

Sure, here’s the proposal:
- Definitive military defeat of the ruzzian invaders and restoration of Ukraine borders
- Allow them to sell stuff again, but as part of their capitulation agreement, make them keep 10% of profits, and use the other 90% for the restoration of the damage caused by them in Ukraine. Keep that in place until an agreed amount is paid off


The irony. Before llamacpp the only way to run llama was using other and on Nvidia GPUs. Then llamacpp expanded to other models, introduced gguf, added backends to run on GPUs and now we’re taking about running qwen using just python on a single Nvidia. Ouroboros is complete.