Xuanzhe Liu

Artificial Intelligence · with Chen · 2024

A researcher in the Science corpus: 1 paper; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

Whom Xuanzhe Liu trusts

Their strongest outbound trust, strongest first, inferred from their citations.

  1. Noam Shazeer (in Model Architectures)

Papers from Xuanzhe Liu's perspective

Ordered by how strongly the researchers Xuanzhe Liu trusts endorse each paper. Same corpus, a different order for every researcher.

  1. Attention is All you Need (Neural Information Processing Systems)
  2. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
  3. GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
  4. Fast Transformer Decoding: One Write-Head is All You Need
  5. PipeDream: generalized pipeline parallelism for DNN training
  6. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Neural Information Processing Systems)
  7. High-throughput Generative Inference of Large Language Models with a Single GPU
  8. Ray: A Distributed Framework for Emerging AI Applications
  9. TurboTransformers: an efficient GPU serving system for transformer models
  10. AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving

Their papers