A reference from Weave

Find a term

Understand the metrics, models, and methods behind modern engineering. Clear definitions, practical examples, and a closer look at what the numbers actually mean.

Terms beginning with M

128 terms

  • Model fallback cost

    Model fallback cost is extra expense when a primary model fails and another route serves work. It gives teams a way to name, measure, or reason about an economic property of an AI workload without treating raw usage as proof of value.

    Token costs and AI ROI

  • Model gateway

    A model gateway is a service layer that gives applications a common interface to one or more model providers. Depending on its design, it can handle routing, authentication, retries, fallbacks, usage tracking, and request policies.

    Model routing and gateways

  • Model loading

    Model loading is the serving concept concerned with model loading during AI inference.

    Inference performance

  • Model mix

    Model mix is the distribution of workload across models, providers, or deployment tiers. It gives teams a way to name, measure, or reason about an economic property of an AI workload without treating raw usage as proof of value.

    Token costs and AI ROI

  • Model parallelism

    Model parallelism is the serving concept concerned with model parallelism during AI inference.

    Inference performance

  • Model registry

    Model registry is a model-routing or gateway concept used to manage operational visibility for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Model replica

    Model replica is the serving concept concerned with model replica during AI inference.

    Inference performance

  • Model replication

    Model replication is the serving concept concerned with model replication during AI inference.

    Inference performance

  • Model routing

    Model routing is the process of selecting which AI model handles a request or a step in a workflow. A routing policy can consider the task, required capabilities, expected quality, price, latency, and provider availability.

    Model routing and gateways

  • Model routing savings

    Model routing savings is spend reduction from sending work to a suitable efficient route. It gives teams a way to name, measure, or reason about an economic property of an AI workload without treating raw usage as proof of value.

    Token costs and AI ROI

  • Model version pinning

    Model version pinning is a model-routing or gateway concept used to manage operational visibility for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Model warmup

    Model warmup is the serving concept concerned with model warmup during AI inference.

    Inference performance

  • Model-based testing

    Model-based testing is a software testing or test-design practice used to gather evidence about a defined risk, behavior, boundary, or operating condition. It makes the question under test explicit, identifies the inputs and observations that matter, and gives a team a repeatable basis for deciding whether the result is acceptable.

    Code quality and technical debt

  • Moderator variable

    Moderator variable is a statistical or measurement concept used to describe, compare, or interpret engineering data. Its meaning depends on the unit of analysis, data-generating process, and question being asked.

    Measurement and experimentation

  • Modular monolith

    Modular monolith is a software maintenance concern describing a condition that can make future changes, verification, operation, or ownership harder. Its practical importance depends on supported behavior, rate of change, and the consequences of delay.

    Code quality and technical debt

  • Module cohesion

    The degree to which the elements of a module support one focused purpose.

    Code quality and technical debt

  • Module stability

    The degree to which a module can change without forcing changes in its consumers.

    Code quality and technical debt

  • Module testing

    Module testing is a software testing or test-design practice used to gather evidence about a defined risk, behavior, boundary, or operating condition. It makes the question under test explicit, identifies the inputs and observations that matter, and gives a team a repeatable basis for deciding whether the result is acceptable.

    Code quality and technical debt

  • Monolith decomposition

    Monolith decomposition is a software maintenance concern describing a condition that can make future changes, verification, operation, or ownership harder. Its practical importance depends on supported behavior, rate of change, and the consequences of delay.

    Code quality and technical debt

  • Monte Carlo simulation

    Monte Carlo simulation is a concept used in software delivery planning to describe a condition, relationship, estimate, or decision about engineering work.

    Flow and capacity planning

  • Monthly recurring AI spend

    Monthly recurring AI spend is the recurring portion of monthly AI expense for ongoing workloads. It gives teams a way to name, measure, or reason about an economic property of an AI workload without treating raw usage as proof of value.

    Token costs and AI ROI

  • Moving average

    Moving average is a statistical or measurement concept used to describe, compare, or interpret engineering data. Its meaning depends on the unit of analysis, data-generating process, and question being asked.

    Measurement and experimentation

  • Multi Agent Orchestration

    Multi Agent Orchestration is a software-engineering concept describing how an AI coding system, its tools, or human collaborators handle a defined task.

    AI coding and agents

  • Multi-query attention

    Multi-query attention is a language-model concept about evaluation design and failure analysis. It names a mechanism, representation, training practice, or operational behavior that can change how an AI system processes input and produces output.

    LLM fundamentals

  • Multi-region routing

    Multi-region routing is a model-routing or gateway concept used to manage traffic selection for AI requests. It describes a distinct decision, control, interface, or observation point between an application and one or more model providers.

    Model routing and gateways

  • Multilingual evaluation

    Multilingual evaluation is a defined lens for examining AI system behavior with a stated task, evidence, and interpretation rule.

    Evaluations and benchmarks

  • Multiple comparisons

    Multiple comparisons is a statistical or measurement concept used to describe, compare, or interpret engineering data. Its meaning depends on the unit of analysis, data-generating process, and question being asked.

    Measurement and experimentation

  • Mutation score

    Mutation score is a software testing or test-design practice used to gather evidence about a defined risk, behavior, boundary, or operating condition. It makes the question under test explicit, identifies the inputs and observations that matter, and gives a team a repeatable basis for deciding whether the result is acceptable.

    Code quality and technical debt