2 papers
cs.DC2026
CacheFlow: Efficient LLM Serving via Automated 3D-Parallel KV Cache Restoration
Sean Nian, Jiahao Fang, Hanzhang Shen +3
KV cache restoration is becoming a major bottleneck in long-context LLM serving, including multi-turn conversations, agentic workloads, and RAG. Existing advances largely treat res…
cs.SI2024
Building a Mastodon Compatible Java Server for ActivityPub
Sean Nian, Angela Huang, Ben Reed
ActivityPub is a decentralized social networking protocol that has gained significant attention from the media for its ability to communicate through the Fediverse, short for the f…