Skip to content
Tagged articles

LLM pruning

2 articles · Page 1 of 1
AI Frontier Lectures
AI Frontier Lectures
Nov 13, 2026 · Artificial Intelligence

Train-Free Iterative Pruning (GISP) Outperforms Layer-Wise LLM Compression

This ACL 2026 outstanding paper introduces GISP, a train-free iterative structured pruning method that globally ranks attention heads and MLP channels by normalized first-order importance scores, achieving lower perplexity than layer-wise uniform pruning on Llama2-7B/13B at 40-50% sparsity without fine-tuning.

GISPLLM pruningLlama2
0 likes · 10 min read
Train-Free Iterative Pruning (GISP) Outperforms Layer-Wise LLM Compression
Baobao Algorithm Notes
Baobao Algorithm Notes
Oct 25, 2024 · Artificial Intelligence

Why Calibration Data Outperforms Pruning Algorithms in LLM Compression

This study investigates how the choice of calibration data, rather than the pruning algorithm itself, dominates post‑training pruning performance for large language models, revealing that data similarity to the original training set and synthetic data generation can significantly boost compression results.

LLM pruningartificial intelligencecalibration data
0 likes · 14 min read
Why Calibration Data Outperforms Pruning Algorithms in LLM Compression