eora: always diff in fp32 + cleanup #1836
Merged
+28
−38
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
Signed-off-by: Qubitium <Qubitium@modelcloud.ai>
Qubitium
changed the title
Signed-off-by: Qubitium <Qubitium@modelcloud.ai>
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Outdated suggestions cannot be applied.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.
@nbasyl We just did a major refractor of internals to add AWQ. Just a little cleanup in the
EoRApaths. The biggest change is doing all diff in fp32. It appears if the diff in fp16 is very small, it can actually result in 0.0 if we don't upcast to fp32.We have not tested awq and eora execution paths but I believe
eoramay also work withawq?