Do you have any plans to support NVFP4?

#14
by taewan2002 - opened

A quantized NVFP4 version would be a huge help for users serving models with vLLM in an environment using dual RTX Pro 6000 Blackwell GPUs.

taewan2002 changed discussion title from 혹시 nvfp4 지원 계획이 있나요? to Do you have any plans to support NVFP4?
LG AI Research org

Hello, @taewan2002 . Sorry for the delay and thank you for your attention.

At the moment, we don’t have plans to release an NVFP4 version of the K-EXAONE model.
If we’re able to support it in the future, we’ll be happy to do so.

Sign up or log in to comment