[ORTModule] ATen Efficient Attention and Triton Flash Attention #17959
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
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
There was a problem hiding this comment.
lintrunner found more than 10 potential problems in the proposed changes. Check the Files changed tab for more details.
orttraining/orttraining/python/training/ort_triton/kernel/_flash_attn.py
Fixed
Show fixed
Hide fixed
orttraining/orttraining/python/training/ort_triton/kernel/_flash_attn.py
Fixed
Show fixed
Hide fixed
askhade
reviewed
Oct 18, 2023
orttraining/orttraining/python/training/ortmodule/transformers/__init__.py
Outdated
Show resolved
Hide resolved
askhade
reviewed
Oct 18, 2023
askhade
approved these changes
Oct 25, 2023
centwang
force-pushed
the
weicwang/attn
branch
from
313a5c6
to
3da5bce
Compare
centwang
force-pushed
the
weicwang/attn
branch
from
3da5bce
to
55113c0
Compare
kleiti
pushed a commit
to kleiti/onnxruntime
that referenced
this pull request
Mar 22, 2024
…osoft#17959) This PR is to support efficient attention and flash attention in ORTModule, including: - Use ATen to call efficient attention, which requires PyTorch 2.2.0 dev or newer. ORTMODULE_USE_EFFICIENT_ATTENTION=1 to enable. - Integrate Triton Flash attention, which requires triton==2.0.0.dev20221202. Need A100 or H100. ORTMODULE_USE_FLASH_ATTENTION=1 to enable. - A python transformer tool to match sub-graph by config and write transformer quickly. Current transformers supports attention mask for both efficient attn and flash attn, and dropout for efficient attn only. To support more training scenarios (such as causal mask in GPT2), more transformers need to be added. The feature is guarded by system environment variables, it won't effect any current behavior if not enabled. Since it requires specific PyTorch/Triton versions, related tests is not added for now.
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.
This PR is to support efficient attention and flash attention in ORTModule, including:
Current transformers supports attention mask for both efficient attn and flash attn, and dropout for efficient attn only. To support more training scenarios (such as causal mask in GPT2), more transformers need to be added.
The feature is guarded by system environment variables, it won't effect any current behavior if not enabled. Since it requires specific PyTorch/Triton versions, related tests is not added for now.