add hunyuanv1 dense and moe model #940
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
Contributor
|
@Kingsleyandher could you kindly update the hunyuan_v1.py to use the output types that also return the metric? See the other models for that refactoring |
Kingsleyandher
force-pushed
the
hunyuanv1
branch
from
d9cd6a8 to
e269841
Compare
Contributor
Author
Thank you. It's done |
Kingsleyandher
force-pushed
the
hunyuanv1
branch
from
e269841 to
55474c4
Compare
Contributor
Author
|
Kingsleyandher
force-pushed
the
hunyuanv1
branch
from
55474c4 to
f62b40b
Compare
Contributor
Author
|
@kashif Please review it, thanks |
kashif
approved these changes
Nov 19, 2025
Contributor
Author
|
@shimizust Hi, this PR's workflow is pending maintainer approval. Could someone please approve running the workflows? Thanks! |
shimizust
approved these changes
Nov 21, 2025
Collaborator
shimizust
left a comment
shimizust
left a comment
There was a problem hiding this comment.
verified hunyuan tests pass, lgtm!
Ginray
pushed a commit
to Ginray/Liger-Kernel
that referenced
this pull request
Nov 24, 2025
## Summary <!--- This is a required section; please describe the main purpose of this proposed code change. ---> This pull request introduces support for the Hunyuanv1 dense and moe model within the Liger-Kernel framework. [HunyuanV1 Model PR](huggingface/transformers#39606) <!--- ## Details This is an optional section; is there anything specific that reviewers should be aware of? ---> ## Testing Done <!--- This is a required section; please describe how this change was tested. ---> <img width="3482" height="595" alt="1763112849386" src="https://github.com/user-attachments/assets/eaab7b15-7737-4285-9f23-1d01cc09ee91" /> And a simple test: <img width="2748" height="1051" alt="image" src="https://github.com/user-attachments/assets/fa6155f3-9456-4054-a874-41e1c25e4b47" /> <!-- Replace BLANK with your device type. For example, A100-80G-PCIe Complete the following tasks before sending your PR, and replace `[ ]` with `[x]` to indicate you have done them. --> - Hardware Type: H20 - [ x ] run `make test` to ensure correctness - [ x ] run `make checkstyle` to ensure code style - [ x ] run `make test-convergence` to ensure convergence Co-authored-by: aureli <[email protected]> Co-authored-by: Steven Shimizu <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Summary
This pull request introduces support for the Hunyuanv1 dense and moe model within the Liger-Kernel framework.
HunyuanV1 Model PR
Testing Done
And a simple test:
make testto ensure correctnessmake checkstyleto ensure code stylemake test-convergenceto ensure convergence