LLM Digest

Story

arxiv_cs_ai · Oct 30, 2026 · paper

Source brief

Prune Gradually, Adapt Sparsely: Efficient Pruning of Large Language Models at Extreme Sparsity

arxiv.orgOct 30, 2026
original source linked

In brief

Weight pruning can reduce the storage and inference cost of large language models (LLMs), but preserving quality at high sparsity levels remains challenging. Existing methods face a quality-cost trade-off in this regi...

Feed lens

eval

Read the original at arxiv.org →Open in live feed Read that day’s brief

Prune Gradually, Adapt Sparsely: Efficient Pruning of Large Language Models at Extreme Sparsity

Earlier in this thread 4 items

CRISP: Co-designing Pruning and Scheduling for Efficient MoE Inference on Edge Servers

Fewer Heads, Fewer Memories: Pruning Redundant Attention Heads Suppresses Verbatim Memorisation

CAMR: Compatibility-Aware Memory Replay for Continual Learning in Large Language Models

SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy