huggingface / optimum-amd

AMD related optimizations for transformer models
https://huggingface.co/docs/optimum/amd/index
MIT License
57 stars 17 forks source link

update quantization configurations for ryzenai (vai_q_onnx) #117

Closed ChaoLi-AMD closed 5 months ago

mht-sharma commented 6 months ago

Hi @ChaoLi-AMD is this the final changes agreed in the meeting?

ChaoLi-AMD commented 6 months ago

Hi @ChaoLi-AMD is this the final changes agreed in the meeting?

This is the first step discussed in the meeting, where we changed the enum to a string. There will be further alignment in the future.

mht-sharma commented 6 months ago

Thanks @ChaoLi-AMD, could you also resolve the conflicts.

@Giuseppe5 would you like to review the PR as we discussed

Giuseppe5 commented 6 months ago

Looks good to me!

ChaoLi-AMD commented 5 months ago

Hi Mohit, is this PR ready to be merged? @mht-sharma