github ggml-org/llama.cpp b7495

latest releases: b7499, b7497, b7496...
8 hours ago
Details

Vulkan: some improvement on mul_mat_iq2_xs (#18031)

  • Some improvement on mul_mat_iq2_xs

Refactor calculations for db values and grid data to optimize performance and reduce redundancy.

  • Fix trailing whitespace

macOS/iOS:

Linux:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.