Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Add bounds check for indices in unique_indices to prevent out-of-bounds errors #2728

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add bounds check for indices in unique_indices to prevent out-of-bounds errors #2728

wants to merge 1 commit into from

Conversation

lxg2015
Copy link

@lxg2015 lxg2015 commented Feb 6, 2025

This commit addresses an issue where enabling unique_indices could lead to a cryptic RuntimeError: when feature IDs exceed the table size

[rank29]:   File "/usr/local/lib/python3.9/site-packages/torchrec/distributed/embedding_sharding.py", line 757, in _wait_impl
[rank29]:     KJTAllToAllTensorsAwaitable(
[rank29]:   File "/usr/local/lib/python3.9/site-packages/torchrec/distributed/dist_data.py", line 368, in __init__
[rank29]:     awaitable = dist.all_to_all_single(
[rank29]:   File "/usr/local/lib/python3.9/site-packages/torch/distributed/c10d_logger.py", line 83, in wrapper
[rank29]:     return func(*args, **kwargs)
[rank29]:   File "/usr/local/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py", line 4000, in all_to_all_single
[rank29]:     work = group.alltoall_base(
[rank29]: RuntimeError: Split sizes doesn't match total dim 0 size

In fact, This error occurs in jagged_unique_indices, which assumes input IDs are within the table bounds. Without unique_indices, TorchRec correctly reports out-of-bounds errors, but this check was missing in the unique_indices path.

This fix adds a bounds check to ensure IDs do not exceed the table size when unique_indices is enabled, providing a clearer error message and preventing the runtime error. This improves debugging and ensures consistent behavior across both paths.

@facebook-github-bot
Copy link
Contributor

Hi @lxg2015!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at [email protected]. Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@lxg2015 @facebook-github-bot