Skip to content

Comments

nemo-ux: Use kv_channels to enable cases where head_dim != hidden_size // head…#9994

Merged
cuichenx merged 3 commits intomainfrom
akoumparouli/fix_mistral_mixtral_hf_import_nemo2
Aug 7, 2024
Merged

nemo-ux: Use kv_channels to enable cases where head_dim != hidden_size // head…#9994
cuichenx merged 3 commits intomainfrom
akoumparouli/fix_mistral_mixtral_hf_import_nemo2

Conversation

@akoumpa
Copy link
Collaborator

@akoumpa akoumpa commented Jul 31, 2024

Use kv_channels to enable cases where head_dim != hidden_size // head_num

for example as is the case with the 2407 modes: https://huggingface.co/mistralai/Mistral-Large-Instruct-2407

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The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.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

@akoumpa akoumpa self-assigned this Jul 31, 2024
@akoumpa akoumpa changed the title Use kv_channels to enable cases where head_dim != hidden_size // head… nemo-ux: Use kv_channels to enable cases where head_dim != hidden_size // head… Aug 2, 2024
@akoumpa akoumpa added Run CICD and removed Run CICD labels Aug 5, 2024
akoumpa added 2 commits August 5, 2024 10:59
…_num

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
@akoumpa akoumpa force-pushed the akoumparouli/fix_mistral_mixtral_hf_import_nemo2 branch from 911da5f to 794513e Compare August 5, 2024 17:59
@akoumpa akoumpa added Run CICD and removed Run CICD labels Aug 5, 2024
@akoumpa akoumpa requested review from cuichenx and marcromeyn August 5, 2024 18:11
Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
@akoumpa akoumpa added Run CICD and removed Run CICD labels Aug 6, 2024
@akoumpa akoumpa requested a review from cuichenx August 6, 2024 17:56
Copy link
Collaborator

@cuichenx cuichenx left a comment

Choose a reason for hiding this comment

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

Thanks, LGTM!

@cuichenx cuichenx merged commit 8dbe1da into main Aug 7, 2024
@cuichenx cuichenx deleted the akoumparouli/fix_mistral_mixtral_hf_import_nemo2 branch August 7, 2024 13:32
adityavavre pushed a commit to adityavavre/NeMo that referenced this pull request Sep 15, 2024
…e // head… (NVIDIA-NeMo#9994)

* Use kv_channels to enable cases where head_dim != hidden_size // head_num

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

* Add head_dim to exporter

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

* Drop default values for kv_channels

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

---------

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
Signed-off-by: adityavavre <aditya.vavre@gmail.com>
monica-sekoyan pushed a commit that referenced this pull request Oct 14, 2024
…e // head… (#9994)

* Use kv_channels to enable cases where head_dim != hidden_size // head_num

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

* Add head_dim to exporter

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

* Drop default values for kv_channels

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

---------

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
hainan-xv pushed a commit to hainan-xv/NeMo that referenced this pull request Nov 5, 2024
…e // head… (NVIDIA-NeMo#9994)

* Use kv_channels to enable cases where head_dim != hidden_size // head_num

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

* Add head_dim to exporter

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

* Drop default values for kv_channels

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

---------

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
Signed-off-by: Hainan Xu <hainanx@nvidia.com>
XuesongYang pushed a commit to paarthneekhara/NeMo that referenced this pull request Jan 18, 2025
…e // head… (NVIDIA-NeMo#9994)

* Use kv_channels to enable cases where head_dim != hidden_size // head_num

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

* Add head_dim to exporter

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

* Drop default values for kv_channels

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

---------

Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants