llama.cpp
59db9a35 - llama: dynamic head_dim and n_rot for SWA (#20301)

Commit
35 days ago
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
Author
Parents
Loading