arXiv:2606. 28831v1 Announce Type: cross Abstract: Long-context LLM inference faces a fundamental conflict: head-adaptive compression algorithms (e.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2607. 22389v1 Announce Type: cross Abstract: With the rapid adoption of long-context large language models (LLMs), the continuously growing KV cache during decoding has become the critical memory bottleneck.
arXiv:2502. 16886v4 Announce Type: replace-cross Abstract: To reduce memory consumption during LLM inference, a handful of methods have been proposed for KV cache pruning.
arXiv:2606. 24467v1 Announce Type: new Abstract: Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware.
Long chain-of-thought (CoT) trajectories in large language model (LLM) reasoning cause severe inference bottlenecks due to rapid key-value (KV) cache growth. Current decoding-time compression methods mitigate this issue via token eviction, but typically assume a uniform budget distribution across all layers and heads.
Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs.
Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt.