GitLab

Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>

This caused missing internal files

remove any unneeded build artifacts

passthrough OLLAMA_HOST path to client

update templates to use messages

fix(test): do not clobber models directory

fix: validate modelpath

detect chat template from configs that contain lists

The numa flag may be having a performance impact on multi-socket systems with GPU loads

The recent cuda variant changes uncovered a bug in ByLibrary
which failed to group by common variant for GPU types.

update faq

During rebasing, the ordering was inverted causing the cuda version
selection logic to break, with driver version being evaluated as zero
incorrectly causing a downgrade to v11.