colibri: Pure-C Zero-Dependency Engine Streams MoE Experts From Disk to Run Frontier Models Locally
JustVugg · github · 2026-09-10
colibri, trending on GitHub with 27K+ stars, is a tiny pure-C inference engine with zero dependencies that runs frontier MoE models on hardware you already own.
The trick: expert weights are streamed from disk on demand instead of residing in memory, sidestepping VRAM/RAM capacity limits. "Tiny engine, immense model" — a notable entry in the local-inference space.
More from Infra
- DeepSpeed shows AutoEP/AutoTP/AutoSP parallelism gains, hosts office hours — PyTorch · 2026-10-27
- Cloudflare Durable Objects validated as top architecture for AI agent WebSocket servers — tristanbob · 2026-10-27
- Gary Marcus: With Q3 data added, Anthropic's compute-efficiency growth shows deceleration — GaryMarcus · 2026-10-27
- SpaceX locks in $40B GPU financing deal with Apollo, the largest ever committed — TechCrunch AI · 2026-10-27
- Inference is just Kubernetes with a multi-trillion-dollar market, and the communities overlap — matt_slotnick · 2026-10-27
- vLLM eyes Rust migration as inference engines race to rewrite the stack — AccBalanced · 2026-10-27