# cpu

> Browse 2 items tagged with cpu.

## Items

- [FusionANNS](https://vectordb.ever.works/items/fusionanns-cpu-gpu-search) — An efficient CPU/GPU cooperative processing architecture for billion-scale approximate nearest neighbor search. FusionANNS achieves up to 13.1× higher QPS compared to SPANN and can handle billion-vector datasets with over 12,000 QPS while maintaining 15ms latency using only one entry-level GPU.
- [GGUF](https://vectordb.ever.works/items/gguf) — GPT-Generated Unified Format for storing quantized model weights, designed for CPU inference and consumer hardware. Enables running LLMs on laptops and edge devices with flexible layer offloading to GPU.

---

_Canonical page: https://vectordb.ever.works/tags/cpu_