If you’re working on LLM inference at scale—or curious how others are solving real performance bottlenecks—Dynamo Day is a great chance to connect with the Dynamo community and ecosystem.
The sessions focus on practical topics like KV-cache optimization, distributed serving, and high-performance LLM inference, with perspectives from OSS inference framework maintainers, experienced inference practitioners, and teams running production deployments.
📅 Thursday, Jan 22 | 8 AM–1 PM PT
🎟️ Free registration: https://nvda.ws/4svwy6m