7 papers
CascadeEP: Asynchronous Expert Execution for MoE Prefill under Attention Imbalance
Jin Qin, Tiancheng Hu, Shiyan Wang +12
Mixture-of-experts (MoE) serving commonly deploys data and expert parallelism (DEP): attention replicas run distinct request batches while routed experts are sharded across an expe…
StrataCL: Fabric-Native Communication Library for Production Supernodes
Tiancheng Hu, Jin Qin, Yuzheng Wang +14
Modern distributed AI workloads run across hundreds of accelerators, making communication a major bottleneck. Existing communication libraries remain largely buffer-centric because…
Beyond Retrieval: A Multitask Benchmark and Model for Code Search
Siqiao Xue, Zihan Liao, Jin Qin +4
Code search has usually been evaluated as first-stage retrieval, even though production systems rely on broader pipelines with reranking and developer-style queries. Existing bench…
Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation
Tiancheng Hu, Jin Qin, Zheng Wang +10
Disaggregation maps parts of an AI workload to different types of GPUs, offering a path to utilize modern heterogeneous GPU clusters. However, existing solutions operate at a coars…
Hummingbird: SLO-Oriented GPU Preemption at Microsecond-scale
Tiancheng Hu, Chenxi Wang, Ting Cao +9
Existing GPU-sharing techniques, including spatial and temporal sharing, aim to improve utilization but face challenges in simultaneously ensuring SLO adherence and maximizing effi…
Large Processor Chip Model
Kaiyan Chang, Mingzhi Chen, Yunji Chen +40
Computer System Architecture serves as a crucial bridge between software applications and the underlying hardware, encompassing components like compilers, CPUs, coprocessors, and R…
QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
Changxin Ke, Rui Zhang, Shuo Wang +11
The rise of GPU-based high-performance computing (HPC) has driven the widespread adoption of parallel programming models such as CUDA. Yet, the inherent complexity of parallel prog…