v0.30.5-rc0: llama.cpp version update (#16511)
Mirrored from Ollama releases for archival readability. Support the source by reading on the original site.
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
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.