github ggml-org/llama.cpp b7783

6 hours ago
Details

CUDA: Replace init_offsets kernel with iterators in cub-based argsort (#18930)

  • CUDA: Replace init_offsets with iterators in argsort

This is a QOL improvement, saving us the cost of materializing the
iterator

  • Remove unnecessary include from top-k.cu

macOS/iOS:

Linux:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.