AMS KV compression adaptively partitions the cache by attention mass regions and assigns quotas to protect contiguous reasoning blocks during long-context LLM inference.
Duoattention: Efficient long-context LLM inference with retrieval and streaming heads
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive Mass-Segmented KV Compression for Long-Context Reasoning
AMS KV compression adaptively partitions the cache by attention mass regions and assigns quotas to protect contiguous reasoning blocks during long-context LLM inference.