Does recurrentgemma support quantization?

[daiwk]

https://developer.nvidia.com/zh-cn/blog/nvidia-tensorrt-llm-revs-up-inference-for-google-gemma/

This post says gemma supports quantization, so does recurrentgemma support quantization?

[byshiue]

If its model architecture is same to gemma, then it should be supported.

[daiwk]

If its model architecture is same to gemma, then it should be supported.
@byshiue its model arch is different with gemma, because it has a mamba-like RNN architecture, rg-lru.