Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
Python
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| benchmarks | ||
| models | ||
| adding-a-model.md 10.0 KB | ||
| architecture.md 8.2 KB | ||
| attention.md 6.7 KB | ||
| moe.md 9.8 KB | ||
| prerouter.md 4.0 KB | ||
| streaming.md 8.2 KB | ||