LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs
arXiv:2602.17681v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). …
Ofir Gordon, Lior Dikstein, Arnon Netzer, Idan Achituve, Hai Victor Habi
3 views
