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 T

12 terms
  • Tail latency

    Tail latency is the serving concept concerned with tail latency during AI inference.

    Inference performance
  • Tensor fusion

    Tensor fusion is the serving concept concerned with tensor fusion during AI inference.

    Inference performance
  • Tensor parallelism

    Tensor parallelism is the serving concept concerned with tensor parallelism during AI inference.

    Inference performance
  • Throughput latency tradeoff

    Throughput latency tradeoff is the serving concept concerned with throughput latency tradeoff during AI inference.

    Inference performance
  • Throughput per gpu

    Throughput per gpu is the serving concept concerned with throughput per gpu during AI inference.

    Inference performance
  • Time to first byte

    Time to first byte is the serving concept concerned with time to first byte during AI inference.

    Inference performance
  • Time to first token

    Time to first token, or TTFT, is the elapsed time from an inference request being accepted until the first output token is delivered. It captures startup and queue delay before generation becomes visible to a user.

    Inference performance
  • Time to last token

    Time to last token is the serving concept concerned with time to last token during AI inference.

    Inference performance
  • Timeout budget

    Timeout budget is the serving concept concerned with timeout budget during AI inference.

    Inference performance
  • Token streaming

    Token streaming is the serving concept concerned with token streaming during AI inference.

    Inference performance
  • Tokens per second

    Tokens per second is the serving concept concerned with tokens per second during AI inference.

    Inference performance
  • Tool latency

    Tool latency is the time an application or agent waits for a tool call to complete. It includes work such as a database query, API request, file operation, or test run between model responses.

    Inference performance