Add Cache Miss/Hit Test

[alex-jw-brooks]

This PR builds on top of #20 and #93 to add a cache for testing using the refactored version of the test to allow some code reuse. #93 should probably be merged first (splitting this out for readability).

Summary of changes (wrt the original cache test PR)
- Makes sure gptq kwargs are passed through to the AIU model
- Makes sure options={"sendnn.dynamic": COMPILE_DYNAMIC_SENDNN} is passed consistently
- Clears the torch sendnn .cache - the current PR can break if the cache test runs second since the cache paths aren't actually reset in torch sendnn. We reset the compiler settings and clear the directory, but don't clear the spyre cache object in the current PR, which causes alignment issues if the cache test doesn't run first
- The current PR runs the check as two tests (cache miss -> cache hit); moves the cache miss test to run as a fixture to set things up so that we can just run cache hit as the test

Note that there is still some weirdness around how micro models are handled, mostly due to the way we configure common models paths / micro model usage and also check thresholds based on whether micro models exist.

[alex-jw-brooks]

bot:test
TEST_FILE=test_decoders.py MODEL_ID=ibm-granite/granite-3.3-8b-instruct BATCH_SIZE=1,2 SEQUENCE_LENGTH=1024,2048 USE_TINY_MODEL=1 NUM_AIU=4

[JRosenkranz]

It looks like we are re-creating the model and validation_model when it's already being created in the fixture. Is this required?

[alex-jw-brooks]

Nope! Good point, returned them both out of the fixture and deleted it from the cache hit check so that it'll be reused

[alex-jw-brooks]

bot:test
TEST_FILE=test_decoders.py MODEL_ID=ibm-granite/granite-3.3-8b-instruct BATCH_SIZE=1,2 SEQUENCE_LENGTH=1024 USE_TINY_MODEL=1 NUM_AIU=4

[JRosenkranz]

lgtm once the duplicate lines are fixed

[matthew-pisano]

@JRosenkranz Is this good to go?