llama-cpp-bonsai
llama.cpp fork for Ternary Bonsai 2 27B: MTP speculation, suffix cache reuse (SCR), q8 KV, two-slot fairness, fused DeltaNet kernels
Star
Fork
Watch
llama-cpp-bonsai src unicode-data.cpp
168 kB · 7034 lines
C++
at main