vektorprime / working_ds4_speedView on GitHub
llama.cpp fork: custom radix-select top-k kernel + CUDA graphs for prefill for fast prompt processing
☆11Aug 16, 2026Updated 2 months ago

Alternatives and similar repositories for working_ds4_speed

Users that are interested in working_ds4_speed 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?