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 S

9 terms
  • Scale to zero

    Scale to zero is the serving concept concerned with scale to zero during AI inference.

    Inference performance
  • Semantic caching

    Semantic caching stores a response and retrieves it for a later request judged similar in meaning. It uses a similarity method rather than requiring the later request to match the earlier text exactly.

    Inference performance
  • Sequence packing

    Sequence packing is the serving concept concerned with sequence packing during AI inference.

    Inference performance
  • Server sent events

    Server sent events is the serving concept concerned with server sent events during AI inference.

    Inference performance
  • Service time

    Service time is the serving concept concerned with service time during AI inference.

    Inference performance
  • Serving backpressure

    Serving backpressure is the serving concept concerned with serving backpressure during AI inference.

    Inference performance
  • Speculative decoding

    Speculative decoding is the serving concept concerned with speculative decoding during AI inference.

    Inference performance
  • Static batching

    Static batching is the serving concept concerned with static batching during AI inference.

    Inference performance
  • Streaming inference

    Streaming inference is the serving concept concerned with streaming inference during AI inference.

    Inference performance