[TESTS] Use FP32 inference precision, FP16 KV cache precision for pipelines #1485
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
OpenVINO plugins enable different kind of optimizations by default like KV cache compression to int8, fp16 inference precision, while in GenAI tests we want to test pipelines and how they are compared against HF / optimum w/o extra optimizations:
openvino.genai/tests/python_tests/common.py
Lines 318 to 325 in 4db67ae
Hopefully, we can merge int8 KV cache by default for CB then #1206, because in tests we will still compare FP16 KV cache, while official Validation should be responsible for validation against reference via WWB metrics.