Arm backend: Add serialized xlarge TOSA model suite (#21492)

The DeepSeek-R1-Distill-Qwen layer-test PRs were reverted because they
caused OOMs in the no-driver Arm TOSA model pytest job.

The normal TOSA model shard should keep using pytest-xdist auto
parallelism so unrelated model tests do not slow down. Add a separate
serialized suite for xlarge TOSA model tests instead.

The reland of the DeepSeek layer tests can mark the memory-heavy cases
as xlarge and route them through this suite. This also gives internal CI
an explicit option for running any xlarge TOSA model coverage serially.

cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils
@Sebastian-Larsson @robell @rascani

Signed-off-by: Baris Demir <baris.demir@arm.com>