[IntraNodeComm] fix a recent breakage #141200
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
[ghstack-poisoned]
pytorch-bot
bot
added
oncall: distributed
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/141200
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (1 Unrelated Failure)As of commit 2f51ba1 with merge base 161425f ( FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
weifengpy
approved these changes
Nov 25, 2024
|
@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 |
kwen2501
approved these changes
Nov 25, 2024
Comment on lines
-13
to
+14
| input.dtype() == at::kBFloat16, | ||
| "oneShotAllReduce only supports bf16 for now"); | ||
| input.dtype() == at::kBFloat16 || input.dtype() == at::kFloat, | ||
| "oneShotAllReduce only supports float and bf16 for now"); |
There was a problem hiding this comment.
Nice fix. Was hitting this issue last week. It unblocks me now :)
pobin6
pushed a commit
to pobin6/pytorch
that referenced
this pull request
Dec 5, 2024
- Pass `group_name` to `CUDASymmetricMemory::alloc()` instead of `CUDASymmetricMemory::rendezvous()`. We can only move the argument to rendezvous() once all the underlying operators do the same. - Added `float` to the allowlist for intra-node all-reduces. - Added a warning when `IntraNodeComm::rendezvous()` is performed with overlapping devices among participants. Pull Request resolved: pytorch#141200 Approved by: https://github.com/weifengpy, https://github.com/kwen2501
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.
Stack from ghstack (oldest at bottom):
group_nametoCUDASymmetricMemory::alloc()instead ofCUDASymmetricMemory::rendezvous(). We can only move the argument to rendezvous() once all the underlying operators do the same.floatto the allowlist for intra-node all-reduces.IntraNodeComm::rendezvous()is performed with overlapping devices among participants.cc @H-Huang @awgu @kwen2501 @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @c-p-i-o