medium10 pts · first answer countscost-optimisationlatency
Making prompt caching work
Your provider supports prompt (prefix) caching. Each request has a long fixed instruction block, a large fixed document set, and a short user question. How should you order the prompt to benefit most?
Discussion 0
Join free to post in the discussion.
Related questions
- What streaming improvesAI Engineer (LLM & Generative AI)
- Where generation time goesAI Engineer (LLM & Generative AI)
- Estimating response timeAI Engineer (LLM & Generative AI)
- How speculative decoding helpsAI Engineer (LLM & Generative AI)
- Percentiles vs average latencySite Reliability Engineer
- p99 latency across all instancesSite Reliability Engineer
- Combining percentiles from many serversSite Reliability Engineer
- Tail latency with fan-outSite Reliability Engineer