Glossary
Quantization
Representing model weights, activations, or cache values with lower numerical precision.
Reviewed as part of AI Inference Efficiency and Model Serving Vocabulary, using the primary references listed below. Updated 2026-07-24.
Plain-English meaning
Quantization is used here to describe representing model weights, activations, or cache values with lower numerical precision. In the daily board, the word is grouped by the role it performs rather than by spelling or market popularity.
You may encounter it in a product interface, technical document, risk report, policy paper, or market dashboard. The term is included for recognition and comparison, not as a product recommendation.
Important boundary
Lower precision can reduce memory or bandwidth while changing speed, compatibility, or output quality.
When this word appears in a report, identify the mechanism being described before treating the label as a conclusion. Similar terms can point to different causes, controls, or outcomes.
Why it belongs with AI Inference Stack
These words cover the runtime pieces that shape speed, cost, and throughput when a model answers.
When solving the puzzle, compare the job this term performs with nearby cards. A correct group usually shares a function, risk type, workflow, or market structure rather than simply sharing similar wording.
Where you might see it
You might encounter this term while reading educational explainers, product documentation, risk disclosures, market dashboards, or beginner guides. Always separate vocabulary learning from financial decision-making.
Reading cue
Comparing two model servers without relying on one headline metric
Use the full guide's applied scenario to ask where Quantization enters the process, what evidence supports it, and which nearby concept it could be confused with.
Read the complete applied scenarioNearby concepts
Compare before you memorize
Batching
Scheduling multiple inference requests together so hardware can process them more efficiently.
Higher batch efficiency can increase queue time for an individual request.KV cache
Stored attention keys and values reused during autoregressive generation.
It reduces repeated computation but can consume significant memory as contexts and concurrency grow.Inference latency
Elapsed time for a request or a defined stage of model serving.
It must specify the measured stage; first-token delay and full-response time are different.Token throughput
The number of input or output tokens processed by a system over time.
Total throughput does not show how long one user waited.Knowledge check
Check the distinction
What tradeoff does a KV cache introduce?
It avoids recomputing prior attention state while using memory that grows with context, model shape, precision, and concurrent sequences.
Source trail
References behind this explanation
These references support the surrounding guide and concept boundaries. Open the full source when you need the original technical or policy context.
Official serving documentation covering continuous batching, quantization, speculation, parallelism, monitoring, and token streaming.
Hugging Face TransformersCache strategiesOfficial documentation explaining cache implementations and the memory-latency tradeoffs of quantized KV caches.