Jianbo Hu
Artificial Intelligence · 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
- Artificial Intelligence — 13 citations into it
- Efficiency & Compression — 8 citations into it
- Computer Vision and Pattern Recognition — 6 citations into it
Whom Jianbo Hu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
Papers from Jianbo Hu's perspective
Ordered by how strongly the researchers Jianbo Hu trusts endorse each paper. Same corpus, a different order for every researcher.
- Attention is All you Need (Neural Information Processing Systems)
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
- GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
- Fast Transformer Decoding: One Write-Head is All You Need
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (Neural Information Processing Systems)
- PipeDream: generalized pipeline parallelism for DNN training
- Ray: A Distributed Framework for Emerging AI Applications
- High-throughput Generative Inference of Large Language Models with a Single GPU
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
- TurboTransformers: an efficient GPU serving system for transformer models