Search

Your search keyword '"Zhuo, Danyang"' showing total 49 results

Search Constraints

Start Over You searched for: Author "Zhuo, Danyang" Remove constraint Author: "Zhuo, Danyang"
49 results on '"Zhuo, Danyang"'

Search Results

1. Lazarus: Resilient and Elastic Training of Mixture-of-Experts Models with Adaptive Expert Placement

2. VcLLM: Video Codecs are Secretly Tensor Codecs

Catalog

Books, media, physical & digital resources

3. Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution

4. Adaptive Skeleton Graph Decoding

5. Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native

6. Fairness in Serving Large Language Models

7. Punica: Multi-Tenant LoRA Serving

8. Symphony: Optimized DNN Model Serving using Deferred Batch Scheduling

9. Agile Development of Linux Schedulers with Ekiben

10. Query Complexity of Active Learning for Function Family With Nearly Orthogonal Basis

11. Collie: Finding Performance Anomalies in RDMA Subsystems

12. Remote Procedure Call as a Managed System Service

13. Adaptive and Dynamic Multi-Resolution Hashing for Pairwise Summations

14. Adore: Differentially Oblivious Relational Database Operators

15. A Faster $k$-means++ Algorithm

16. Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing

17. Training Overparametrized Neural Networks in Sublinear Time

18. Dynamic Maintenance of Kernel Density Estimation Data Structure: From Practice to Theory

19. Sublinear Time Algorithm for Online Weighted Bipartite Matching

20. Dissecting Service Mesh Overheads

21. Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures

22. Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning

23. Fast Graph Neural Tangent Kernel via Kronecker Sketching

24. TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models

25. InstaHide's Sample Complexity When Mixing Two Private Images

26. On InstaHide, Phase Retrieval, and Sparse Matrix Factorization

27. Ansor: Generating High-Performance Tensor Programs for Deep Learning

28. High Velocity Kernel File Systems with Bento

29. Hoplite: Efficient and Fault-Tolerant Collective Communication for Task-Based Distributed Systems

30. Volur: Concurrent Edge/Core Route Control in Data Center Networks

31. Curator: Efficient Indexing for Multi-Tenant Vector Databases

32. Application Defined Networks

33. Dissecting Overheads of Service Mesh Sidecars

35. Fast Graph Neural Tangent Kernel via Kronecker Sketching

38. Adore

41. Hoplite

42. Differentially Oblivious Database Joins: Overcoming the Worst-Case Curse of Fully Oblivious Algorithms

43. Gallium

46. Rack-level Congestion Control

48. Subways