collaborators

7 papers

cs.DC2026

InstantInfer: Enabling Fast LLM Cold Start with Communicating Finite Automata

Yitao Yuan, Yongchao He, Shaoke Fang +1

Cold starts in large language model (LLM) inference services significantly affect user experience, yet they remain inefficient due to sequential initialization and a massive number…

cs.DC2026

CascadeInfer: Length-Aware Scheduling of LLM Serving with Low Latency and Load Balancing

Yitao Yuan, Chenqi Zhao, Bohan Zhao +3

Efficiently harnessing GPU compute is critical to improving user experience and reducing operational costs in large language model (LLM) services. However, current inference engine…

cs.CL2025

A Unified Sparse Attention via Multi-Granularity Compression

Siran Liu, Zane Cao, Yongchao He

Efficient long-context understanding and reasoning are increasingly vital for large language model (LLM) applications such as multi-turn dialogue and program analysis. However, the…

cs.DC2025

SIMPLE: Disaggregating Sampling from GPU Inference into a Decision Plane for Faster Distributed LLM Serving

Bohan Zhao, Zane Cao, Yongchao He

As large language models (LLMs) scale out with tensor parallelism (TP) and pipeline parallelism (PP) and production stacks have aggressively optimized the data plane (attention/GEM…

cs.CL2025

HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding

Siran Liu, Yang Ye, Qianchao Zhu +2

Autoregressive decoding inherently limits the inference throughput of Large Language Model (LLM) due to its sequential dependency. Speculative decoding mitigates this by verifying…

cs.DC2025

MegatronApp: Efficient and Comprehensive Management on Distributed LLM Training

Bohan Zhao, Guang Yang, Shuo Chen +4

The rapid escalation in the parameter count of large language models (LLMs) has transformed model training from a single-node endeavor into a highly intricate, cross-node activity.…