Add sdpa for DistilBert #33724
Merged
Add sdpa for DistilBert #33724
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. |
amyeroberts
approved these changes
Sep 27, 2024
There was a problem hiding this comment.
Thanks for adding this feature and all the benchmark numbers!
Regarding the tests:
- The slow tests were skipped because the PR didn't have the
run-slowlabel on the PR. Could you try retriggering with another[run-slow] distilbertcommit? - The failure on the fetch_tests step is something which seems to be afflicting other PRs -- we've contacted CircleCI to try and get this resolved
| On a local benchmark (NVIDIA GeForce RTX 2060-8GB, PyTorch 2.3.1, OS Ubuntu 20.04) with `float16` and the `distilbert-base-uncased` model with | ||
| a MaskedLM head, we saw the following speedups during training and inference. | ||
|
|
||
| #### Training |
|
Hey! 🤗 Thanks for your contribution to the Before merging this pull request, slow tests CI should be triggered. To enable this:
(For maintainers) The documentation for slow tests CI on PRs is here. |
|
@amyeroberts It seems the tests worked. |
NielsRogge
pushed a commit
to NielsRogge/transformers
that referenced
this pull request
Oct 21, 2024
* Add sdpa for DistilBert * [run_slow] distilbert * [run_slow] distilbert * [run_slow] distilbert * Try without slow tests * [run_slow] distilbert * [run_slow] distilbert
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Outdated suggestions cannot be applied.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?
Towards #28005
Adds sdpa for the DistilBert model
Who can review?
@amyeroberts