JakeATX / llamAmpereView on GitHub
llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): TurboQuant KV cache, MTP speculative decoding with a 64K draft-vocabulary shortlist, custom SM86 + Qwen kernels. 90 tok/s over a 100K-token generation at temperature 1.
95Sep 18, 2026Updated this week

Alternatives and similar repositories for llamAmpere

Users that are interested in llamAmpere 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?