Hanyong Shao

SlideSparse: Fast and Flexible (2N-2):2N Structured Sparsity

NVIDIA's 2:4 Sparse Tensor Cores deliver $2\times$ throughput but demand 50% pruning—a ratio that collapses LLM reasoning accuracy (Qwen3: 54%→15%). Milder $(2N-2):2N$ patterns (e.g., 6:8, 25% pruning) preserve accuracy yet receive *no* hardware support, falling back to dense execution. We present *…