Putri improves structured LLM pruning by FFN weight updates, sequential FFN pruning, and fine-grained GQA-compatible head removal, enabling usable models at extreme sparsity.
Pointer sentinel mixture models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Prune, Update and Trim: Robust Structured Pruning for Large Language Models
Putri improves structured LLM pruning by FFN weight updates, sequential FFN pruning, and fine-grained GQA-compatible head removal, enabling usable models at extreme sparsity.