LEAP learns unstructured pruning masks end-to-end for LLMs via Gumbel-sigmoid Bernoulli relaxation and reports +2.59 average zero-shot accuracy gain over ADMM at 50-60% sparsity across five model families.
arXiv preprint arXiv:2104.08378 , year=
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 12roles
background 1polarities
background 1representative citing papers
MosaicKV achieves up to 16x attention speedup, 4.8x lower decode latency, 7.3x higher throughput, and 3x memory reduction with 1.76% accuracy loss via dynamic two-D KV cache compression and management on H800 GPUs.
SpenseGPT introduces a hybrid sparse-dense weight format and one-shot pruning that delivers 1.2x end-to-end LLM decoding speedup on B200 GPUs with FP8 while preserving accuracy on Qwen3-32B and Seed-OSS-36B.
HORST uses non-commutative operator composition and a hyperbolic mirror map to combine stability from adaptive optimizers with L1 sparsity bias, outperforming AdamW across sparsity levels on vision and language tasks.
SparseForge achieves 57.27% zero-shot accuracy on LLaMA-2-7B at 2:4 sparsity using only 5B retraining tokens, beating the dense baseline and nearly matching a 40B-token SOTA method.
SLaB compresses LLM weights via sparse-lowrank-binary decomposition guided by activation-aware scores, achieving up to 36% lower perplexity than prior methods at 50% compression on Llama models.
MaskPro learns categorical distributions over groups of M weights to generate exact (N:M) sparsity via N-way sampling without replacement and stabilizes training with a moving average tracker of loss residuals.
Pruned initializations from an 8B model outperform random starts with equal training tokens, but with full token budgets fine-grained pruning retains advantage while coarse structured pruning does not.
Marchenko-Pastur random-matrix pruning of DNNs yields theoretical certificates for accuracy preservation under small fine-tuning and empirical ImageNet results with 50-60% MAC reduction and sub-2pp accuracy drops on ViT and CNN models.
ELAS pre-trains low-rank LLMs by applying 2:4 activation sparsity after squared ReLU to cut memory and accelerate training with minimal performance loss.
Covariance-aware ridge and combined l1-l2 regularizers for neural networks yield better predictive performance and complexity control than standard penalties in simulations and applications to cooling-load prediction and leukemia classification.
HieraSparse delivers a hierarchical semi-structured sparse KV attention system that achieves 1.2x KV compression and 4.57x decode attention speedup versus prior unstructured sparsity methods at equivalent sparsity, plus up to 1.85x prefill speedup and 1.37x/1.77x speedups with magnitude pruning and
citing papers explorer
-
HieraSparse: Hierarchical Semi-Structured Sparse KV Attention
HieraSparse delivers a hierarchical semi-structured sparse KV attention system that achieves 1.2x KV compression and 4.57x decode attention speedup versus prior unstructured sparsity methods at equivalent sparsity, plus up to 1.85x prefill speedup and 1.37x/1.77x speedups with magnitude pruning and