mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-11-10 13:54:54 +01:00
* CUDA: FA support for Deepseek (Ampere or newer) * do loop unrolling via C++ template
* CUDA: FA support for Deepseek (Ampere or newer) * do loop unrolling via C++ template