domvox / triattention-ggmlView on GitHub
Frequency-based KV cache pruning for llama.cpp — 25% cache reduction, improved PPL at long context. GPU compaction kernel for HIP/ROCm.
17Apr 18, 2026Updated 2 months ago

Alternatives and similar repositories for triattention-ggml

Users that are interested in triattention-ggml 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?