Validate your local LLM advertised KV cache against real pressure; see exactly how old contexts get evicted from cache

Hello, I'm a bit obsessed with cache management on local LLMs. For the last few days I've been working on cache management on vLLM with my 2x DGX Spark and DeepSeek v4 Flash 0731. I felt something was off so I investigated, found issues, fixed them, but needed a way to validate the fixes. That led m