Morph MORPH
SIGN IN SIGN UP
ggml-org / llama.cpp UNCLAIMED

LLM inference in C/C++

0 0 0 C++

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
X
Xuan-Son Nguyen committed
59db9a357d9a247009c70fda34050661b17a1a5c
Parent: 23fbfcb
Committed by GitHub <noreply@github.com> on 3/9/2026, 9:22:39 PM