Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
TriSP: Tri-Signal Structured Pruning for Large Language Models
Manel Kara laoua, Soumia Bouyahiaoui, Aicha Boutorh
Large language models (LLMs) achieve strong performance across diverse tasks but their deployment is constrained by the memory and compute cost of their parameters. Structured prun…
cs.AI2026
SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation
Soumia Bouyahiaoui, Manel Kara laouar, Aicha Boutorh +1
Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottlenec…