Kmic-68 / llama.cppView on GitHub
llama.cpp tuned for 2x Tesla P100 (sm_60). Decode 1.86x, 3-4x with MTP (up to ~70 t/s on code). Prefill 2x, full 262k context with vision. More numerically accurate than upstream.
☆29Nov 1, 2026Updated this week

Alternatives and similar repositories for llama.cpp

Users that are interested in llama.cpp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?