Sebastian Krüger 7fc945e179 fix: update LiteLLM config for direct vLLM server access ...

- 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>

2025-11-23 16:10:20 +01:00

..

postgres/init

feat: add PostgreSQL initialization script for AI stack

2025-11-09 18:36:50 +01:00

comfyui-nginx.conf

feat: make ComfyUI backend IP/port configurable via environment variables

2025-11-21 21:24:51 +01:00

compose.yaml

fix: use complete URL env var for vLLM API base

2025-11-23 13:17:37 +01:00

disable-nsfw-filter.patch

fix: correct patch for Facefusion 3.5.0 content_analyser.py

2025-11-13 04:28:50 +00:00

Dockerfile

fix: update content_analyser hash check in core.py for patched version

2025-11-13 06:16:14 +01:00

entrypoint.sh

fix: add Gradio environment variables and remove conflicting command

2025-11-13 05:52:13 +01:00

litellm-config.yaml

fix: update LiteLLM config for direct vLLM server access

2025-11-23 16:10:20 +01:00

supervisor-nginx.conf

feat: add Supervisor proxy with Authelia SSO

2025-11-22 13:19:02 +01:00