6 papers
PipeWeave: Synergizing Analytical and Learning Models for Unified GPU Performance Prediction
Kaixuan Zhang, Yunfan Cui, Shuhao Zhang +8
The rapid expansion of Transformer-based large language models has dramatically increased the need for high-performance GPUs. As a result, there is growing demand for fast, accurat…
WaveTune: Wave-aware Bilinear Modeling for Efficient GPU Kernel Auto-tuning
Kaixuan Zhang, Chutong Ding, Shiyou Qian +6
The rapid adoption of Large Language Models (LLMs) has made GPU inference efficiency an increasingly critical system concern. The runtime of LLM workloads is largely dominated by t…
Hestia: Hyperthread-Level Scheduling for Cloud Microservices with Interference-Aware Attention
Dingyu Yang, Fanyong Kong, Jie Dai +5
Modern cloud servers routinely co-locate multiple latency-sensitive microservice instances to improve resource efficiency. However, the diversity of microservice behaviors, coupled…
LLM-SrcLog: Towards Proactive and Unified Log Template Extraction via Large Language Models
Jiaqi Sun, Wei Li, Heng Zhang +4
Log parsing transforms raw logs into structured templates containing constants and variables. It underpins anomaly detection, failure diagnosis, and other AIOps tasks. Current pars…
GFS: A Preemption-aware Scheduling Framework for GPU Clusters with Predictive Spot Instance Management
Jiaang Duan, Shenglin Xu, Shiyou Qian +15
The surge in large language models (LLMs) has fundamentally reshaped the landscape of GPU usage patterns, creating an urgent need for more efficient management strategies. While cl…
Atys: An Efficient Profiling Framework for Identifying Hotspot Functions in Large-scale Cloud Microservices
Jiaqi Sun, Dingyu Yang, Shiyou Qian +2
To handle the high volume of requests, large-scale services are comprised of thousands of instances deployed in clouds. These services utilize diverse programming languages and are…