kvcached is an open-source LLM inference tool from ovg-project, licensed under Apache-2.0. With 1.8k stars on GitHub, it was last updated in October 2026. Related topics: elastic-kvcache, gpu-mutiplexing and gpu-sharing.
“Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond”
— ovg-project, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 1,820 |
| Forks | 216 |
| Language | Python |
| License | Apache-2.0 |
| Last updated | |
| Owner | ovg-project |
| Repository | ovg-project/kvcached |
Tags
elastic-kvcachegpu-mutiplexinggpu-sharinginference-enginekvcachekvcache-optimizationkvcachedllm
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.