- Upgrade websockets from ==12.0 to >=13.0 (openai[realtime] requires >=13) - Install torch CPU-only build separately in Dockerfile to avoid ~2GB CUDA download - Remove torch from requirements.txt (installed via --index-url cpu wheel) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| src | ||
| Dockerfile | ||
| requirements.txt | ||