fix[export]: reshard model correctly handles extra_state when it's a tensor #12132
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
|
Contains the same change as #12131. Once 12131 goes in, this change is just the change to tensorrt_llm.py |
terrykong
changed the title
…tensor Signed-off-by: Terry Kong <[email protected]>
….from_engine Signed-off-by: Terry Kong <[email protected]>
Signed-off-by: Terry Kong <[email protected]>
Signed-off-by: terrykong <[email protected]>
terrykong
force-pushed
the
terryk/reshard-extra-state-fp8-tensor-handling
branch
from
c5bc426 to
5c207f5
Compare
meatybobby
approved these changes
Feb 12, 2025
|
[🤖]: Hi @terrykong 👋, We wanted to let you know that a CICD pipeline for this PR just finished successfully So it might be time to merge this PR or get some approvals I'm just a bot so I'll leave it you what to do next. //cc @pablo-garay @ko3n1g |
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Outdated suggestions cannot be applied.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.
Important
The
Update branchbutton must only be pressed in very rare occassions.An outdated branch is never blocking the merge of a PR.
Please reach out to the automation team before pressing that button.
What does this PR do ?
After this TE PR NVIDIA/TransformerEngine#1335, we now need to check whether the FP8 metadata is a tensor or not b/c it's stored on the CPU and can't be broadcasted w/ the mcore pp nccl group.
We haven't tested FP8 generation in Aligner, so for now we just ignore the extra_state as was the status quo before TE made this change. Left a comment to document that FP8 is not supported.
Collection: [Note which collection this PR will affect]
Changelog
Usage
# Add a code snippet demonstrating how to use thisGitHub Actions CI
The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.
The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".
Before your PR is "Ready for review"
Pre checks:
PR Type:
If you haven't finished some of the above items you can still open "Draft" PR.
Who can review?
Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.
Additional Information