wide-6f024946·1 events·first seen Aliases: WIDE
WIDE is a new end-to-end differentiable framework for token-level dynamic width pruning of LLMs, enabling each token to independently select attention-head groups and FFN-channel groups at inference time. The system introduces a pruning-kernel co-design that decomposes dynamic sparsity acceleration into mask reordering and block-level skipping, achieving near-theoretical speedups of up to 1.98x for prefill and 4.95x for decoding at 50% sparsity. At that sparsity level, WIDE reports a 55.1% performance improvement over state-of-the-art dynamic depth pruning under calibration-only settings. Code is publicly released.