GitLab

Co-authored-by: Blake Mizerany <blake.mizerany@gmail.com>

- return descriptive error messages when unauthorized to create blob or push a model
- display the local public key associated with the request that was denied

Updated the code a bit

* Bump llama.cpp to b2761

* Adjust types for bump

Fix relative path lookup

* app: restart server on failure

* fix linter

* address comments

* refactor log directory creation to be where logs are written

* check all log dir creation errors

Add support for building on Windows ARM64

Fix concurrency for CPU mode

Prior refactoring passes accidentally removed the logic to bypass VRAM
checks for CPU loads.  This adds that back, along with test coverage.

This also fixes loaded map access in the unit test to be behind the mutex which was
likely the cause of various flakes in the tests.

The Digest type needs more thought and is not necessary at the moment.

Fine grain control over windows generate steps

This will speed up CI which already tries to only build static for unit tests

Fix target in gen_windows.ps1

fix gemma, command-r layer weights