feed/tags/long-context
long context
2 explainers you can run, 3 glossary terms, and one reading ordered as a path, each with one line on why it earns your time.
explainers/ 2 pages
- beginnerThe KV cache is the thing you are actually renting
Fill a GPU with weights and per-request cache until it will not take another user. 320 KiB per token adds up faster than anyone expects.
- intermediateThe hit rate is the workload
Agent sessions taking turns against one card's memory. Add sessions and watch each turn's cost jump from nothing to ten seconds as its history is evicted.
advanced/ 1 entry
Current work, at the depth practitioners actually argue about.