Join us for a deep technical dive at ML OpenTalk November 2025: Speeding up training with FP8 and Triton

Training Large Language Models requires a lot of compute. To mitigate the GPU cost and speed up both the compute and communication, research labs have started exploring training in lower precision. FP8 has the potential of speeding up a kernel by up to 2x, but may introduce non-trivial quality degradation if done wrong.

In this talk, Vlad from the YandexGPT pretraining team will provide an overview of recent papers on FP8 training and related open source software and share the insights behind production-scale FP8 pretraining. Along the way, we will cover how GPUs work and implement Triton kernels to speed up computations.

You’ll learn:

• Why training in lower precision can cut costs and speed up compute
• What recent FP8 research papers and open-source tools reveal
• How GPUs actually work and how Triton kernels boost performance in practice
• Real insights from YandexGPT’s production-scale FP8 pretraining

Agenda

• 18:15 l Doors open
• 19:00-20:00 l Talk by Vladislav + Q&A
• 20:00-21:00 l Networking

November 13, 7:00 PM
Yandex Hall, Yerevan
Language: English

Link for registration to ML OpenTalk November 2025: https://forms.yandex.ru/surveys/13794306.bdd0707f942d9c6592938b40d89b1b6a5d672933

You can find more tech events happening in Armenia here