waste
Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
About
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
Languages
Contributors10
No features listed.
Comments Theme
Install
Build from source
