RedKnot decomposes the KV cache by attention heads to enable position-independent reuse, prefix compression, hot/cold separation, and distributed placement for long-context LLM serving without model changes.
CompressKV: Seman- tic retrieval heads know what tokens are not important before generation.arXiv preprint arXiv:2508.02401, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
RedKnot decomposes the KV cache by attention heads to enable position-independent reuse, prefix compression, hot/cold separation, and distributed placement for long-context LLM serving without model changes.