4 accepted papers
In large language model (LLM) serving, reusing the key-value (KV) cache of prompts across requests is a key technique for reducing time-to-first-token (TTFT) and lowering serving costs. Cache-affinity scheduling, which co-locates requests with the same prompt prefix to maximize KV cache reuse, often…
Scaling test-time compute with multi-path chain-of-thought can improve reasoning accuracy, but its gains hinge on an effective exploration–exploitation trade-off. Existing methods handle this trade-off in rigid ways: tree-structured search hard-codes exploration via brittle expansion rules that disr…
Sparse attention has emerged as a vital technique for long-context inference in Large Language Models (LLMs), effectively accelerating memory-bound decoding by reducing memory access for non-essential keys. However, the assumption that decoding attention is memory-bound has been shattered. The proli…
Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference…