#1125448 llama.cpp: autopkgtests fail on systems with insufficient memory

#1125448#5
Date:
2026-01-13 22:21:19 UTC
From:
To:
The llama.cpp autopkgtests currently fail if they are run on a GPU with
insufficient memory for the used models. The test runner must discover
this, and skip the tests for those models.

#1125448#10
Date:
2026-02-16 22:08:08 UTC
From:
To:
The workaround was to reduce the tests run to those requiring less than
4GB memory. Anything larger was being too punishing on CPU-only tests
anyway.