3 papers
cs.CL2026
LLM Router: Rethinking Routing with Prefill Activations
Tanay Varshney, Annie Surla, Michelle Xu +5
Existing routers rely on semantic query features or handcrafted features, which often fail to capture model-specific failures or intrinsic task difficulty. We instead route using i…
cs.LG2026
KVzap: Fast, Adaptive, and Faithful KV Cache Pruning
Simon Jegou, Maximilian Jeblick
Growing context lengths in transformer-based language models have made the key-value (KV) cache a critical inference bottleneck. While many KV cache pruning methods have been propo…
cs.AI2025
Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution
Alessio Devoto, Maximilian Jeblick, Simon Jégou
Memory consumption of the Key-Value (KV) cache represents a major bottleneck for efficient large language model inference. While attention-score-based KV cache pruning shows promis…