Elamur Research⌕
☰
home / authors / Alexey Tumanov

Alexey Tumanov

Alexey Tumanov has 2 papers in our library, in 2024, most of them on Language models & pretraining; often with Amey Agrawal, Ashish Panwar, Bhargav S. Gulavani.

2 papers in our library · 2024

OpenAlex · ORCID · h-index 23 · 78 works · 3,288 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 668 times in our library · 8 more in our library without a page yet · ⭐ Paper Stars ranking: #4460

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

🎓Georgia Institute of TechnologyAtlanta · United States2019–2026 · 37 papersEmployment since 2019 · Assistant Professor, School of Computer Sciencecurrent🎓Carnegie Mellon UniversityPittsburgh · United States2012–2017 · 9 papers🎓University of California, BerkeleyBerkeley · United States2017–2018 · 8 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Fields, topics and concepts

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

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArts and Humanities · 1 workHardware and Architecture · 2 worksArtificial Intelligence · 1 workLanguage and Linguistics · 1 workComputer Networks and Communications · 1 workInformation Systems · 1 work

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 2 works

 Works by year

2020s

20242 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve (2024 · 369 citations)
    Serving LLMs online requires both high throughput, to keep costs down, and low latency between generated tokens.
  2. Vidur: A Large-Scale Simulation Framework For LLM Inference (2024 · 90 citations)
    Deploying a large language model involves many choices: the parallelism layout (TP, PP, number of replicas), the scheduler (Orca, vLLM, Sarathi-Serve), batch size, scheduler-specific knobs and the GPU SKU.

All works

10 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. Ray: A Distributed Framework for Emerging AI Applications ↗arXiv (Cornell University) · no summary yetPhilipp Moritz et al.2017 · 437 citations
  2. Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-ServeOSDI 2024Amey Agrawal, Nitin Kedia, Ashish Panwar, et al.2024 · 369 citations
  3. Vidur: A Large-Scale Simulation Framework For LLM InferencearXiv:2405.05465Amey Agrawal, Nitin Kedia, Jayashree Mohan, et al.2024 · 90 citations
  4. Real-Time Machine Learning ↗Workshop on Hot Topics in Operating Systems · no summary yetRobert Nishihara et al.2017 · 48 citations
  5. Dynamic Space-Time Scheduling for GPU Inference ↗arXiv:1901.00041 · no summary yetParas Jain et al.2018 · 43 citations
  6. Real-Time Machine Learning: The Missing Pieces ↗arXiv (Cornell University) · no summary yetRobert Nishihara et al.2017 · 16 citations
  7. InferLine: ML Inference Pipeline Composition Framework. ↗arXiv (Cornell University) · no summary yetDaniel Crankshaw et al.2018 · 10 citations
  8. HyperSched: Dynamic Resource Reallocation for Model Development on a Deadline ↗arXiv (Cornell University) · no summary yetRichard Liaw et al.2020 · 8 citations
  9. The OoO VLIW JIT Compiler for GPU Inference ↗arXiv:1901.10008 · no summary yetParas Jain et al.2019 · 7 citations
  10. SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads ↗arXiv (Cornell University) · no summary yetAlind Khare et al.2023 · 6 citations

 Co-authors here

7 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 668 times (of the 149,439 papers whose bibliographies we read); 29 citing papers with a page here →.

Updated

↑ back to top

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