- Add BGE embedding model config (port 8002) to litellm-config.yaml
- Add GPU_VLLM_EMBED_URL env var to compose and .env
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove crawl4ai service from ai/compose.yaml (will use local MCP instead)
- Remove crawl4ai backup volume from core/compose.yaml
- Add core/backrest/config.json (infrastructure as code)
- Change backrest from volume to bind-mounted config
- Update CLAUDE.md and README.md documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Supervisor XML-RPC API v3.0 (Supervisor 4.3.0) only supports 2-parameter
readLog(offset, length) calls, not 3-parameter calls with filename.
The SUPERVISOR_LOGFILE environment variable is not used by the API.
Testing showed:
- Working: server.supervisor.readLog(-4096, 0)
- Failing: server.supervisor.readLog(-4096, 4096, '/path/to/log')
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replaced nginx:alpine proxy with dev.pivoine.art/valknar/supervisor-ui:latest
- Modern Next.js UI with real-time SSE updates, batch operations, and charts
- Changed service port from 80 (nginx) to 3000 (Next.js)
- Removed supervisor-nginx.conf (no longer needed)
- Kept same URL (supervisor.ai.pivoine.art) and Authelia SSO protection
- Added health check for /api/health endpoint
- Service connects to RunPod Supervisor via Tailscale (SUPERVISOR_HOST/PORT)
- Replace orchestrator routing with direct vLLM server connections
- Qwen 2.5 7B on port 8000 (GPU_VLLM_QWEN_URL)
- Llama 3.1 8B on port 8001 (GPU_VLLM_LLAMA_URL)
- Simplify architecture by removing orchestrator proxy layer
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replace GPU_TAILSCALE_IP interpolation with GPU_VLLM_API_URL
- LiteLLM requires full URL in api_base with os.environ/ syntax
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replace COMFYUI_BACKEND_HOST and SUPERVISOR_BACKEND_HOST with GPU_TAILSCALE_IP
- Update LiteLLM config to use os.environ/GPU_TAILSCALE_IP for vLLM models
- Add GPU_TAILSCALE_IP env var to LiteLLM service
- Configure qwen-2.5-7b and llama-3.1-8b to route through orchestrator
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove hardcoded default values from compose.yaml
- Backend IPs now managed via environment variables only
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add nginx reverse proxy service for Supervisor web UI at supervisor.ai.pivoine.art with Authelia authentication. Proxies to RunPod GPU instance via Tailscale (100.121.199.88:9001).
Changes:
- Create supervisor-nginx.conf for nginx proxy configuration
- Add supervisor service to docker-compose with Traefik labels
- Add supervisor.ai.pivoine.art to Authelia protected domains
- Remove deprecated Flux-related files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replace hardcoded IP in comfyui-nginx.conf with env vars
- Add COMFYUI_BACKEND_HOST and COMFYUI_BACKEND_PORT to compose.yaml
- Use envsubst to substitute variables at container startup
- Defaults: 100.121.199.88:8188 (current RunPod Tailscale IP)
- Add ComfyUI service to AI stack using nginx:alpine as reverse proxy
- Proxy to RunPod ComfyUI via Tailscale (100.121.199.88:8188)
- Configure Traefik routing for comfy.ai.pivoine.art
- Enable Authelia SSO middleware (net-authelia)
- Support WebSocket connections for real-time updates
- Set appropriate timeouts for image generation (300s)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Set drop_params: false in litellm_settings
- Set modify_params: false in litellm_settings
- Set drop_params: false in default_litellm_params
- Commented out LITELLM_DROP_PARAMS env var
- Removed --drop_params command flag
These settings were stripping critical streaming parameters causing
vLLM streaming responses to collapse into empty deltas
- Reverted direct orchestrator connection to WebUI
- Added stream: true parameter to qwen-2.5-7b model config
- Keep LiteLLM as single proxy for all models
- Configure WebUI with both LiteLLM and direct orchestrator API base URLs
- This bypasses LiteLLM's streaming issues for the qwen-2.5-7b model
- WebUI will now show models from both endpoints
- Allows testing if LiteLLM is the bottleneck for streaming
Related to streaming fix in RunPod models/vllm/server.py
- Changed back from hosted_vllm/qwen-2.5-7b to openai/qwen-2.5-7b
- Removed /v1 suffix from api_base (LiteLLM adds it automatically)
- Added supports_system_messages: false for vLLM compatibility
- Update api_base URLs from 100.100.108.13 to 100.121.199.88 (RunPod Tailscale IP)
- All self-hosted models (qwen-2.5-7b, flux-schnell, musicgen-medium) now route through Tailscale VPN
- Tested and verified connectivity between VPS and RunPod GPU orchestrator
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Removed outdated AI infrastructure README that referenced GPU services.
VPS AI services (Open WebUI, Crawl4AI, facefusion) are documented in compose.yaml comments.
GPU infrastructure docs are now in dedicated runpod repository.
Multi-modal AI stack (text/image/music generation) has been moved to:
Repository: ssh://git@dev.pivoine.art:2222/valknar/runpod.git
Updated ai/README.md to document:
- VPS AI services (Open WebUI, Crawl4AI, AI PostgreSQL)
- Reference to new runpod repository for GPU infrastructure
- Clear separation between VPS and GPU deployments
- Integration architecture via Tailscale VPN
Implemented a cost-optimized AI infrastructure running on single RTX 4090 GPU with
automatic model switching based on request type. This enables text, image, and
music generation on the same hardware with sequential loading.
## New Components
**Model Orchestrator** (ai/model-orchestrator/):
- FastAPI service managing model lifecycle
- Automatic model detection and switching based on request type
- OpenAI-compatible API proxy for all models
- Simple YAML configuration for adding new models
- Docker SDK integration for service management
- Endpoints: /v1/chat/completions, /v1/images/generations, /v1/audio/generations
**Text Generation** (ai/vllm/):
- Reorganized existing vLLM server into proper structure
- Qwen 2.5 7B Instruct (14GB VRAM, ~50 tok/sec)
- Docker containerized with CUDA 12.4 support
**Image Generation** (ai/flux/):
- Flux.1 Schnell for fast, high-quality images
- 14GB VRAM, 4-5 sec per image
- OpenAI DALL-E compatible API
- Pre-built image: ghcr.io/matatonic/openedai-images-flux
**Music Generation** (ai/musicgen/):
- Meta's MusicGen Medium (facebook/musicgen-medium)
- Text-to-music generation (11GB VRAM)
- 60-90 seconds for 30s audio clips
- Custom FastAPI wrapper with AudioCraft
## Architecture
```
VPS (LiteLLM) → Tailscale VPN → GPU Orchestrator (Port 9000)
↓
┌───────────────┼───────────────┐
vLLM (8001) Flux (8002) MusicGen (8003)
[Only ONE active at a time - sequential loading]
```
## Configuration Files
- docker-compose.gpu.yaml: Main orchestration file for RunPod deployment
- model-orchestrator/models.yaml: Model registry (easy to add new models)
- .env.example: Environment variable template
- README.md: Comprehensive deployment and usage guide
## Updated Files
- litellm-config.yaml: Updated to route through orchestrator (port 9000)
- GPU_DEPLOYMENT_LOG.md: Documented multi-modal architecture
## Features
✅ Automatic model switching (30-120s latency)
✅ Cost-optimized single GPU deployment (~$0.50/hr vs ~$0.75/hr multi-GPU)
✅ Easy model addition via YAML configuration
✅ OpenAI-compatible APIs for all model types
✅ Centralized routing through LiteLLM proxy
✅ GPU memory safety (only one model loaded at time)
## Usage
Deploy to RunPod:
```bash
scp -r ai/* gpu-pivoine:/workspace/ai/
ssh gpu-pivoine "cd /workspace/ai && docker compose -f docker-compose.gpu.yaml up -d orchestrator"
```
Test models:
```bash
# Text
curl http://100.100.108.13:9000/v1/chat/completions -d '{"model":"qwen-2.5-7b","messages":[...]}'
# Image
curl http://100.100.108.13:9000/v1/images/generations -d '{"model":"flux-schnell","prompt":"..."}'
# Music
curl http://100.100.108.13:9000/v1/audio/generations -d '{"model":"musicgen-medium","prompt":"..."}'
```
All models available via Open WebUI at https://ai.pivoine.art
## Adding New Models
1. Add entry to models.yaml
2. Define Docker service in docker-compose.gpu.yaml
3. Restart orchestrator
That's it! The orchestrator automatically detects and manages the new model.
## Performance
| Model | VRAM | Startup | Speed |
|-------|------|---------|-------|
| Qwen 2.5 7B | 14GB | 120s | ~50 tok/sec |
| Flux.1 Schnell | 14GB | 60s | 4-5s/image |
| MusicGen Medium | 11GB | 45s | 60-90s for 30s audio |
Model switching overhead: 30-120 seconds
## License Notes
- vLLM: Apache 2.0
- Flux.1: Apache 2.0
- AudioCraft: MIT (code), CC-BY-NC (pre-trained weights - non-commercial)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
This commit finalizes the GPU infrastructure deployment on RunPod:
- Added qwen-2.5-7b model to LiteLLM configuration
- Self-hosted on RunPod RTX 4090 GPU server
- Connected via Tailscale VPN (100.100.108.13:8000)
- OpenAI-compatible API endpoint
- Rate limits: 1000 RPM, 100k TPM
- Marked GPU deployment as COMPLETE in deployment log
- vLLM 0.6.4.post1 with custom AsyncLLMEngine server
- Qwen/Qwen2.5-7B-Instruct model (14.25 GB)
- 85% GPU memory utilization, 4096 context length
- Successfully integrated with Open WebUI at ai.pivoine.art
Infrastructure:
- Provider: RunPod Spot Instance (~$0.50/hr)
- GPU: NVIDIA RTX 4090 24GB
- Disk: 50GB local SSD + 922TB network volume
- VPN: Tailscale (replaces WireGuard due to RunPod UDP restrictions)
Model now visible and accessible in Open WebUI for end users.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Removed supports_prompt_caching parameter that was causing 400 errors.
Prompt caching is automatically enabled by Anthropic when the client
sends cache_control blocks in messages - no config needed.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
