A load-aware prefill deflection scheduler for disaggregated LLM serving reduces P95 TTFT by up to 81% by interleaving chunked prefill on decode nodes and eliminating KV-cache transfers.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
TokenDance scales multi-agent LLM serving to 2.7x more concurrent agents by collective KV cache reuse and block-sparse diff encoding that achieves 11-17x compression.
citing papers explorer
-
Towards Load-Aware Prefill Deflection for Disaggregated LLM Serving
A load-aware prefill deflection scheduler for disaggregated LLM serving reduces P95 TTFT by up to 81% by interleaving chunked prefill on decode nodes and eliminating KV-cache transfers.
-
TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
TokenDance scales multi-agent LLM serving to 2.7x more concurrent agents by collective KV cache reuse and block-sparse diff encoding that achieves 11-17x compression.