Throughput
[/ˈθruːpaʊt/]
Definitions
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.
“The inference cluster achieved 10,000 tokens per second throughput across all concurrent users.”
Related Terms
- LatencyTechnology
The time delay between initiating an action and receiving the first response. In networking, latency is the round-trip time for a data packet; in AI, it often refers to time-to-fir...
- TelemetryTechnology
Automated collection and transmission of data about a system's performance, usage, and health to a remote monitoring service. Software telemetry typically includes metrics (CPU, la...
- API-FirstTechnology
A design philosophy where the API contract is defined and agreed upon before any implementation begins. API-first teams treat the API as the product — writing the specification fir...
- BaseTechnology
The foundational infrastructure layer of the PlatPhorm News Network (base.platphormnews.com). Base provides core shared services — authentication, storage, and routing — that all o...
- CI/CDTechnology
Continuous Integration / Continuous Delivery — a set of software engineering practices and tools that automate the process of testing, building, and deploying code changes. CI auto...
- DevOpsTechnology
A set of practices, tools, and cultural philosophies that unite software development (Dev) and IT operations (Ops) teams. DevOps breaks down silos, automates repetitive tasks, and ...