apply sdpa for mpt and internlm #676
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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
|
@echarlaix could you please take a look? |
AlexKoff88
reviewed
Apr 24, 2024
|
Can we have a test for each model architecture that is updated in this PR? |
echarlaix
reviewed
Apr 24, 2024
this is update for models that are already in testing, I added only baichuan based on different code version in tests, mpt and internlm are remain without changes |
eaidova
force-pushed
the
ea/mpt_sdpa
branch
2 times, most recently
from
cd9633c to
ad62a15
Compare
AlexKoff88
approved these changes
Apr 25, 2024
echarlaix
approved these changes
Apr 30, 2024
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Outdated suggestions cannot be applied.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?
optimize mpt and internlm models with scaled dot product attention
fixed export baichuan-13b model
Before submitting