Prefix caching and data movement when serving coding agents at scale

Week 1· Thu, Sep 3

— skipped

Week 2· Thu, Sep 10

• 📄 PaperDiogo

  Mooncake: Trading More Storage for Less Computation — A KVCache-centric Architecture for Serving LLM Chatbot

Week 3· Thu, Sep 17

• 📄 PaperMick

  Efficient Remote KV Cache Reuse with GPU-native Video Codec

Week 4· Thu, Sep 24

• Rohan

  GPU IO