mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-05-25 07:05:56 +00:00
* WIP: Gemma4 vision Crashes on the GPU because of rms_norm requiring ne0 to be multiple of warp_size. Runs on the CPU, but produces garbage. * Remove unnecessary assert in CUDA rms_norm * GLU was not advertised as supported on CUDA * Still not working * This seems to work
15 KiB
15 KiB