.5-7b port from 8001 to 8000 in models.yaml
- Matches actual vLLM server default port configuration
- Tested and verified: orchestrator successfully loaded model and generated response
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>
