Concept
TTFT
TTFT stands for Time To First Token: the latency between submitting a request to an LLM and receiving the first generated token back. It measures how long a user waits before anything appears on screen, distinct from the total generation time.
The rest of “TTFT” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→