In the RamaLama project we've been extensively using podman. We've also been using docker. Both work resonably well with llama.cpp . Highlighting this in the docmumentation Signed-off-by: Eric Curtin <ecurtin@redhat.com> |
||
|---|---|---|
| .. | ||
| backend | ||
| development | ||
| android.md | ||
| build.md | ||
| containers.md | ||
| cuda-fedora.md | ||
| install.md | ||
| llguidance.md | ||