5 papers
Multi-Token Residual Prediction
Yufeng Xu, Zishuo Bao, Qian Wang +6
Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive model…
An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference
Feiyu Yao, Zhixiong Niu, Xiaqing Li +3
Long-context inference increasingly operates over CPU-resident KV caches, either because decoding-time KV states exceed GPU memory capacity or because disaggregated prefill-decode…
HFX: Joint Design of Algorithms and Systems for Multi-SLO Serving and Fast Scaling
Zahra Yousefijamarani, Xinglu Wang, Qian Wang +12
Large language model (LLM) serving faces the dual challenge of meeting strict user-specific service-level objectives (SLOs) while minimizing computational cost under dynamic, multi…
MEPIC: Memory Efficient Position Independent Caching for LLM Serving
Qian Wang, Zahra Yousefijamarani, Morgan Lindsay Heisler +8
Modern LLM applications such as deep-research assistants, coding agents, and Retrieval-Augmented Generation (RAG) systems, repeatedly process long prompt histories containing share…
ExpertWeave: Efficiently Serving Expert-Specialized Fine-Tuned Adapters at Scale
Ge Shi, Hanieh Sadri, Qian Wang +4
Expert-Specialized Fine-Tuning (ESFT) adapts Mixture-of-Experts (MoE) large language models to enhance their task-specific performance by selectively tuning the top-activated exper…