GitLab

allocate a large enough tokens slice

restart server more gracefully

Update .gitignore

use gin-contrib/cors middleware

fix markdown.

fix vars.First

Co-authored-by: Jeffrey Morgan <251292+jmorganca@users.noreply.github.com>

Improve CLI error display

add llama.cpp mpi, opencl files

windows: fix model pulling

fix stream errors

verify blob digest

update llama.cpp to e782c9e735f93ab4767ffc37462c523b73a17ddc