Skip to content

Change activation parsing in TRTLLM#11173

Merged
pablo-garay merged 3 commits intomainfrom
bobchen/trtllm_act
Nov 6, 2024
Merged

Change activation parsing in TRTLLM#11173
pablo-garay merged 3 commits intomainfrom
bobchen/trtllm_act

Conversation

@meatybobby
Copy link
Collaborator

What does this PR do ?

Add a one line overview of what this PR aims to accomplish.

Collection: [Note which collection this PR will affect]

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The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.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)

elif k == "activation_func":
if isinstance(v, torch.jit.ScriptFunction):
nemo_model_config["activation"] = v.name.replace("_", "-")
nemo_model_config["activation"] = v.name
Copy link
Collaborator

Choose a reason for hiding this comment

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

n00b question: could you explain the reasoning for this change? the PR doesn't have any description and it's hard to parse out from this alone. are there any tests that exercise this path?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

There are two kinds of activation in config: JIT function and python function. Original code is to rename "squared_relu"->"squared-relu", but it will only rename JIT function. New code renames it after parsing all config and can handle both JIT and python function. Besides, removing "_"->"-" is to keep some activation like "gelu_fast".

Copy link
Collaborator

@oyilmaz-nvidia oyilmaz-nvidia left a comment

Choose a reason for hiding this comment

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

LGTM.

@oyilmaz-nvidia oyilmaz-nvidia enabled auto-merge (squash) November 5, 2024 23:27
@pablo-garay pablo-garay disabled auto-merge November 6, 2024 01:22
@pablo-garay pablo-garay merged commit a9ba593 into main Nov 6, 2024
@pablo-garay pablo-garay deleted the bobchen/trtllm_act branch November 6, 2024 01:22
ko3n1g pushed a commit that referenced this pull request Nov 6, 2024
* Fix squared relu

* Fix openai-gelu
pablo-garay pushed a commit that referenced this pull request Nov 6, 2024
* Fix squared relu

* Fix openai-gelu

Co-authored-by: meatybobby <bobchen@nvidia.com>
@github-actions
Copy link
Contributor

github-actions bot commented Nov 6, 2024

[🤖]: Hi @meatybobby 👋,

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

jojennin pushed a commit to jojennin/NeMo that referenced this pull request Nov 6, 2024
* Fix squared relu

* Fix openai-gelu

Signed-off-by: Joseph Jennings <jjennings@nvidia.com>
lilyw97 pushed a commit to lilyw97/NeMo that referenced this pull request Nov 13, 2024
HuiyingLi pushed a commit to HuiyingLi/NeMo that referenced this pull request Nov 15, 2024
yashaswikarnati pushed a commit that referenced this pull request Nov 21, 2024
* Fix squared relu

* Fix openai-gelu
XuesongYang pushed a commit to paarthneekhara/NeMo that referenced this pull request Jan 18, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants