{
  "artifacts": [
    {
      "file": "5661d44b4bac479f17576dd5b2c14554e7924ab4d273ae14ddd6482b3fb81cab.tflite",
      "sha256": "ced5f52bef6e76ad4a66d1055b2b404336ceafbae8eeac8fed6aa9c7b2e4d776",
      "size_mb": 0.244
    }
  ],
  "benchmarks": [],
  "browser": {
    "backends": [
      {
        "backend": "wasm_xnnpack",
        "date": "2026-08-11",
        "env": {
          "browser": "chromium",
          "browser_version": "151.0.7922.34",
          "headless": true,
          "jspi": true,
          "litertjs_core_version": "2.5.3",
          "machine_label": "mac-studio-m4-max",
          "os": "macOS",
          "os_version": "27.0.0",
          "webgpu_adapter": {
            "architecture": "metal-3",
            "description": "",
            "device": "",
            "vendor": "apple"
          }
        },
        "full_delegation": null,
        "latency_p50_ms": 140.42,
        "loads": true,
        "max_rel_diff": null,
        "output_match": null,
        "provenance": "measured",
        "runs": true
      },
      {
        "backend": "webgpu_mldrift",
        "date": "2026-08-11",
        "env": {
          "browser": "chromium",
          "browser_version": "151.0.7922.34",
          "headless": true,
          "jspi": true,
          "litertjs_core_version": "2.5.3",
          "machine_label": "mac-studio-m4-max",
          "os": "macOS",
          "os_version": "27.0.0",
          "webgpu_adapter": {
            "architecture": "metal-3",
            "description": "",
            "device": "",
            "vendor": "apple"
          }
        },
        "full_delegation": true,
        "latency_p50_ms": 6.527,
        "loads": true,
        "max_rel_diff": 0.013726315789473684,
        "output_match": true,
        "provenance": "measured",
        "runs": true
      }
    ],
    "demo_url": null,
    "sweep_source": "data/sweep/2.5.3/2026-08-11/yunet-face.json"
  },
  "conversion": {
    "command": "python yunet/scripts/build_yunet.py",
    "quantization": "fp16",
    "tool": "litert-torch",
    "tool_version": "0.10.0 (editable dev checkout 115a136 + local patches)"
  },
  "cross_runtime": [],
  "delegation": null,
  "device": {
    "records": [
      {
        "device": "galaxy-s26",
        "run": {
          "accelerator": "gpu_mldrift",
          "context_length": null,
          "date": "2026-08-25",
          "decode_tokens_per_s": null,
          "delegated_ops": null,
          "env": {
            "device": "Galaxy S26 (SM-S942Q)",
            "machine_label": "galaxy-s26-npubench",
            "os_build": "Android 16",
            "runtime": "litert",
            "runtime_version": "2.2.0",
            "soc": "Qualcomm SM8850",
            "vendor_sdk": null
          },
          "error": null,
          "evidence": [
            "npubench sweep row: N=50 median, 1 backend = 1 process, accepted only with thermal NONE->NONE; NPU rows additionally required qnn_partition delegate evidence in logcat (a stock model asked for on the NPU can silently land on XNNPACK and report a CPU number)",
            "mode=jit thermal=NONE->NONE headroom=0.5366667->0.5366667 attempt=0"
          ],
          "failure_class": null,
          "full_delegation": null,
          "latency_p50_ms": 3.315,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "iterations": 50,
            "latency_max_ms": 3.633,
            "latency_min_ms": 2.197,
            "load_ms": 577.2
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": null,
          "provenance": "measured",
          "runs": true,
          "total_ops": null,
          "ttft_ms": null
        },
        "source": "data/device_runs/2.2.0/2026-08-25/yunet-face__galaxy-s26.json"
      },
      {
        "device": "galaxy-s26",
        "run": {
          "accelerator": "npu_qnn",
          "context_length": null,
          "date": "2026-08-25",
          "decode_tokens_per_s": null,
          "delegated_ops": null,
          "env": {
            "device": "Galaxy S26 (SM-S942Q)",
            "machine_label": "galaxy-s26-npubench",
            "os_build": "Android 16",
            "runtime": "litert",
            "runtime_version": "2.2.0",
            "soc": "Qualcomm SM8850",
            "vendor_sdk": "QAIRT (Hexagon, JIT on-device)"
          },
          "error": null,
          "evidence": [
            "npubench sweep row: N=50 median, 1 backend = 1 process, accepted only with thermal NONE->NONE; NPU rows additionally required qnn_partition delegate evidence in logcat (a stock model asked for on the NPU can silently land on XNNPACK and report a CPU number)",
            "mode=jit thermal=NONE->NONE headroom=0.53333336->0.53333336 attempt=0"
          ],
          "failure_class": null,
          "full_delegation": null,
          "latency_p50_ms": 1.85,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "iterations": 50,
            "jit_first_load_ms": 979.3,
            "latency_max_ms": 1.908,
            "latency_min_ms": 1.803,
            "load_ms": 100.4,
            "qnn_partition_lines": 57
          },
          "output_match": null,
          "peak_mem_mb": null,
          "prefill_tokens_per_s": null,
          "provenance": "measured",
          "runs": true,
          "total_ops": null,
          "ttft_ms": null
        },
        "source": "data/device_runs/2.2.0/2026-08-25/yunet-face__galaxy-s26.json"
      },
      {
        "device": "raspberry-pi-5",
        "run": {
          "accelerator": "cpu_xnnpack",
          "context_length": null,
          "date": "2026-08-31",
          "decode_tokens_per_s": null,
          "delegated_ops": null,
          "env": {
            "device": "Raspberry Pi 5 Model B Rev 1.1",
            "machine_label": "raspberry-pi-5",
            "os_build": "Linux-6.18.34+rpt-rpi-2712-aarch64-with-glibc2.41",
            "runtime": "litert",
            "runtime_version": "2.2.0.dev20260804",
            "soc": null,
            "vendor_sdk": null
          },
          "error": null,
          "evidence": [
            "pi5 sweep row: LiteRT benchmark_model, CPU/XNNPACK at --num_threads=4, 3 invocations per file of 10 warm-up + 50 timed runs (the tool caps a phase at 150 s, so very slow graphs run fewer); latency = median of the three per-invocation medians over the timed phase; a row counts as measured only when every invocation exited 0 with XNNPACK engaged and vcgencmd get_throttled 0x0 before and after",
            "versions: ai-edge-litert-nightly=2.2.0.dev20260804, benchmark_model_sha256=babc9275addd8612caf0842294cb5b3f301c3cce46e6c5979cd2803f215f6bee, cpu=Raspberry Pi 5 Model B Rev 1.1, litert-cli-nightly=0.2.0.dev20260805, platform=Linux-6.18.34+rpt-rpi-2712-aarch64-with-glibc2.41, python=3.13.5",
            "invocation 0: exit=0 wall_s=2.2 temp 51.6->59.8C throttled=0x0 xnnpack=True median_us=33849.0 runs=50 footprint_peak_mb=137.5",
            "invocation 1: exit=0 wall_s=2.2 temp 51.6->60.9C throttled=0x0 xnnpack=True median_us=33696.0 runs=50 footprint_peak_mb=137.5",
            "invocation 2: exit=0 wall_s=2.2 temp 51.6->58.2C throttled=0x0 xnnpack=True median_us=33632.0 runs=50 footprint_peak_mb=137.5"
          ],
          "failure_class": null,
          "full_delegation": null,
          "latency_p50_ms": 33.696,
          "loads": true,
          "max_abs_diff": null,
          "max_rel_diff": null,
          "metrics": {
            "init_ms": 3.159,
            "invocations": 3,
            "iterations": 150,
            "latency_max_ms": 35.201,
            "latency_min_ms": 33.432,
            "threads": 4,
            "warmup_runs_per_invocation": 10
          },
          "output_match": null,
          "peak_mem_mb": 137.5,
          "prefill_tokens_per_s": null,
          "provenance": "measured",
          "runs": true,
          "total_ops": null,
          "ttft_ms": null
        },
        "source": "data/device_runs/2.2.0.dev20260804/2026-08-31/yunet-face__raspberry-pi-5.json"
      }
    ]
  },
  "model": {
    "family": "yunet",
    "id": "yunet-face",
    "license": "bsd-3-clause",
    "source_url": "https://huggingface.co/litert-community/YuNet-Face-LiteRT",
    "task": "object-detection"
  },
  "pitfalls": [
    "Input is BGR, 0-255, no normalization, letterboxed to 640x640; decode (priors + center/exp box + 5 landmarks + NMS over the 12 raw per-stride outputs) runs in the app (zoo README L1669-1675)."
  ],
  "schema_version": "1.2"
}