github ggml-org/llama.cpp b8263
on GitHub

5 hours ago
Details

llama: dynamic head_dim and n_rot for SWA (#20301)

  • llama: dynamic head_dim and n_rot for SWA

  • also add gguf_writer wrappers

  • fix build

  • build_rope_shift arg reorder

macOS/iOS:

Linux:

Windows:

openEuler:

Check out latest releases or
releases around ggml-org/llama.cpp b8263

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.

Get notifications