activity
20242026
collaborators

6 papers

cs.DC2026

Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs

Yixuan Mei, Zikun Li, Zixuan Chen +5

The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide range of mid-tier and older-ge…

cs.PL2026

Prism: Symbolic Superoptimization of Tensor Programs

Mengdi Wu, Xiaoyu Jiang, Oded Padon +1

This paper presents Prism, the first symbolic superoptimizer for tensor programs. The key idea is sGraph, a symbolic, hierarchical representation that compactly encodes large class…

cs.DC2025

MPK: A Compiler and Runtime for Mega-Kernelizing Tensor Programs

Xinhao Cheng, Zhihao Zhang, Yu Zhou +17

We introduce Mirage Persistent Kernel (MPK), the first compiler and runtime system that automatically transforms multi-GPU model inference into a single high-performance mega-kerne…

cs.CC2025

Identity Testing for Circuits with Exponentiation Gates

Jiatu Li, Mengdi Wu

Motivated by practical applications in the design of optimization compilers for neural networks, we initiated the study of identity testing problems for arithmetic circuits augment…

cs.DC2024

GraphPipe: Improving Performance and Scalability of DNN Training with Graph Pipeline Parallelism

Byungsoo Jeon, Mengdi Wu, Shiyi Cao +11

Deep neural networks (DNNs) continue to grow rapidly in size, making them infeasible to train on a single device. Pipeline parallelism is commonly used in existing DNN systems to s…

cs.LG2024

Mirage: A Multi-Level Superoptimizer for Tensor Programs

Mengdi Wu, Xinhao Cheng, Shengyu Liu +7

We introduce Mirage, the first multi-level superoptimizer for tensor programs. A key idea in Mirage is Graphs, a uniform representation of tensor programs at the kernel, thread…