chore: activate input compression for encrypted data-frames [BLOCKED BY CP] #731
Conversation
This file contains 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
RomanBredehoft
commented
Jun 13, 2024
| @@ -347,7 +347,7 @@ def _get_training_quantized_module( | |||
| # Enable the underlying FHE circuit to be composed with itself | |||
| # This feature is used in order to be able to iterate in the clear n times without having | |||
| # to encrypt/decrypt the weight/bias values between each loop | |||
| configuration = Configuration(composable=True, compress_evaluation_keys=True) | |||
There was a problem hiding this comment.
the feature is activated in the QuantizedModule's compile function, so let's avoid some confusion here
RomanBredehoft
commented
Jun 13, 2024
| @@ -37,17 +37,9 @@ def run_hybrid_llm_test( | |||
| ): | |||
| """Run the test for any model with its private module names.""" | |||
|
|
|||
| # Multi-parameter strategy is used in order to speed-up the FHE executions | |||
| configuration = Configuration( | |||
There was a problem hiding this comment.
same, these options are the QM's default, so let's avoid some confusion / unexpected mismatches
RomanBredehoft
force-pushed
the
feat/activate_input_compression_dataframe
branch
from
7c8f05e to
0463ca3
Compare
RomanBredehoft
force-pushed
the
feat/activate_input_compression_dataframe
branch
from
9b8dc3a to
525beb7
Compare
Coverage passed ✅Coverage details
|
RomanBredehoft
changed the title
|
will be added in #805 |
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Outdated suggestions cannot be applied.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.
We realized with @andrei-stoian-zama that encrypted data-frames did not have the input compression feature activated
this is currently blocked by https://github.com/zama-ai/concrete-internal/issues/758