Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration
Haoyun Jiang, Haolin Li, Jianwei Zhang +7
Large language models (LLMs) have demonstrated strong capabilities in handling long-context tasks, but processing such long contexts remains challenging due to the substantial memo…
cs.LG2026
TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification
Haoyun Jiang, Junqi He, Feng Hong +8
Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and respo…