RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention.

arXiv:2606.06256v4 Announce Type: replace Abstract: As the input length of large language model (LLM) serving continues to grow, the KV cache has become a dominant bottleneck in AI infrastructure. It limits GPU memory capacity, serving concurrency, cache reuse