-
Notifications
You must be signed in to change notification settings - Fork 424
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add Multi-Head Attention support for Vitis #1163
Open
rianbrooksflynn
wants to merge
65
commits into
fastmachinelearning:main
Choose a base branch
from
rianbrooksflynn:multi-head-attention
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Add Multi-Head Attention support for Vitis #1163
rianbrooksflynn
wants to merge
65
commits into
fastmachinelearning:main
from
rianbrooksflynn:multi-head-attention
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
…nto transformer
Thank you so much for merging it to the main! |
pre-commit.ci autofix |
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Outdated suggestions cannot be applied.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.
Description
This PR adds support for Multi-Head Attention using either Keras or PyTorch with the Vitis backend in
io_parallel
mode.Tests have been added for both Keras and Pytorch parsing.
Credit is due to @Ethan0Jiang and @LostEcho365 (Zhixing Jiang and Dennis Yin) for their original implementation and Keras parsing support; my contributions were implementing PyTorch support and adding unit tests. (Here's a link to their pre-print.) The original code authors have given permission for their code to be merged into hls4ml.
There are some important notes for PyTorch (TODO: add documentation to this effect):
batch_first=True
when instantiatingnn.MultiheadAttention
so that the inputs match up ((batch_size, seq_len, embed_dim)
instead of(seq_len, batch_size, embed_dim)
).channels_last_conversion='off'
when callingconfig_from_pytorch_model()
since batch-first PyTorch and Keras use the same input shape.query
,key
, andvalue
; hls4ml currently only supports the case wherekey
andvalue
are the same; thus, you must give PyTorch the same data for the second input and the third input.Type of change
Tests
Two unit tests added:
test/pytest/test_multiheadattention.py
andtest/pytest/test_multiheadattention_pytorch.py
Checklist
pre-commit
on the files I edited or added.