Zahra Dehghanighobadi

Ruhr University Bochum

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Architecture Design (Transformers, SSMs, MoE) (1)Distributed Systems & Hardware (1)Inference & Quantization (1)

Frequent co-authors

Asja Fischer (1)

Papers (1)

Apr 27, 2026

Ruhr University Bochum3w ago

DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference

Not all layers are created equal: pruning the KV cache in a layer-dependent manner significantly boosts long-context LLM performance compared to uniform pruning strategies.

Zahra Dehghanighobadi, Asja Fischer

Architecture Design (Transformers, SSMs, MoE)Distributed Systems & Hardware Inference & Quantization

Search

Zahra Dehghanighobadi

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)