PFlash: 10x prefill speedup over llama.cpp at 128K on a RTX 3090(github.com)
github.com
PFlash: 10x prefill speedup over llama.cpp at 128K on a RTX 3090
https://github.com/Luce-Org/lucebox-hub/tree/main/pflash
2 comments
is this repo a legit one, has anyone audited it?