Views
No views yet
down_proj tensors calibrated in FP8_DYNAMIC and the rest using Four Over Six adaptive block scaling, created to compare against my hybrid quant. Made with the same version of llm-compressor and compressed-tensors, using the same calibration data, to isolate the variables as much as possible.1@misc{cook2025sixaccuratenvfp4quantization,
2 title={Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling},
3 author={Jack Cook and Junxian Guo and Guangxuan Xiao and Yujun Lin and Song Han},
4 year={2025},
5 eprint={2512.02010},
6 archivePrefix={arXiv},
7 primaryClass={cs.CL},
8 url={https://arxiv.org/abs/2512.02010},
9}