这是indexloc提供的服务,不要输入任何密码
Skip to content

Update quantization scripts & relax modelopt requirement specifier #12709

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
merged 9 commits into from
Mar 24, 2025

Conversation

janekl
Copy link
Collaborator

@janekl janekl commented Mar 20, 2025

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An outdated branch is never blocking the merge of a PR.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 ?

  • Relaxing modelopt version constraint in requirements_nlp.txt to >=0.23.2,<=0.25.0 to support setting up NeMo in different projects
  • Moving definition of QUANT_CFG_CHOICES to a dedicated function get_quant_cfg_choices() which stores the configs depending on availability (may differ between modelopt versions)
  • Limiting generation to 30 tokens

Collection: NLP / LLM

Changelog

  • Add specific line by line info of high level changes in this PR.

Usage

  • You can potentially add a usage example below
# 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The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.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:

  • Make sure you read and followed Contributor guidelines
  • Did you write any new necessary tests?
  • Did you add or update any necessary documentation?
  • Does the PR affect components that are optional to install? (Ex: Numba, Pynini, Apex etc)
    • Reviewer: Does the PR have correct import guards for all optional libraries?

PR Type:

  • New Feature
  • Bugfix
  • Documentation

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

  • Related to # (issue)

Signed-off-by: Jan Lasek <janek.lasek@gmail.com>
@janekl janekl requested review from ko3n1g and chtruong814 March 20, 2025 14:24
janekl and others added 4 commits March 21, 2025 13:14
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: janekl <janekl@users.noreply.github.com>
@janekl janekl changed the title Relax modelopt version constraint Update quantization scripts & relax modelopt requirement specifier Mar 21, 2025
mcore_inference,
mcore_tokenizer,
prompts,
inference_params=CommonInferenceParams(top_k=1, num_tokens_to_generate=30),
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The default is to use as many as 512 tokens which is not really necessary

janekl added 4 commits March 21, 2025 15:24
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>
Copy link
Collaborator

@Laplasjan107 Laplasjan107 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

Copy link
Contributor

[🤖]: 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

I'm just a bot so I'll leave it you what to do next.

//cc @pablo-garay @ko3n1g

@janekl janekl merged commit 5c11bb5 into main Mar 24, 2025
221 checks passed
@janekl janekl deleted the jlasek/relax_modelopt_version branch March 24, 2025 17:58
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants