SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression.

Tim Dettmers, Ruslan Svirschevski, Vage Egiazarian, Denis Kuznedelev, Elias Frantar, Saleh Ashkboos, Alexander Borzunov, Torsten Hoefler, Dan Alistarh

Browse the full ICLR paper archive.