Nitin Kedia
Nitin Kedia has 2 papers in our library, in 2024, most of them on Language models & pretraining; often with Alexey Tumanov, Amey Agrawal, Ashish Panwar.
OpenAlex · h-index 3 · 7 works · 28 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 436 times in our library · ⭐ Paper Stars ranking: #4461
Affiliations
Fields, topics and concepts
📚 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
Papers
- 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. - 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.
Co-authors here
- Alexey Tumanov ×2
- Amey Agrawal ×2
- Ashish Panwar ×2
- Bhargav S. Gulavani ×2
- Jayashree Mohan ×2
- Nipun Kwatra ×2
- Ramachandran Ramjee ×2
Venues
- OSDI 2024
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/nitin-kedia/