v0.30.5-rc0: llama.cpp version update (#16511)
🔒
https://github.com
«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 ...»
Automatische Weiterleitung...
1.5s