Understanding KV Cache Compression
A systems view of why KV cache becomes the limiting resource in long-context inference and where compression actually helps.
Read noteKnowledge repository
Technical Notes
Deep dives, research surveys, engineering notes, and technology outlooks for building intelligent systems.
Agent Memory Is a System Architecture
A practical model for separating working context, durable knowledge, task state, and execution history.
Read noteAI Chip Architecture for LLM Inference
A concise map of the compute, memory, and interconnect constraints behind modern language-model serving.
Read note