Implement split_with_sizes backward for NT #110647
Conversation
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/110647
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (2 Unrelated Failures)As of commit b20d4cb with merge base a3e5ec4 ( UNSTABLE - The following jobs failed but were likely due to flakiness present on trunk and has been marked as unstable:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
jbschlosser
added
release notes: nested tensor
|
@pytorchbot 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 |
| const Tensor& nt_sizes, | ||
| const at::TensorOptions& options) { | ||
| // add 1 to account for batch dim | ||
| dim = at::maybe_wrap_dim(dim, static_cast<int64_t>(nt_sizes.size(1)) + 1); |
There was a problem hiding this comment.
nit: maybe we don't need (some of) the static casts?
|
The merge job was canceled. If you believe this is a mistake, then you can re trigger it through pytorch-bot. |
|
I've cancelled the merge as #110404 is likely to be reverted. |
Needed internally. Note that `split_with_sizes()` for NT is currently supported only on `dim=-1`. [ghstack-poisoned]
|
@pytorchbot 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 |
5 participants
Stack from ghstack (oldest at bottom):
Needed internally. Note that
split_with_sizes()for NT is currently supported only ondim=-1.