<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
  <url>
    <loc>https://docs.nvidia.com/aiperf/welcome-to-ai-perf-documentation</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/getting-started/profiling-with-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/getting-started/ai-perf-comprehensive-llm-benchmarking</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/getting-started/migrating-from-gen-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/getting-started/gen-ai-perf-vs-ai-perf-cli-feature-comparison-matrix</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/model-endpoint-guides/profile-open-ai-compatible-text-ap-is-using-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/model-endpoint-guides/profile-the-open-ai-responses-api-with-ai-perf</loc>
    <lastmod>2026-04-13T22:15:22.742Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/model-endpoint-guides/profile-hugging-face-tgi-models-with-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/model-endpoint-guides/profile-vision-language-models-with-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/model-endpoint-guides/profile-audio-language-models-with-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/model-endpoint-guides/profile-embedding-models-with-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/model-endpoint-guides/profile-ranking-models-with-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/model-endpoint-guides/sg-lang-image-generation</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/model-endpoint-guides/sg-lang-video-generation</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/model-endpoint-guides/synthetic-video-generation</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/model-endpoint-guides/template-endpoint</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/datasets-inputs/custom-dataset-guide</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/datasets-inputs/custom-prompt-benchmarking</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/datasets-inputs/profile-with-share-gpt-dataset</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/datasets-inputs/multi-turn-conversations</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/datasets-inputs/sequence-length-distributions-for-advanced-benchmarking</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/datasets-inputs/prefix-data-synthesis-tutorial</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/load-patterns-scheduling/arrival-patterns-simulating-realistic-traffic</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/load-patterns-scheduling/fixed-schedule-benchmarking</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/load-patterns-scheduling/gradual-ramping</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/load-patterns-scheduling/request-rate-with-max-concurrency</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/load-patterns-scheduling/prefill-concurrency-fine-grained-benchmarking-control</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/load-patterns-scheduling/time-based-benchmarking</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/load-patterns-scheduling/multi-url-load-balancing</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/load-patterns-scheduling/request-cancellation-testing</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/load-patterns-scheduling/warmup-phase-configuration</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/metrics-analysis/benchmark-goodput-with-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/metrics-analysis/multi-run-confidence-reporting</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/metrics-analysis/time-slicing-for-performance-analysis</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/metrics-analysis/http-trace-metrics-guide</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/metrics-analysis/working-with-profile-export-files</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/metrics-analysis/visualization-and-plotting-with-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/metrics-analysis/user-centric-timing-for-kv-cache-benchmarking</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/metrics-analysis/gpu-telemetry-with-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/configuration/user-interface</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/configuration/using-local-tokenizers-without-hugging-face</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/tutorials/configuration/random-number-generation-reproducibility</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/benchmark-modes/load-generator-options-reference</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/benchmark-modes/trace-replay-with-mooncake-traces</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/reference/command-line-options</loc>
    <lastmod>2026-04-15T01:00:14.098Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/reference/environment-variables</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/reference/ai-perf-metrics-reference</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/reference/benchmark-datasets</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/reference/pre-flight-tokenizer-auto-detection</loc>
    <lastmod>2026-04-13T20:20:21.883Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/server-metrics/server-metrics-collection</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/server-metrics/ai-perf-server-metrics-reference</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/server-metrics/ai-perf-server-metrics-json-export-schema</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/server-metrics/ai-perf-server-metrics-parquet-export-schema</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/plugins/ai-perf-plugin-system</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/plugins/creating-your-first-ai-perf-plugin</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/api/prefix-synthesis-api-reference</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/architecture-internals/architecture-of-ai-perf</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/architecture-internals/metrics-flow</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/architecture-internals/mixins</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
  <url>
    <loc>https://docs.nvidia.com/aiperf/architecture-internals/ai-perf-code-patterns</loc>
    <lastmod>2026-04-10T23:04:34.184Z</lastmod>
  </url>
</urlset>
