Skip to content
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

Adding support for switch-transformer / NLLB-MoE #1565

Closed
yl3469 opened this issue Nov 5, 2023 · 5 comments
Closed

Adding support for switch-transformer / NLLB-MoE #1565

yl3469 opened this issue Nov 5, 2023 · 5 comments

Comments

@yl3469
Copy link

yl3469 commented Nov 5, 2023

Hi vLLM Team,

Thanks again for the great work!

Recently my collaborator and I have been working on MoE and like to try to integrate vLLM with SwitchTransformer / FairSeq. I was wondering if you mind sharing if there is any effort already going on and what would be the major challenges?

https://huggingface.co/docs/transformers/main/model_doc/nllb-moe
https://github.dev/huggingface/transformers/blob/main/src/transformers/models/switch_transformers/modeling_switch_transformers.py

Thanks,
Lisa

@hmellor
Copy link
Member

hmellor commented Mar 13, 2024

@yl3469 do you still intend to add support for this model archutecture?

@hmellor hmellor closed this as not planned Won't fix, can't repro, duplicate, stale May 31, 2024
@thangld201
Copy link

Hi @hmellor, if I want to add support for NLLB in vllm, what should I do ?

@hmellor
Copy link
Member

hmellor commented Aug 2, 2024

You can follow the steps at https://docs.vllm.ai/en/latest/models/adding_model.html

@thangld201
Copy link

You can follow the steps at https://docs.vllm.ai/en/latest/models/adding_model.html

This is for CausalLM, where as NLLB is encoder-decoder. I suppose that it would be very different from what's written here ?

@hmellor
Copy link
Member

hmellor commented Aug 2, 2024

Ah I see, in that case you'll want to head over to #187 to discuss Encoder-Decoder model support.

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

No branches or pull requests

3 participants