LLM Scaling Week

powered by the Yandex School of Data Analysis

  • International registration track by November 13, 2025

  • Yandex School of Data Analysis experts will explain the engineering and mathematical foundations of large language models, how they are trained on GPU clusters, and how to make them faster.

*The program is held in Russian.
This is not an educational program.
By registering, you agree to the Terms and Conditions

Scaling AI: From experiments to production systems

  • Who's the intensive for?

    • The course is designed for technical university students, researchers, developers, ML engineers, and anyone seeking to scale NLP systems beyond single‑GPU constraints
    •  

    • Practical assignments require familiarity with modern NLP, ML and algorithms such as transformers, GPT‑like models, deep learning, and big data infrastructure
  • What will the participants learn?

    • Experts from the Yandex School of Data Analysis will explain the core concepts and engineering solutions behind modern LLMs
    •  

    • Speakers will demonstrate how to identify inefficiencies and speed up inference
    •  

    • You’ll learn about distributed training and scaling methods used by leading engineers

     

     

  • How does it work?

    • All video presentations will be available as pre-recorded evening releases on YouTube and VKontakte. During video streams, participants can ask questions.
    •  

    • While video presentations are open to all registered viewers, certification requires passing the selection test and completing the final assignment
    •  

    • Selection evaluates basic skills: knowledge of ML, code, and algorithms
    •  

    • If you pass the selection stage, the final assignment will appear in your account

     

     

Program timeline

01 Registration October 28—November 13 2025
02 Selection stage October 28—November 14 2025
03 Video presentations and workshops November 10–14 2025
04 Final assignment November 15–23 2025 *
05 Certificates issued December 3–10 2025 *
*Dates are subject to change. Any updates will be announced separately

What’s in the program

The schedule is shown in Moscow time (GMT+3)

10.11

18:00

Topic 1. Deep Learning Arithmetic

Mikhail Khrushchev

Head of the pretraining group at YandexGPT

смотреть лекцию в YouTube
смотреть лекцию в ВКонтакте
11.11

18:00

Topic 2. Mixture of Experts

Alexander Mazitov

Head of architecture research at YandexGPT

смотреть лекцию в YouTube
смотреть лекцию в ВКонтакте
12.11

18:00

Topic 3.1. Speeding Up Training with FP8 and Triton

Vladislav Savinov

Head of the YandexGPT training 
infrastructure team

смотреть лекцию в YouTube
смотреть лекцию в ВКонтакте

19:20

Topic 3.2. Speeding Up Training with FP8 and Triton

Vladislav Savinov

Head of the YandexGPT training 
infrastructure team

смотреть лекцию в YouTube
смотреть лекцию в ВКонтакте
13.11

18:00

Topic 4. Communications in Distributed Learning and Inference

Stepan Kargaltsev

Lead developer, Yandex

смотреть лекцию в YouTube
смотреть лекцию в ВКонтакте
14.11

18:00

Topic 5.1 Inference Challenges

Roman Gorb

Head of the YandexGPT inference acceleration team

смотреть лекцию в YouTube
смотреть лекцию в ВКонтакте

19:45

Topic 5.2. Inference Challenges. Practice

Roman Gorb

Head of the YandexGPT inference acceleration team

смотреть лекцию в YouTube
смотреть лекцию в ВКонтакте

FAQ

Still have questions?

Tue Oct 28 2025 18:49:50 GMT+0300 (Moscow Standard Time)