Popular repositories Loading
-
termux-harness
termux-harness PublicMeasured report + drop-in harness for running llama.cpp with the Vulkan backend on Android/Adreno (Turnip). GPU offload cuts CPU time 6.6x while token generation stays flat. Raw benchmark data, off…
Shell 1
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.
