antirez: DwarfStar now runs Kimi K3.1 PRO inference from safetensors via SSD streaming
antirez · x · 2026-11-08
antirez reports that the kimi-k3 branch of his DwarfStar project can now run K3.1 PRO inference directly from safetensors weights with SSD streaming. It's slow, but good enough for QA tasks.
More from Infra
- Hugging Face free accounts now get 2 ZeroGPU Spaces with ~5 min GPU/day — Fine_League311 · 2026-11-08
- kmorph: open-source Linux project recovers from kernel crashes without rebooting in ~2s — kingslyj · 2026-11-08
- AI progress per dollar fell 63% as R&D spending grew 5.3x faster than capability gains — kimmonismus · 2026-11-08
- blank: open-source local-first agent harness fixes parallel sub-agent collisions and rate-limit halts — Big_Veterinarian7479 · 2026-11-08
- Google plans $15B Malaysia data centers by 2028; Microsoft carries $80B+ obligations — YvesMulkers · 2026-11-08
- Your local LLM server is reachable by any web page: CSRF/DNS rebinding risk tested live — FeydRowan · 2026-11-08