[cuDNN][SDPA] Handle noncontig nested tensors in cuDNN SDPA #164958
Closed
Conversation
This file contains hidden or 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
eqy
added
module: cudnn
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/164958
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 0710feb with merge base f46ddb1 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Skylion007
approved these changes
Oct 8, 2025
Skylion007
reviewed
Oct 8, 2025
aten/src/ATen/native/cudnn/MHA.cpp
Outdated
| {K, k.data_ptr()}, | ||
| {V, v.data_ptr()}, | ||
| {SCALE, &scaling_factor}, | ||
| {O, o.data_ptr()}, |
There was a problem hiding this comment.
nit: data_ptr is deprecated, please use mutable or const_data_ptr
drisspg
approved these changes
Oct 8, 2025
|
@pytorchmergebot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
Previously we hardcoded the assumption in cuDNN that the inputs would be dense which breaks when e.g., the user is chunking tensors yielding noncontig inputs
New test added to check this when
TORCH_CUDNN_SDPA_NESTED_TENSOR_ENABLED=1is set intest/test_transformers.pyOne issue I noticed was that the old gating of nested tensor in
sdp_utils.cppseems to be a no-op? All of the inputs are reported as "dense" by the time that function is called in the nested tensor tests intest/test_nestedtensor.py -k sdpacc @csarofeen @ptrblck @xwang233 @cpuhrsch @jbschlosser @bhosmer @drisspg @soulitzer @davidberard98 @YuqingJ