WActiGrad: Structured Pruning for Efficient Finetuning and Inference of Large Language Models on AI Accelerators.

Krishna Teja Chitty-Venkata, Varuni Katti Sastry, Murali Emani, Venkatram Vishwanath, Sanjif Shanmugavelu, Sylvia Howland

Browse the full EuroPar paper archive.