-
llama.cpp version update (#16511)
frostbyte_neo 发布于
2026-06-04 15:20:57 +00:00 Bump llama.cpp to b9509, which includes the upstream Gemma 4 12B multimodal projector fixes for the n_head=0 divide-by-zero crash seen on x86/CUDA/Linux/Windows.
Fixes #16479
Fixes #16489
Fixes #16491
Fixes #16492
Fixes #16495下载附件