A reference from Weave

Find a term

Explore latency, throughput, caching, and serving techniques. Understand which parts of a model request consume time and compute.

Terms beginning with P

11 terms
  • P50 latency

    P50 latency is the serving concept concerned with p50 latency during AI inference.

    Inference performance
  • P95 latency

    P95 latency is the serving concept concerned with p95 latency during AI inference.

    Inference performance
  • P99 latency

    P99 latency is the serving concept concerned with p99 latency during AI inference.

    Inference performance
  • Paged attention

    Paged attention is the serving concept concerned with paged attention during AI inference.

    Inference performance
  • Pipeline parallelism

    Pipeline parallelism is the serving concept concerned with pipeline parallelism during AI inference.

    Inference performance
  • Prefill decode disaggregation

    Prefill decode disaggregation is the serving concept concerned with prefill decode disaggregation during AI inference.

    Inference performance
  • Prefill phase

    Prefill phase is the serving concept concerned with prefill phase during AI inference.

    Inference performance
  • Prefix cache

    Prefix cache is the serving concept concerned with prefix cache during AI inference.

    Inference performance
  • Processing time

    Processing time is the serving concept concerned with processing time during AI inference.

    Inference performance
  • Prompt caching

    Prompt caching reuses processing associated with previously supplied prompt content, often a matching prefix, to reduce repeated input work. It differs from response caching, which returns a stored answer instead of generating a new one.

    Inference performance
  • Prompt length

    Prompt length is the serving concept concerned with prompt length during AI inference.

    Inference performance