> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/aiperf/v0.13.0/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/aiperf/_mcp/server.

# v0.13.0

## Docs

- [Welcome to AIPerf Documentation](https://docs.nvidia.com/aiperf/v0.13.0/welcome-to-ai-perf-documentation.md)
- [Profiling with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/getting-started/profiling-with-ai-perf.md)
- [Comprehensive LLM Benchmarking](https://docs.nvidia.com/aiperf/v0.13.0/getting-started/ai-perf-comprehensive-llm-benchmarking.md)
- [Interactive Chat Sanity Checks](https://docs.nvidia.com/aiperf/v0.13.0/getting-started/interactive-chat-sanity-checks.md)
- [Migrating from GenAI-Perf](https://docs.nvidia.com/aiperf/v0.13.0/getting-started/migrating-from-gen-ai-perf.md)
- [GenAI-Perf vs AIPerf CLI Feature Comparison Matrix](https://docs.nvidia.com/aiperf/v0.13.0/getting-started/gen-ai-perf-vs-ai-perf-cli-feature-comparison-matrix.md)
- [Profile OpenAI-Compatible Text APIs Using AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/profile-open-ai-compatible-text-ap-is-using-ai-perf.md)
- [Profile the OpenAI Responses API with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/profile-the-open-ai-responses-api-with-ai-perf.md)
- [Profile the Anthropic Messages API with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/profile-the-anthropic-messages-api-with-ai-perf.md)
- [Profile Hugging Face TGI Models with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/profile-hugging-face-tgi-models-with-ai-perf.md)
- [Profile Vision Language Models with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/profile-vision-language-models-with-ai-perf.md)
- [Profile Audio Language Models with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/profile-audio-language-models-with-ai-perf.md)
- [Profile ASR Models with Public Datasets](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/profile-asr-models-with-ai-perf.md)
- [Profile Embedding Models with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/profile-embedding-models-with-ai-perf.md)
- [Profile Ranking Models with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/profile-ranking-models-with-ai-perf.md)
- [Profile NIM Image Retrieval with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/profile-nim-image-retrieval-with-ai-perf.md)
- [SGLang Image Generation](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/sg-lang-image-generation.md)
- [SGLang Image Edit](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/sg-lang-image-edit.md)
- [SGLang Video Generation](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/sg-lang-video-generation.md)
- [Synthetic Video Generation](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/synthetic-video-generation.md)
- [Template Endpoint](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/model-endpoint-guides/template-endpoint.md)
- [Custom Dataset Guide](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/custom-dataset-guide.md)
- [Inline Datasets](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/inline-datasets.md)
- [Custom Prompt Benchmarking](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/custom-prompt-benchmarking.md)
- [Profile with ShareGPT Dataset](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-share-gpt-dataset.md)
- [Synthetic Dataset Generation](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/synthetic-dataset-generation.md)
- [Profile with InstructCoder Dataset](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-instruct-coder-dataset.md)
- [Profile with AIMO Dataset](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-aimo-dataset.md)
- [Profile with MMStar Dataset](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-mm-star-dataset.md)
- [Profile with MMVU Dataset](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-mmvu-dataset.md)
- [Profile with LLaVA-OneVision Dataset](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-l-la-va-one-vision-dataset.md)
- [Profile with VisionArena Dataset](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-vision-arena-dataset.md)
- [Profile with Blazedit Dataset](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-blazedit-dataset.md)
- [Profile with SpecBench Dataset](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-spec-bench-dataset.md)
- [Profile with SPEED-Bench Dataset](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-speed-bench-dataset.md)
- [Per-Request Spec-Decode Metrics](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/per-request-speculative-decoding-metrics.md)
- [Profile with Bailian Traces](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-bailian-traces.md)
- [Profile with BurstGPT Traces](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/profile-with-burst-gpt-traces.md)
- [Replay SageMaker Data Capture Traces](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/replay-sage-maker-data-capture-traces.md)
- [Raw Payload Replay](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/raw-payload-replay.md)
- [Inputs JSON Replay](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/inputs-json-replay.md)
- [Multi-Turn Conversations](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/multi-turn-conversations.md)
- [Sequence Length Distributions for Advanced Benchmarking](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/sequence-length-distributions-for-advanced-benchmarking.md)
- [Prefix Data Synthesis Tutorial](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/prefix-data-synthesis-tutorial.md)
- [Agentic Code Dataset Generator](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/agentic-code-dataset-generator.md)
- [Replay Weka Agentic Coding Traces](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/replay-weka-agentic-coding-traces.md)
- [Replay TraceLab Agentic Coding Traces](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/replay-trace-lab-agentic-coding-traces.md)
- [InferenceX AgentX MVP Benchmark](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/datasets-inputs/inference-x-agent-x-mvp-benchmark.md)
- [Arrival Patterns: Simulating Realistic Traffic](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/arrival-patterns-simulating-realistic-traffic.md)
- [Fixed Schedule Benchmarking](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/fixed-schedule-benchmarking.md)
- [Gradual Ramping](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/gradual-ramping.md)
- [Request Rate with Max Concurrency](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/request-rate-with-max-concurrency.md)
- [Prefill Concurrency: Fine-Grained Benchmarking Control](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/prefill-concurrency-fine-grained-benchmarking-control.md)
- [Adaptive Scale](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/adaptive-scale.md)
- [Multi-Phase Workflows](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/multi-phase-workflows.md)
- [Time-Based Benchmarking](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/time-based-benchmarking.md)
- [Multi-URL Load Balancing](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/multi-url-load-balancing.md)
- [Request Cancellation Testing](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/request-cancellation-testing.md)
- [Warmup Phase Configuration](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/warmup-phase-configuration.md)
- [Benchmark Control Hooks](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/benchmark-control-hooks.md)
- [Control Hooks by Server (vLLM / SGLang / TRT-LLM)](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/load-patterns-scheduling/control-hooks-by-server-v-llm-sg-lang-trt-llm.md)
- [Benchmark Goodput with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/benchmark-goodput-with-ai-perf.md)
- [Multi-Run Confidence Reporting](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/multi-run-confidence-reporting.md)
- [Parameter Sweeps and Multi-Run Statistics](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/parameter-sweeps.md)
- [Adaptive Search](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/adaptive-search.md)
- [Adaptive Scale](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/adaptive-scale.md)
- [Time Slicing for Performance Analysis](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/time-slicing-for-performance-analysis.md)
- [HTTP Trace Metrics Guide](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/http-trace-metrics-guide.md)
- [Working with Profile Export Files](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/working-with-profile-export-files.md)
- [Visualization and Plotting with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/visualization-and-plotting-with-ai-perf.md)
- [Auto-Plot After `aiperf profile`](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/auto-plot-after-aiperf-profile.md)
- [User-Centric Timing for KV Cache Benchmarking](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/user-centric-timing-for-kv-cache-benchmarking.md)
- [GPU Telemetry with AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/gpu-telemetry-with-ai-perf.md)
- [OTel and MLflow Telemetry](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/open-telemetry-m-lflow-integration.md)
- [Weights & Biases Export](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/metrics-analysis/weights-biases-export.md)
- [YAML Configuration Files](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/configuration/yaml-configuration-files.md)
- [Sampling Distributions in YAML Configs](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/configuration/sampling-distributions-in-yaml-configs.md)
- [User Interface](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/configuration/user-interface.md)
- [Using Local Tokenizers Without HuggingFace](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/configuration/using-local-tokenizers-without-hugging-face.md)
- [Random Number Generation & Reproducibility](https://docs.nvidia.com/aiperf/v0.13.0/tutorials/configuration/random-number-generation-reproducibility.md)
- [Search Recipes](https://docs.nvidia.com/aiperf/v0.13.0/sweeping-adaptive-search/search-recipes.md)
- [Bayesian Optimization](https://docs.nvidia.com/aiperf/v0.13.0/sweeping-adaptive-search/bayesian-optimization.md)
- [Space-filling Sweeps (Sobol, Latin Hypercube)](https://docs.nvidia.com/aiperf/v0.13.0/sweeping-adaptive-search/space-filling-sweeps-sobol-latin-hypercube.md)
- [Load Generator Options Reference](https://docs.nvidia.com/aiperf/v0.13.0/benchmark-modes/load-generator-options-reference.md)
- [Trace Replay with Mooncake Traces](https://docs.nvidia.com/aiperf/v0.13.0/benchmark-modes/trace-replay-with-mooncake-traces.md)
- [Baseten Traces](https://docs.nvidia.com/aiperf/v0.13.0/benchmark-modes/baseten-trace-replay.md)
- [Conversation DAG Benchmarks](https://docs.nvidia.com/aiperf/v0.13.0/benchmark-modes/conversation-dag-benchmarks.md)
- [Getting Started on Kubernetes](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/getting-started-on-kubernetes.md)
- [Source Checkout Deployment](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/deploy-from-source-checkout.md)
- [End-to-End Workflow](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/end-to-end-workflow.md)
- [Config Init and Manifest Generation](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/config-init-and-manifest-generation.md)
- [Kubernetes Configuration](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/kubernetes-configuration-reference.md)
- [Production Deployments](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/production-deployment.md)
- [RBAC and Security](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/rbac-and-security.md)
- [Monitoring and Troubleshooting](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/monitoring-and-observability.md)
- [Config Validation](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/config-validation.md)
- [CRD Validation Rules](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/crd-validation-rules.md)
- [Preflight Checks](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/preflight-checks.md)
- [Debug Command](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/debug-command.md)
- [Attach to a Running Benchmark](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/attach-to-a-running-benchmark.md)
- [Logs](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/logs.md)
- [Results Server API Reference](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/results-server-api-reference.md)
- [Web Dashboard](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/web-dashboard.md)
- [Controller Pod Sidecars](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/controller-pod-sidecars.md)
- [Memory Estimator](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/memory-estimator.md)
- [Kueue Integration](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/kueue-integration.md)
- [GPU Telemetry on Kubernetes](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/gpu-telemetry-on-kubernetes.md)
- [Direct Mode (no operator)](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/direct-mode-no-operator.md)
- [Adaptive Search on Kubernetes](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/adaptive-search-on-kubernetes.md)
- [User-Defined Output Files](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/user-defined-output-files.md)
- [AI Agent Debugging Guide](https://docs.nvidia.com/aiperf/v0.13.0/kubernetes/ai-assisted-debugging-guide.md)
- [Accuracy Benchmarking](https://docs.nvidia.com/aiperf/v0.13.0/accuracy/accuracy-benchmarking.md)
- [Command Line Options](https://docs.nvidia.com/aiperf/v0.13.0/reference/command-line-options.md)
- [Environment Variables](https://docs.nvidia.com/aiperf/v0.13.0/reference/environment-variables.md)
- [Metrics Reference](https://docs.nvidia.com/aiperf/v0.13.0/reference/ai-perf-metrics-reference.md)
- [GPU Telemetry & Power-Efficiency Dataflow](https://docs.nvidia.com/aiperf/v0.13.0/reference/gpu-telemetry-power-efficiency-dataflow.md)
- [Benchmark Datasets](https://docs.nvidia.com/aiperf/v0.13.0/reference/benchmark-datasets.md)
- [Pre-Flight Tokenizer Auto Detection](https://docs.nvidia.com/aiperf/v0.13.0/reference/pre-flight-tokenizer-auto-detection.md)
- [Input Sequence Length (ISL) Tokenization](https://docs.nvidia.com/aiperf/v0.13.0/reference/input-sequence-length-isl-tokenization.md)
- [Prompt Corpus Selection](https://docs.nvidia.com/aiperf/v0.13.0/reference/prompt-corpus-selection.md)
- [Validating ISL/OSL Distributions with the Mock Server](https://docs.nvidia.com/aiperf/v0.13.0/reference/validating-isl-osl-distributions-with-the-mock-server.md)
- [ISL Budget Compensation Derivation](https://docs.nvidia.com/aiperf/v0.13.0/reference/isl-budget-compensation-derivation.md)
- [Conversation Context Mode](https://docs.nvidia.com/aiperf/v0.13.0/reference/conversation-context-mode.md)
- [List-Metric Aggregation](https://docs.nvidia.com/aiperf/v0.13.0/reference/list-metric-aggregation.md)
- [Effective vs Active Metrics](https://docs.nvidia.com/aiperf/v0.13.0/reference/effective-vs-active-metrics.md)
- [Vendor Usage Field Reference](https://docs.nvidia.com/aiperf/v0.13.0/reference/vendor-usage-field-reference.md)
- [Per-Request Speculative-Decoding Acceptance](https://docs.nvidia.com/aiperf/v0.13.0/reference/per-request-speculative-decoding-acceptance.md)
- [JSON Export Schema](https://docs.nvidia.com/aiperf/v0.13.0/reference/json-export-schema.md)
- [HTTP API Endpoints](https://docs.nvidia.com/aiperf/v0.13.0/reference/http-api-endpoints.md)
- [Cache-Bust Targets](https://docs.nvidia.com/aiperf/v0.13.0/reference/cache-bust-targets.md)
- [YAML Config Roadmap](https://docs.nvidia.com/aiperf/v0.13.0/reference/yaml-config-roadmap.md)
- [Mocking a ROCm Environment](https://docs.nvidia.com/aiperf/v0.13.0/reference/mocking-a-ro-cm-environment.md)
- [Server Metrics Collection](https://docs.nvidia.com/aiperf/v0.13.0/server-metrics/server-metrics-collection.md)
- [Server Metrics Reference](https://docs.nvidia.com/aiperf/v0.13.0/server-metrics/ai-perf-server-metrics-reference.md)
- [Server Metrics JSON Export Schema](https://docs.nvidia.com/aiperf/v0.13.0/server-metrics/ai-perf-server-metrics-json-export-schema.md)
- [Server Metrics Parquet Export Schema](https://docs.nvidia.com/aiperf/v0.13.0/server-metrics/ai-perf-server-metrics-parquet-export-schema.md)
- [Plugin System](https://docs.nvidia.com/aiperf/v0.13.0/plugins/ai-perf-plugin-system.md)
- [Creating Your First AIPerf Plugin](https://docs.nvidia.com/aiperf/v0.13.0/plugins/creating-your-first-ai-perf-plugin.md)
- [Prefix Synthesis API Reference](https://docs.nvidia.com/aiperf/v0.13.0/api/prefix-synthesis-api-reference.md)
- [Sweep Aggregates API Reference](https://docs.nvidia.com/aiperf/v0.13.0/api/sweep-aggregates-api-reference.md)
- [Search History API Reference](https://docs.nvidia.com/aiperf/v0.13.0/api/search-history-api-reference.md)
- [Architecture of AIPerf](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/architecture-of-ai-perf.md)
- [Metrics Flow](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/metrics-flow.md)
- [Mixins](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/mixins.md)
- [Code Patterns](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/ai-perf-code-patterns.md)
- [Global Property-Test Invariants](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/global-property-test-invariants.md)
- [Sweep Orchestrator (Dev Reference)](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/sweep-orchestrator-dev-reference.md)
- [YAML Config Future Goals](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/yaml-config-future-goals.md)
- [Kubernetes Flow](https://docs.nvidia.com/aiperf/v0.13.0/architecture-internals/kubernetes-flow.md)
- [Sweep & Adaptive Search Errors](https://docs.nvidia.com/aiperf/v0.13.0/troubleshooting/sweep-adaptive-search-errors.md)