[CPU][TESTS] Enable quantization for single layer tests #30775
+590
−78
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
category: IE Tests
EgorDuplensky
commented
May 28, 2025
src/plugins/intel_cpu/tests/functional/custom/single_layer_tests/instances/x64/convolution.cpp
Outdated
Show resolved
Hide resolved
src/plugins/intel_cpu/tests/functional/custom/single_layer_tests/instances/x64/convolution.cpp
Outdated
Show resolved
Hide resolved
src/plugins/intel_cpu/tests/functional/custom/single_layer_tests/classes/convolution.hpp
Outdated
Show resolved
Hide resolved
EgorDuplensky
force-pushed
the
int8_single_layer_tests
branch
6 times, most recently
from
50d72ac to
c48d0c9
Compare
Use convolution as an example
EgorDuplensky
force-pushed
the
int8_single_layer_tests
branch
from
c48d0c9 to
14f8373
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Use convolution as an example
Quantization of an operation is achieved naturally by inserting FQ nodes on the inputs.
Also, it is possible to quantize output by inserting FQ + ShuffleChannels(data movement) operations after the node being tested.
For now, only per Tensor quantization is enabled. The logic can be easily extended to support per-channel.
Support for dynamic quantization and weights decompression can also be considered later (we already have custom tests for these scenarios, so it is not that necessary).