[Blip2] Add int8 support for blip2-flan-t5-xxl
#21574
Merged
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
younesbelkada
requested review from
sgugger and
NielsRogge
and removed request for
sgugger
younesbelkada
changed the title
Blip2] Add int8 supportBlip2] Add int8 support for blip2-flan-t5-xxl
|
The documentation is not available anymore as the PR was closed or merged. |
Merged
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Outdated suggestions cannot be applied.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.
What does this PR do?
Similarly as #20683 - currently the largest blip2 + flan-t5-xxl fails to run in int8 since we forgot to add the patch presented in the aforementioned PR
This PR adds the
_keep_in_fp32_modulessupport forBlip2so that users can run this model in fp16 and int8 with no performance degradation as the original model trained in bf16cc @sgugger @NielsRogge