arXiv2
Search
Dark
/ Date
/ Name
Aa
W
/ Date
/ Name
"au:"Xupeng Miao"" — arXiv2 Search
Showing 1–7 of 7 results
/ Date
/ Name
Oct 3, 2025
TridentServe: A Stage-level Serving System for Diffusion Pipelines
Apr 29, 2025
Hetu v2: A General and Scalable Deep Learning System with Hierarchical and Heterogeneous Single Program Multiple Data Annotations
Nov 13, 2024
LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing
Sep 5, 2024
Spindle: Efficient Distributed Training of Multi-Task Large Models via Wavefront Scheduling
Jul 1, 2024
PQCache: Product Quantization-based KVCache for Long Context LLM Inference
May 27, 2023
Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference
Jul 29, 2022
Towards Communication-efficient Vertical Federated Learning Training via Cache-enabled Local Updates