Folzo 20767c2300 feat: keep Ollama models in memory for 5 minutes ...

- Add OLLAMA_KEEP_ALIVE_MINUTES config (default: 5)
- schedule_ollama_unload(): delays Ollama unload when switching to Jean
- cancel_ollama_unload(): cancels timer if returning to Ollama
- Ollama models stay in VRAM for X minutes after last use
- Timer resets on each Ollama request

2026-07-20 10:46:58 +02:00

..

app.py

feat: keep Ollama models in memory for 5 minutes

2026-07-20 10:46:58 +02:00

Dockerfile

feat: jean-router — routing dynamique Jean + Ollama

2026-07-20 10:10:18 +02:00