⭐️ Featured

End-to-end open-source RAG pipeline for website content.

Open-source tools to cleanse, transform and enrich unstructured data at scale for LLM / RAG workloads.

Companion examples repo for Data Prep Kit

LLMs compete in the classic Snake game

Model visualizers, developer utilities for testing inference, and more.

Examples and tutorials for Nebius Token Factory

Browser-based benchmark for testing LLM inference endpoints - speed, latency, accuracy, and cost.

Gave a talk on Coding with Open Models.

Gave a talk on Engineering Open Models for Production alongside Dylan Bristot.

Delivered the talk: Adding real time intelligence to OpenClaw using Tavily and Token Factory.

Delivered a talk ‘Coding with open models’.

Talk: Engineering Open Models for Production.

Created and ran demos on Token Factory at the GTC booth.

Very first event on the ‘Nebius Build’ series - a pre-GTC workshop and hackathon in San Francisco. Organized / presented / supported the event.

Gave a talk: ‘Post training Open Models for Production’

Talk: Preparing Data for LLM Applications Using Data Prep Kit.

Talk: Streamlining Data Prep for LLMs with Data Prep Kit.

Ran a hands-on workshop introducing Data Prep Kit. This is the first of the Data Prep Kit series.

Presented BigDL framework.

Linux 0.02 was announced 35 years ago. I’ve used it for 31 of those years - from recompiling kernels to running AI models locally.

Fine-tuning, distillation, and quantization sound similar but solve different problems. This LEGO explainer shows how.

Using open models with modern coding agents for practical software development.

Practical techniques for improving LLM inference latency, throughput, and cost, with benchmarks and production examples.

Post training best practices for open LLMs.

Prepare data for LLM applications with an open-source toolkit for cleansing, transforming, and enriching unstructured data.