Zeyu Zhang

Orcid: 0009-0005-7853-6854

Affiliations:

According to our database¹, Zeyu Zhang authored at least 3 papers between 2023 and 2024.

Collaborative distances:

Timeline

Book

In proceedings

Article

PhD thesis

Dataset

Other

2024

CSPS: A Communication-Efficient Sequence-Parallelism based Serving System for Transformer based Models with Long Prompts.

[BibT_eX]

[DOI]

CoRR, 2024

Zero-Delay QKV Compression for Mitigating KV Cache and Network Bottlenecks in LLM Inference.

[BibT_eX]

[DOI]

CoRR, 2024

2023

Embracing Uncertainty for Equity in Resource Allocation in ML Training.

[BibT_eX]

[DOI]

Proceedings of the 52nd International Conference on Parallel Processing, 2023