-
Notifications
You must be signed in to change notification settings - Fork 3.1k
Add vLLM Mixtral and TRT-LLM qnemo export tests (plus a couple of bugfixes) #13697
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.
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
Merged
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
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
oyilmaz-nvidia
previously approved these changes
May 22, 2025
Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
[🤖]: Hi @janekl 👋, 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. |
ko3n1g
approved these changes
May 26, 2025
melllinia
pushed a commit
to melllinia/NeMo
that referenced
this pull request
May 27, 2025
…fixes) (NVIDIA#13697) * Pin transformers and comment on Mixtral Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Remove unused tokenizer_group.py as a follow-up to NVIDIA#13498 Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Extend test_hf_import.py for other model classes and configs Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Translate the number of experts for MoE models Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Pass overwrite flag around Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Rename & fix a typo in L2_NeMo_2_VLLM_EXPORT test Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Add vLLM Mixtral export test Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Bugfix for AWQ-like methods Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Add int8_sq qnemo TRTLLM export test Signed-off-by: Jan Lasek <janek.lasek@gmail.com> --------- Signed-off-by: Jan Lasek <janek.lasek@gmail.com> Signed-off-by: mmkrtchyan <mmkrtchyan@nvidia.com>
shjwudp
pushed a commit
to shjwudp/NeMo
that referenced
this pull request
May 31, 2025
…fixes) (NVIDIA#13697) * Pin transformers and comment on Mixtral Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Remove unused tokenizer_group.py as a follow-up to NVIDIA#13498 Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Extend test_hf_import.py for other model classes and configs Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Translate the number of experts for MoE models Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Pass overwrite flag around Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Rename & fix a typo in L2_NeMo_2_VLLM_EXPORT test Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Add vLLM Mixtral export test Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Bugfix for AWQ-like methods Signed-off-by: Jan Lasek <janek.lasek@gmail.com> * Add int8_sq qnemo TRTLLM export test Signed-off-by: Jan Lasek <janek.lasek@gmail.com> --------- Signed-off-by: Jan Lasek <janek.lasek@gmail.com> Signed-off-by: jianbinc <shjwudp@gmail.com>
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 branch
button 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 ?
transformers==4.51.3
as recent newer versions sethead_dim=None
in a Mixtral HF config (which corrupts subsequent vLLM export)nemo/export/vllm/tokenizer_group.py
moduleCollection: LLM
Changelog
Usage
# Add a code snippet demonstrating how to use this
GitHub 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