Elamur Research⌕
☰
home / authors / Zhihao Jia

Zhihao Jia

Zhihao Jia has 5 papers in our library, in 2018–2024, most of them on Language models & pretraining; often with Alex Aiken, Matei Zaharia, Xupeng Miao.

5 papers in our library · 2018–2024

OpenAlex · ORCID · Wikidata · h-index 21 · 55 works · 1,847 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 Cited 415 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #3523

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Carnegie Mellon UniversityPittsburgh · United States2021–2026 · 51 paperscurrent🎓Stanford UniversityStanford · United States2015–2024 · 14 papers🎓Tsinghua UniversityBeijing · China2012–2024 · 5 papers🎓Imperial College LondonLondon · United Kingdom2026 · 2 papers🏢MicrosoftRedmond · United States2022–2024 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 12 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 8The field of science this work belongs to (OpenAlex fields).Computer Science · 5 worksComputer Vision and Pattern Recognition · 3 worksHardware and Architecture · 2 worksInformation Systems · 2 worksArts and Humanities · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Networks and Communications · 1 work

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3 works

 Works by year

2020s

20241 paper20232 papers

2010s

20191 paper20181 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Beyond Data and Model Parallelism for Deep Neural Networks (2018 · 280 citations)
    Training large DNNs is now routinely spread across many GPUs, yet mainstream frameworks mostly rely on plain data parallelism or model parallelism.
  2. SpotServe: Serving Generative Large Language Models on Preemptible Instances (2023 · 145 citations)
    SpotServe addresses the high cost of serving generative LLMs. It runs inference on preemptible cloud GPUs, such as AWS spot instances, which can be up to 90% cheaper than on-demand machines but can be reclaimed at any time. Earlier spot-based serving systems assumed that a model fits on one instance and handled…
  3. Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems (2023 · 110 citations)
    Generative LLMs are expensive to deploy. Their size and token-by-token generation make low-latency, high-throughput serving difficult, especially for organizations without large compute budgets. This survey by researchers at Purdue and Carnegie Mellon reviews the field from a machine-learning-systems perspective. It…
  4. TASO: Optimizing Deep Learning Computation with Automatic Generation of Graph Substitutions (2019 · 72 citations)
    Deep learning frameworks such as TensorFlow, PyTorch, TensorRT and TVM speed up computation graphs by rewriting subgraphs into faster equivalent forms.
  5. MagicPIG: LSH Sampling for Efficient LLM Generation (2024 · 68 citations)
    Serving long-context LLMs is constrained by the KV cache. It consumes GPU memory and makes decoding memory-bound. Many speedups keep only the highest-scoring keys (TopK attention). The authors show this is a biased estimator that breaks down when attention is spread out, as in aggregation tasks like common- or…

All works

7 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

  1. Beyond Data and Model Parallelism for Deep Neural NetworksSysML 2019Zhihao Jia, Matei Zaharia, Alex Aiken2018 · 280 citations
  2. SpotServe: Serving Generative Large Language Models on Preemptible InstancesACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)Xupeng Miao, Chunan Shi, Jiangfei Duan, et al.2023 · 145 citations
  3. Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to SystemsACM Computing SurveysXupeng Miao, Gabriele Oliaro, Zhihao Zhang, et al.2023 · 110 citations
  4. TASO: Optimizing Deep Learning Computation with Automatic Generation of Graph SubstitutionsSOSP 2019Zhihao Jia, Oded Padon, James Thomas, et al.2019 · 72 citations
  5. MagicPIG: LSH Sampling for Efficient LLM GenerationarXiv:2410.16179Zhuoming Chen, Ranajoy Sadhukhan, Zihao Ye, et al.2024 · 68 citations
  6. PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections ↗OSDI 2021 · no summary yetHaojie Wang et al.2021 · 40 citations
  7. Redundancy-Free Computation Graphs for Graph Neural Networks ↗arXiv (Cornell University) · no summary yetZhihao Jia et al.2019 · 9 citations

 Co-authors here

12 of 17 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 415 times (of the 149,439 papers whose bibliographies we read); 31 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zhihao-jia/