3 papers
cs.CL2025
Value-Guided KV Compression for LLMs via Approximated CUR Decomposition
Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty
Key-value (KV) cache compression has emerged as a critical technique for reducing the memory and latency overhead of autoregressive language models during inference. Prior approach…
cs.CL2025
Compression Laws for Large Language Models
Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty
We introduce compression laws for language language models (LLMs). While recent scaling laws have sought to understand how LLMs scale with respect to model size, pre-training data,…
cs.CL2025
You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning
Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty
The ever-increasing size of large language models (LLMs) presents significant challenges for deployment due to their heavy computational and memory requirements. Current model prun…