See full schedule

Running large LLMs in production is expensive, but often unnecessary. In this masterclass, Mashrur Haider and Dylan Bristot break down how distillation, a popular post-training technique can cut inference costs by up to 70% while maintaining enterprise-grade performance.
You’ll learn how distillation compares to fine-tuning, see real benchmarks, and watch a demo on Nebius Token Factory, the platform powering high-performance open-source inference at scale.
Key takeaways:
Distillation 101: How it works and why enterprises use it
Benchmarks: Cost savings without accuracy trade-offs
Workflow: From data prep to deployment on Nebius Token Factory
Scaling: Running distilled models in production with compliance and reliability

Please be aware that attendance is first-come, first-served.

LLM distillation explained: Post training techniques make smarter, cheaper, and deployable AI for the enterprise [Hosted by Nebius Token Factory]

Hosts