Feature Request: Support Glm4MoeLiteForCausalLM #18931
Description
Prerequisites
- I am running the latest code. Mention the version if possible as well.
- I carefully followed the README.md.
- I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
- I reviewed the Discussions, and have a new and useful enhancement to share.
Feature Description
Z.ai released a new 30B MoE GLM-4.7-Flash which has the architecture defined as Glm4MoeLiteForCausalLM.
Motivation
As a small alternative to Z.ai's flagship model, it would be great to have GGUF support for this model as well!
Possible Implementation
Reference implementations:
Transformers PR
vLLM PR