Enable optimized compression of models with fp8 weights #20
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
| @@ -381,6 +387,7 @@ def _build_compress_model( | |||
| # Build OV model | |||
| weight = opset.parameter(weight_shape, name="weight", dtype=DTYPE_MAP_OV[weight_dtype]) | |||
| ov_parameters = [weight] | |||
| weight = convert_op(weight, ov.Type.f32) | |||
There was a problem hiding this comment.
Casting to FP32 in the beginning because FP8 data type does not support abs operation.
|
@alexsu52 please take a look |
Thanks for the PR. As far as I understand how to compress of fp8 data types is open question. Do you have any tickets where user scenario are described. |
Unfortunately not. Closing then. |
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Outdated suggestions cannot be applied.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.
Changes
Reason for changes
Related tickets
Tests