Fix per-tensor FP8 weight dequantization#1962

chadvoegele merged 2 commits into

mainNVIDIA/Model-Optimizer:mainfrom

cvoegele/mistral3-fp8-per-tensor-dequantNVIDIA/Model-Optimizer:cvoegele/mistral3-fp8-per-tensor-dequantCopy head branch name to clipboard