github ggml-org/llama.cpp b7314

latest release: b7315
10 hours 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.

Vulkan: improve mul_mat_vec_iq1_m (#16907)

  • Optimize Vulkan shader for matrix-vector multiplication

  • Revert changes on compute_outputs and main

Refactor compute_outputs to handle remaining rows correctly.

  • Fix trailing whitespace

macOS/iOS:

Linux:

Windows:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.