Refactor llm-d tests to use declarative config classes (#1182)

* refactoring llmd tests using config-based approach

* adjust markers

* use tinyllama from hf

* remove readme

* add docstrings

* make timeout for llmisvc configurable

* delete llmd dir

rename llmd_v2 to llmd

* run precommit

fix wrong import

* remove cpu marker

* remove unused code as per tox-tests failure

* Add assertion after send_prefix_cache_requests in both prefix cache tests

* use fixtures to check gpu before deploying llmisvc

* guard for ns to be max 63 chars

* nitpick comments

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: threcc

tests/model_serving/model_server/llmd/__init__.py

@@ -1 +1 @@
-"""LLMD (LLM Deployment) test module for OpenDataHub and OpenShift AI."""
+"""llm-d test module for OpenDataHub and OpenShift AI."""