11 papers
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
Shuzhang Zhong, Haochen Huang, Shengxuan Qiu +3
Tree-of-Thought (ToT) reasoning structures Large Language Model (LLM) inference as a tree-based search, demonstrating strong potential for solving complex mathematical and programm…
HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction
Shengxuan Qiu, Haochen Huang, Shuzhang Zhong +2
Scaling test-time compute with multi-path chain-of-thought improves reasoning accuracy, but its effectiveness depends critically on the exploration-exploitation trade-off. Existing…
DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving
Ying Yuan, Pengfei Zuo, Bo Wang +3
In LLM serving, reusing the KV cache of prompts across requests is critical for reducing TTFT and serving costs. Cache-affinity scheduling, which co-locates requests with the same…
RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference
Jiarui Wang, Huichao Chai, Yuanhang Zhang +38
Real-time recommender systems execute multi-stage cascades (retrieval, pre-processing, fine-grained ranking) under strict tail-latency SLOs, leaving only tens of milliseconds for r…
Lotus: Optimizing Disaggregated Transactions with Disaggregated Locks
Zhisheng Hu, Pengfei Zuo, Junliang Hu +3
Disaggregated memory (DM) separates compute and memory resources, allowing flexible scaling to achieve high resource utilization. To ensure atomic and consistent data access on DM,…
SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving
Qihui Zhou, Peiqi Yin, Pengfei Zuo +1
Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to…