Feat (core): use runtime parameter for scale #1037
Open
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
Giuseppe5
force-pushed
the
runtime_parameter
branch
from
b92d5dd
to
609a164
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Outdated suggestions cannot be applied.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.
Wait before merge this.
It should help with the implementation of quantized scales since we can rely on the runtime value to compute scale rather than used the tracked parameter.
A bit more forward looking, this is a more """functional""" implementation of quantization, more similar to what happens with activations.
If we assume that group_dim can also become a runtime parameter, this could help towards having a """functional""" weight quantizer that it is not attached to any specific layer
@nickfraser