For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
LogoLogoDocumentation
    • Welcome to AIPerf Documentation
  • Getting Started
    • Profiling with AIPerf
    • Comprehensive LLM Benchmarking
    • Migrating from GenAI-Perf
    • GenAI-Perf vs AIPerf CLI Feature Comparison Matrix
  • Tutorials
      • Architecture of AIPerf
      • Metrics Flow
      • Mixins
      • Code Patterns
      • Global Property-Test Invariants
      • Sweep Orchestrator (Dev Reference)
      • YAML Config Future Goals
  • Welcome to AIPerf Documentation
  • Profiling with AIPerf
  • Comprehensive LLM Benchmarking
  • Migrating from GenAI-Perf
  • GenAI-Perf vs AIPerf CLI Feature Comparison Matrix
  • Profile OpenAI-Compatible Text APIs Using AIPerf
  • Profile the OpenAI Responses API with AIPerf
  • Profile Hugging Face TGI Models with AIPerf
  • Profile Vision Language Models with AIPerf
  • Profile Audio Language Models with AIPerf
  • Profile ASR Models with Public Datasets
  • Profile Embedding Models with AIPerf
  • Profile Ranking Models with AIPerf
  • Profile NIM Image Retrieval with AIPerf
  • SGLang Image Generation
  • SGLang Image Edit
  • SGLang Video Generation
  • Synthetic Video Generation
  • Template Endpoint
  • Custom Dataset Guide
  • Inline Datasets
  • Custom Prompt Benchmarking
  • Profile with ShareGPT Dataset
  • Synthetic Dataset Generation
  • Profile with InstructCoder Dataset
  • Profile with AIMO Dataset
  • Profile with MMStar Dataset
  • Profile with MMVU Dataset
  • Profile with LLaVA-OneVision Dataset
  • Profile with VisionArena Dataset
  • Profile with Blazedit Dataset
  • Profile with SpecBench Dataset
  • Profile with SPEED-Bench Dataset
  • Profile with Bailian Traces
  • Profile with BurstGPT Traces
  • Replay SageMaker Data Capture Traces
  • Raw Payload Replay
  • Inputs JSON Replay
  • Multi-Turn Conversations
  • Sequence Length Distributions for Advanced Benchmarking
  • Prefix Data Synthesis Tutorial
  • Agentic Code Dataset Generator
  • Arrival Patterns: Simulating Realistic Traffic
  • Fixed Schedule Benchmarking
  • Gradual Ramping
  • Request Rate with Max Concurrency
  • Prefill Concurrency: Fine-Grained Benchmarking Control
  • Time-Based Benchmarking
  • Multi-URL Load Balancing
  • Request Cancellation Testing
  • Warmup Phase Configuration
  • Benchmark Goodput with AIPerf
  • Multi-Run Confidence Reporting
  • Parameter Sweeps and Multi-Run Statistics
  • Adaptive Search
  • Time Slicing for Performance Analysis
  • HTTP Trace Metrics Guide
  • Working with Profile Export Files
  • Visualization and Plotting with AIPerf
  • Auto-Plot After `aiperf profile`
  • User-Centric Timing for KV Cache Benchmarking
  • GPU Telemetry with AIPerf
  • OTel and MLflow Telemetry
  • YAML Configuration Files
  • Sampling Distributions in YAML Configs
  • User Interface
  • Using Local Tokenizers Without HuggingFace
  • Random Number Generation & Reproducibility
  • Search Recipes
  • Bayesian Optimization
  • Space-filling Sweeps (Sobol, Latin Hypercube)
  • Load Generator Options Reference
  • Trace Replay with Mooncake Traces
  • Conversation DAG Benchmarks
  • Accuracy Benchmarking
  • Command Line Options
  • Environment Variables
  • Metrics Reference
  • Benchmark Datasets
  • Pre-Flight Tokenizer Auto Detection
  • Conversation Context Mode
  • List-Metric Aggregation
  • Vendor Usage Field Reference
  • JSON Export Schema
  • HTTP API Endpoints
  • YAML Config Roadmap
  • Server Metrics Collection
  • Server Metrics Reference
  • Server Metrics JSON Export Schema
  • Server Metrics Parquet Export Schema
  • Plugin System
  • Creating Your First AIPerf Plugin
  • Prefix Synthesis API Reference
  • Sweep Aggregates API Reference
  • Search History API Reference
  • Architecture of AIPerf
  • Metrics Flow
  • Mixins
  • Code Patterns
  • Global Property-Test Invariants
  • Sweep Orchestrator (Dev Reference)
  • YAML Config Future Goals
  • Sweep & Adaptive Search Errors
Architecture & Internals

Mixins

||View as Markdown|
Previous

Metrics Flow

Next

Code Patterns

NVIDIANVIDIA
Developer-friendly docs for your API
Privacy Policy | Your Privacy Choices | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2026, NVIDIA Corporation.