Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".
Why do you think that https://github.com/Dao-AILab/flash-attention is a good alternative to sparsegpt
Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".
Why do you think that https://github.com/Dao-AILab/flash-attention is a good alternative to sparsegpt