Profiles2023-2025ORCID 0000-0002-9371-8358
Xupeng Miao
Carnegie Mellon University Pittsburgh
11Papers
0Last author
56Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers11
- Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-FlowAuthor 3 of 6ASPLOS 2025 · 33 citations
- GraphPipe: Improving Performance and Scalability of DNN Training with Graph Pipeline ParallelismAuthor 10 of 13ASPLOS 2025 · 10 citations
- SpecInfer: Accelerating Large Language Model Serving with Tree-based Speculative Inference and VerificationAuthor 1 of 18ASPLOS 2024 · 105 citations
- SpotServe: Serving Generative Large Language Models on Preemptible InstancesAuthor 1 of 6ASPLOS 2024 · 71 citations
- Experimental Analysis of Large-scale Learnable Vector Storage CompressionAuthor 3 of 7VLDB 2024 · 20 citations
- Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion InferenceAuthor 4 of 5AAAI 2024 · 19 citations
- Optimal Kernel Orchestration for Tensor Programs with KorchAuthor 9 of 11ASPLOS 2024 · 11 citations
- Atlas: Hierarchical Partitioning for Quantum Circuit Simulation on GPUsAuthor 3 of 5SC 2024 · 9 citations
- SDPipe: A Semi-Decentralized Framework for Heterogeneity-aware Pipeline-parallel TrainingAuthor 1 of 4VLDB 2023 · 48 citations
- FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device PlacementAuthor 2 of 6SIGMOD 2023 · 40 citations
- Model-enhanced Vector IndexAuthor 9 of 19NeurIPS 2023 · 12 citations
