[Do not submit] Add model digest #131
Draft
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
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Outdated suggestions cannot be applied.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.
I created this simplified version of a model digest mostly out of curiosity to see if it could actually work, and it turns out it doesn't :). The test fails because the digests are different.
I think that just hashing the raw bytes can never really be relied upon because of all the pointers in the bytes - unless it is built in exactly the same order the bytes will inevitably be different.
There is another issue that if the Model is a not the root of the buffer, it will capture more information than we want, in particular info that is not hermetic (for instance, request IDs).
So, I think we will need a different approach here.