3 papers
cs.LG2025
Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
Yilong Zhao, Jiaming Tang, Kan Zhu +10
Reasoning language models have demonstrated remarkable capabilities on challenging tasks by generating elaborate chain-of-thought (CoT) solutions. However, such lengthy generation…
cs.DC2025
PolyServe: Efficient Multi-SLO Serving at Scale
Kan Zhu, Haiyang Shi, Le Xu +4
Advances in Large Language Models (LLMs) have led to a surge of LLM-powered applications. These applications have diverse token-generation latency requirements. As a result, simply…
cs.LG2025
Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs
Kan Zhu, Tian Tang, Qinyu Xu +7
Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse att…