🛰️ Daily AI Frontier
‹ back to 2026-07-27

Unified Static-Dynamic Pruning for Efficient LLM Inference

Research Efficiency & Systems

Merged summary

TL;DR - SPDP combines static weight pruning with input-adaptive dynamic pruning through a shared compressed format and specialized GPU kernels. It accelerates LLM inference while preserving perplexity and supporting greater sparsity.

  • Introduces the Tiled-CBC bitmap-compressed format for efficient static and dynamic sparsity.
  • Uses a CUDA-core spMspV kernel for activation-aware skipping during decoding.
  • Provides a Tensor-Core SpMM kernel optimized for prefill.
  • Achieves 1.24–1.37× average speedups, up to 2.51×, over sparse frameworks such as SpInfer, with matching perplexity and up to 25% higher sparsity.

Sources (1)

Unified Static-Dynamic Pruning for Efficient LLM Inference

arXiv cs.DC Jinhyeok Kim, Yejoon Lee, Jaeyoung Do 2026-07-24 arXiv:2607.21985

TL;DR - SPDP combines static weight pruning with input-adaptive dynamic pruning through a shared compressed format and specialized GPU kernels. It accelerates LLM inference while preserving perplexity and supporting greater sparsity.

  • Introduces the Tiled-CBC bitmap-compressed format for efficient static and dynamic sparsity.
  • Uses a CUDA-core spMspV kernel for activation-aware skipping during decoding.
  • Provides a Tensor-Core SpMM kernel optimized for prefill.
  • Achieves 1.24–1.37× average speedups, up to 2.51×, over sparse frameworks such as SpInfer, with matching perplexity and up to 25% higher sparsity.
item →