long-context-llm

Minima-KV presents a retention-preserving KV cache compression method using mixed-format paged attention to reduce memory footprint in long-context LLM serving, with evaluated performance on benchmarks.

Introduces FreqDepthKV, a frequency-guided depth sharing method for KV cache compression in long-context LLM inference, which factorizes adjacent-layer KV states into shared low-frequency components and sparse high-frequency residuals, improving memory efficiency and throughput while preserving accuracy on benchmarks.