SparPR: Runtime KV-Cache Recovery for Resource-Constrained LLM Inference on Consumer Hardware

cs.CL

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: 9 pages, 5 tables, 1 figure

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• OPT: Open Pre-trained Transformer Language Models
• Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering