github ggml-org/llama.cpp b7327

latest releases: b7388, b7387, b7386...
5 days ago

Warning

Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.

graph : use fill instead of scale_bias in grouped expert selection (#17867)

  • use fill instead of scale_bias in grouped expert selection

  • do not explicitly use _inplace

macOS/iOS:

Linux:

Windows:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.