CERBERUS/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-05 07:11:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
ollama/LLAMA_CPP_VERSION
Daniel Hiltgen 455f57457d
llama.cpp version update (#16511) 
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
2026-06-04 08:20:57 -07:00

1 line
6 B
Text
Raw Permalink Blame History

b9509
Reference in a new issue View git blame Copy permalink