Announcement_1
Our paper Mirage Persistent Kernel is accepted to OSDI 2026! MPK reduces end-to-end LLM inference latency by up to 1.7x over existing systems, pushing performance close to hardware limits!
Our paper Mirage Persistent Kernel is accepted to OSDI 2026! MPK reduces end-to-end LLM inference latency by up to 1.7x over existing systems, pushing performance close to hardware limits!