Elevate Your LLM Performance: LMCache Meetup + Hands-on Workshop

Elevate Your LLM Performance: LMCache Hands-on Workshop

Join us for an exclusive, interactive four-hour workshop where we move beyond theory to beginning our mastery of LMCache. This session is designed for engineers and researchers looking to push the boundaries of KV cache management and LLM efficiency. You will engage directly with experts, explore live deployments, and gain hands-on experience in optimizing performance.

Why Attend?

• Actionable Insights: Transition from passive listening to active experimentation.
• Direct Access: Collaborate with technical leaders and peers in the field.
• Real-World Application: Use our live environment to test and refine your understanding of LMCache.

Workshop Agenda

• 13:30 – Registration & Networking
• 14:00 – Host Overview
• 14:10 – Introduction to LMCache: Karsten Wade (@quaid), Tensormesh
• 14:30 – Coffee Break
• 14:45 – Deep Dive: Research & Testing with mini-lmcache: Samuel Shen (@sammshen), Tensormesh

• Learn the mechanics of public server deployment.
• Interactive Hands-on: Directly engage with API endpoints to benchmark and optimize KV cache management.
• The test environment remains open for your continued experimentation post-session.
• 15:30 – Networking Break
• 16:00 – Technical Session: Luis Chamberlain (@mcgrof), Samsung
• 16:30 – Technical Session: Dongjoo Seo (@DongDongJu) , Samsung
• 17:00 – Closing Remarks
• 17:05 – Networking Reception
• 17:30 – Event Adjournment