RDLTR

Short for Read Later. Save links from any browser or phone. Click to save, read to clear. The full tour

One topic. Every takeSeek and you shall find

Reading up on Flex Processing

1 deep · digging since feb 20

  • developers.openai.com favicon
    Prompt Caching 201

    Prompt caching reduces latency by up to 80% and costs by up to 90% by reusing computed key/value tensors for repeated prompt prefixes in OpenAI's API.