Llms Glossary
Browse 47 llms terms defined in plain English, from the cultural dictionary of computing.
47 Llms Terms
- Context Window Limit
- The maximum amount of input and generated token context a model can handle in one request.
- Decoder-Only Transformer
- A transformer architecture that predicts the next token from prior context without using a separate encoder, which is the common design behind many modern...
- DeepSeek
- A family of AI models and related company identity associated with high-profile open or semi-open language-model releases.
- Gemini Model
- A model in Google's Gemini family, commonly discussed in the context of multimodal AI, assistants, and foundation-model competition.
- Grok Model
- A model from the Grok family associated with xAI and public discussion around chat assistants and frontier-model competition.
- Llama Model
- A model from Meta's Llama family, widely discussed in open-model ecosystems, fine-tuning, and local inference workflows.
- LLM-as-Judge
- An evaluation pattern where one language model grades, compares, or scores the outputs of another model according to a rubric or prompt.
- LLM Benchmark
- A benchmark used specifically to evaluate large language models on tasks such as reasoning, coding, factuality, tool use, or safety. LLM benchmarks are useful...
- LLM Cache
- A cache used to store and reuse large language model outputs or related intermediate results so repeated requests do not trigger full generation again. LLM...
- LLM Calling
- The act or pattern of invoking a large language model from application code, a workflow engine, or another model-mediated system. The phrase often comes up...
- LLM Chain
- A sequence of large language model calls or model-driven steps linked together to complete a larger task. LLM chains can combine summarization, retrieval,...
- LLM Completion
- A completion or generated output produced by a large language model in response to a prompt. The term often refers specifically to text generation APIs or the...
- LLM Config
- The configuration used for a large language model workflow, including model choice, temperature, max tokens, system prompts, tool settings, and routing rules....
- LLM Cost
- The cost associated with using a large language model, including API charges, compute resources, and surrounding operational overhead. LLM cost is closely...
- LLM Gateway
- A gateway layer that centralizes access to one or more large language models and often handles authentication, logging, rate limits, policy enforcement, and...
- LLM Judge
- A large language model used to evaluate, rank, or critique the outputs of another model or system according to some rubric. LLM-as-judge approaches can scale...
- LLM Memory
- The mechanisms by which a large language model system retains or reuses relevant information across turns, tasks, or sessions. LLM memory may involve...
- LLM Observability
- The practice of instrumenting and analyzing large language model systems so teams can understand their behavior, performance, cost, and failure modes. LLM...
- LLM Optimization
- Improving a large language model workflow for quality, speed, reliability, or cost through changes to prompts, routing, context management, evaluation, or...
- LLM Output
- The text, structure, or tool call returned by a large language model after processing a prompt. LLM output often needs validation or post-processing before it...
- LLM Pipeline
- A pipeline built around large language model interactions, often including retrieval, prompt assembly, inference, validation, and downstream actions. LLM...
- LLM Platform
- A shared platform that gives teams standardized access to large language models along with tooling for prompts, evaluations, logging, and governance. LLM...
- LLM Plugin
- A plugin that adds large language model capabilities to an application, or a plugin that lets an LLM interact with external functions or data sources. The term...
- LLM Prompt
- The prompt used for a large language model, including instructions, examples, formatting constraints, and context. LLM prompts are often versioned and tuned...
- LLM Provider
- A provider that offers access to large language models through APIs, hosted infrastructure, or platform tooling. Teams compare LLM providers on quality,...
- LLM Proxy
- A proxy service that sits between applications and large language models to add routing, logging, caching, security, or compatibility layers. An LLM proxy can...
- LLM Reliability
- The extent to which a large language model system behaves consistently and acceptably across repeated use, edge cases, and operational conditions. Reliability...
- LLM Request
- A request made to a large language model, including the prompt, context, settings, and any tools or metadata attached to the call. Tracking LLM requests...
- LLM Response
- The response returned by a large language model after processing a request. Depending on the system, an LLM response may include text, structured fields, tool...
- LLM Router
- A routing component that decides which large language model should handle a request based on task type, cost, latency, policy, or capacity. LLM routers help...
- LLM Scale
- The operational or capability scale at which large language model systems are run, whether measured in traffic, context size, model size, or organizational...
- LLM SDK
- A software development kit for integrating large language models more conveniently than working with raw endpoints directly. LLM SDKs usually help with typed...
- LLM Security
- The security discipline around large language model systems, including prompt injection defenses, data protection, access control, abuse prevention, and safe...
- LLM Server
- A server that hosts or brokers access to one or more large language models for applications or internal users. LLM servers may perform model serving directly...
- LLM Service
- A service that exposes large language model capabilities to other systems, typically with an API and surrounding operational logic. LLM services often package...
- LLM Streaming
- The incremental delivery of large language model output as it is generated rather than only after completion finishes. LLM streaming improves perceived...
- LLM Throughput
- The rate at which a large language model system can process requests or generate tokens over time. Throughput matters for capacity planning, queueing behavior,...
- LLM Token
- A token as used in the context of large language models, counted toward prompt size, generation limits, and billing. LLM token usage is closely monitored...
- LLM Tool
- A tool made available to a large language model system so it can access external data or perform actions beyond plain text generation. LLM tools are central to...
- LLM Trace
- A trace showing the full path of a large language model request through prompts, retrieval, model calls, tool interactions, and post-processing. LLM traces are...
- LLM Workflow
- A workflow in which large language models play one or more central roles, often alongside retrieval, tools, review, and business logic. The phrase emphasizes...
- LLM Wrapper
- A wrapper around large language model APIs that hides provider details and exposes a cleaner project-specific interface. LLM wrappers are common when teams...
- Multimodal Model
- A model that can process or generate across more than one data type, such as text, images, audio, or video.
- Phi Model
- A model in Microsoft's Phi family, often noted for strong performance from comparatively small model sizes.
- Qwen Model
- A model from the Qwen family, commonly referenced in open-model comparisons and multilingual language-model discussions.
- Retrieval Augmented Generation
- A pattern where a model first retrieves relevant documents or facts and then uses them while generating an answer.
- RoPE
- Short for Rotary Positional Embedding, a positional method used in transformer models to encode token order in attention calculations.
Related Topics
- Ai (35 terms in common)
- Vendors (3 terms in common)
- Open Models (3 terms in common)
- Evaluation (3 terms in common)
- Transformers (2 terms in common)
- Pipelines (2 terms in common)
- Tokens (2 terms in common)
- Vision (1 terms in common)
- Routing (1 terms in common)
- Architecture (1 terms in common)
- Generation (1 terms in common)
- Configuration (1 terms in common)
- Outputs (1 terms in common)
- Microsoft (1 terms in common)
- Retrieval (1 terms in common)
- Google (1 terms in common)
- Memory (1 terms in common)
- Sdks (1 terms in common)
- Responses (1 terms in common)
- Small Models (1 terms in common)