Inference performance as a competitive advantage

Official Schedule Context

Most AI teams focus on model quality, but production success often comes down to inference

performance. In this session, FriendliAI will explore the optimization techniques behind high-

performance LLM serving, including continuous batching, speculative decoding, smart caching, and

efficient GPU utilization. Learn how leading AI teams reduce infrastructure costs, improve latency,

and scale inference workloads without sacrificing performance. We'll share practical insights and

deployment strategies that separate experimental AI projects from production-grade systems.Whether

you're an ML engineer, platform engineer, MLOps practitioner, or technical founder, you'll leave

with a better understanding of how inference optimization can become a competitive advantage for

your AI applications.

No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

Pending transcript synthesis when an official recording or confirmed matching video is available.