Sebastian Krüger 57b706abe6 fix: correct vLLM service port to 8000 ...

- 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

2025-11-21 16:28:54 +01:00

..

models.yaml

fix: correct vLLM service port to 8000

2025-11-21 16:28:54 +01:00

orchestrator_subprocess.py

wip: start architecture redesign for RunPod (no Docker)

2025-11-21 15:09:30 +01:00

orchestrator.py

Initial commit: RunPod multi-modal AI orchestration stack

2025-11-21 14:34:55 +01:00

requirements.txt

Initial commit: RunPod multi-modal AI orchestration stack

2025-11-21 14:34:55 +01:00