Throughput
[/ˈθruːpaʊt/]
Definitions
Automatischer Uebersetzungsentwurf (German) for "Throughput": The amount of work a system can process in a given time period. In APIs it's usually measured in requests per second; in AI inference it's tokens per second. Throughput and latency are related but distinct — a system can have high throughput while still having high latency for individual requests.
“Beispielentwurf: The inference cluster achieved 10,000 tokens per second throughput across all concurrent users.”
Related Terms
- LatencyTechnology
Automatischer Uebersetzungsentwurf (German) for "Latency": The time delay between initiating an action and receiving the first response. In networking, latency is the round-trip ti...
- TelemetryTechnology
Automatischer Uebersetzungsentwurf (German) for "Telemetry": Automated collection and transmission of data about a system's performance, usage, and health to a remote monitoring se...
- API-FirstTechnology
Automatischer Uebersetzungsentwurf (German) for "API-First": A design philosophy where the API contract is defined and agreed upon before any implementation begins. API-first teams...
- BaseTechnology
Automatischer Uebersetzungsentwurf (German) for "Base": The foundational infrastructure layer of the PlatPhorm News Network (base.platphormnews.com). Base provides core shared serv...
- CI/CDTechnology
Automatischer Uebersetzungsentwurf (German) for "CI/CD": Continuous Integration / Continuous Delivery — a set of software engineering practices and tools that automate the process ...
- DevOpsTechnology
Automatischer Uebersetzungsentwurf (German) for "DevOps": A set of practices, tools, and cultural philosophies that unite software development (Dev) and IT operations (Ops) teams. ...