{
  "model": "LiquidAI/d1-omni-600M",
  "revision": "02b55d7076f15129e59ab3f94783f32c4b088674",
  "date_utc": "2026-10-09T18:05:45.361657+00:00",
  "environment": {
    "torch": "2.8.0+cu128",
    "transformers": "5.17.0",
    "huggingface_hub": "1.33.0"
  },
  "gpu": "NVIDIA RTX PRO 6000 Blackwell Server Edition",
  "gpu_total_bytes": 101975851008,
  "cuda": "12.8",
  "cases": [
    {
      "label": "cuda_fp16_text_0",
      "dtype": "float16",
      "input": "I was charged twice. Please refund the duplicate payment.",
      "expected_choice": "billing",
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        8.254455402493477,
        7.310966029763222,
        7.174380123615265
      ],
      "result": {
        "answers": {
          "team": {
            "type": "choice",
            "choice": "billing",
            "confidence": 0.9713873863220215,
            "probabilities": {
              "billing": 0.9713873863220215,
              "technical": 0.028612619265913963
            }
          }
        },
        "usage": {
          "input_tokens": 45,
          "output_tokens": 0
        }
      },
      "classification_correct": true,
      "peak_allocated_bytes": 1197767168,
      "peak_reserved_bytes": 1212153856,
      "nvidia_smi_used_mib": "1849",
      "process_max_rss_kib": 4261532
    },
    {
      "label": "cuda_fp16_text_1",
      "dtype": "float16",
      "input": "The application crashes at startup. Please help me fix it.",
      "expected_choice": "technical",
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        7.308522239327431,
        7.180800661444664,
        7.183875888586044
      ],
      "result": {
        "answers": {
          "team": {
            "type": "choice",
            "choice": "technical",
            "confidence": 0.9956815242767334,
            "probabilities": {
              "billing": 0.0043184831738471985,
              "technical": 0.9956815242767334
            }
          }
        },
        "usage": {
          "input_tokens": 46,
          "output_tokens": 0
        }
      },
      "classification_correct": true,
      "peak_allocated_bytes": 1197789696,
      "peak_reserved_bytes": 1212153856,
      "nvidia_smi_used_mib": "1849",
      "process_max_rss_kib": 4261532
    },
    {
      "label": "cuda_fp16_text_repeats10",
      "dtype": "float16",
      "state_repetitions": 10,
      "expected_choice": "billing",
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        10.331137105822563,
        7.299182936549187,
        7.324641570448875
      ],
      "result": {
        "answers": {
          "team": {
            "type": "choice",
            "choice": "billing",
            "confidence": 0.9836205244064331,
            "probabilities": {
              "billing": 0.9836205244064331,
              "technical": 0.016379492357373238
            }
          }
        },
        "usage": {
          "input_tokens": 145,
          "output_tokens": 0
        }
      },
      "classification_correct": true,
      "peak_allocated_bytes": 1201516544,
      "peak_reserved_bytes": 1214251008,
      "nvidia_smi_used_mib": "1851",
      "process_max_rss_kib": 4261532
    },
    {
      "label": "cuda_fp16_text_repeats40",
      "dtype": "float16",
      "state_repetitions": 40,
      "expected_choice": "billing",
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        8.03447887301445,
        7.772022858262062,
        7.505703717470169
      ],
      "result": {
        "answers": {
          "team": {
            "type": "choice",
            "choice": "billing",
            "confidence": 0.981817901134491,
            "probabilities": {
              "billing": 0.981817901134491,
              "technical": 0.01818203739821911
            }
          }
        },
        "usage": {
          "input_tokens": 475,
          "output_tokens": 0
        }
      },
      "classification_correct": true,
      "peak_allocated_bytes": 1217928704,
      "peak_reserved_bytes": 1243611136,
      "nvidia_smi_used_mib": "1881",
      "process_max_rss_kib": 4261532
    },
    {
      "label": "cuda_fp16_text_repeats160",
      "dtype": "float16",
      "state_repetitions": 160,
      "expected_choice": "billing",
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        12.848937883973122,
        12.62974739074707,
        12.569459155201912
      ],
      "result": {
        "answers": {
          "team": {
            "type": "choice",
            "choice": "billing",
            "confidence": 0.951725959777832,
            "probabilities": {
              "billing": 0.951725959777832,
              "technical": 0.04827399179339409
            }
          }
        },
        "usage": {
          "input_tokens": 1795,
          "output_tokens": 0
        }
      },
      "classification_correct": true,
      "peak_allocated_bytes": 1637544448,
      "peak_reserved_bytes": 1755316224,
      "nvidia_smi_used_mib": "2369",
      "process_max_rss_kib": 4261532
    },
    {
      "label": "cuda_fp16_text_repeats640",
      "dtype": "float16",
      "state_repetitions": 640,
      "expected_choice": "billing",
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        66.08821265399456,
        65.99919870495796,
        65.94854965806007
      ],
      "result": {
        "answers": {
          "team": {
            "type": "choice",
            "choice": "billing",
            "confidence": 0.9268376231193542,
            "probabilities": {
              "billing": 0.9268376231193542,
              "technical": 0.07316235452890396
            }
          }
        },
        "usage": {
          "input_tokens": 7075,
          "output_tokens": 0
        }
      },
      "classification_correct": true,
      "peak_allocated_bytes": 7720559104,
      "peak_reserved_bytes": 8164212736,
      "nvidia_smi_used_mib": "8481",
      "process_max_rss_kib": 4261532
    },
    {
      "label": "cuda_fp16_batch2",
      "dtype": "float16",
      "batch_size": 2,
      "expected_choices": [
        "billing",
        "technical"
      ],
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        7.917901501059532,
        7.537534460425377,
        7.2609540075063705
      ],
      "result": [
        {
          "answers": {
            "team": {
              "type": "choice",
              "choice": "billing",
              "confidence": 0.9714184403419495,
              "probabilities": {
                "billing": 0.9714184403419495,
                "technical": 0.02858154848217964
              }
            }
          },
          "usage": {
            "input_tokens": 45,
            "output_tokens": 0
          }
        },
        {
          "answers": {
            "team": {
              "type": "choice",
              "choice": "technical",
              "confidence": 0.9957055449485779,
              "probabilities": {
                "billing": 0.004294505808502436,
                "technical": 0.9957055449485779
              }
            }
          },
          "usage": {
            "input_tokens": 46,
            "output_tokens": 0
          }
        }
      ],
      "classification_correct": true,
      "peak_allocated_bytes": 1199209472,
      "peak_reserved_bytes": 8164212736,
      "nvidia_smi_used_mib": "8481",
      "process_max_rss_kib": 4261532
    },
    {
      "label": "cuda_fp16_batch8",
      "dtype": "float16",
      "batch_size": 8,
      "expected_choices": [
        "billing",
        "technical",
        "billing",
        "technical",
        "billing",
        "technical",
        "billing",
        "technical"
      ],
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        8.727919310331345,
        8.608996868133545,
        8.50118137896061
      ],
      "result": [
        {
          "answers": {
            "team": {
              "type": "choice",
              "choice": "billing",
              "confidence": 0.9713873863220215,
              "probabilities": {
                "billing": 0.9713873863220215,
                "technical": 0.028612619265913963
              }
            }
          },
          "usage": {
            "input_tokens": 45,
            "output_tokens": 0
          }
        },
        {
          "answers": {
            "team": {
              "type": "choice",
              "choice": "technical",
              "confidence": 0.995719850063324,
              "probabilities": {
                "billing": 0.004280185326933861,
                "technical": 0.995719850063324
              }
            }
          },
          "usage": {
            "input_tokens": 46,
            "output_tokens": 0
          }
        },
        {
          "answers": {
            "team": {
              "type": "choice",
              "choice": "billing",
              "confidence": 0.9713873863220215,
              "probabilities": {
                "billing": 0.9713873863220215,
                "technical": 0.028612619265913963
              }
            }
          },
          "usage": {
            "input_tokens": 45,
            "output_tokens": 0
          }
        },
        {
          "answers": {
            "team": {
              "type": "choice",
              "choice": "technical",
              "confidence": 0.995719850063324,
              "probabilities": {
                "billing": 0.004280185326933861,
                "technical": 0.995719850063324
              }
            }
          },
          "usage": {
            "input_tokens": 46,
            "output_tokens": 0
          }
        },
        {
          "answers": {
            "team": {
              "type": "choice",
              "choice": "billing",
              "confidence": 0.9713873863220215,
              "probabilities": {
                "billing": 0.9713873863220215,
                "technical": 0.028612619265913963
              }
            }
          },
          "usage": {
            "input_tokens": 45,
            "output_tokens": 0
          }
        },
        {
          "answers": {
            "team": {
              "type": "choice",
              "choice": "technical",
              "confidence": 0.995719850063324,
              "probabilities": {
                "billing": 0.004280185326933861,
                "technical": 0.995719850063324
              }
            }
          },
          "usage": {
            "input_tokens": 46,
            "output_tokens": 0
          }
        },
        {
          "answers": {
            "team": {
              "type": "choice",
              "choice": "billing",
              "confidence": 0.9713873863220215,
              "probabilities": {
                "billing": 0.9713873863220215,
                "technical": 0.028612619265913963
              }
            }
          },
          "usage": {
            "input_tokens": 45,
            "output_tokens": 0
          }
        },
        {
          "answers": {
            "team": {
              "type": "choice",
              "choice": "technical",
              "confidence": 0.995719850063324,
              "probabilities": {
                "billing": 0.004280185326933861,
                "technical": 0.995719850063324
              }
            }
          },
          "usage": {
            "input_tokens": 46,
            "output_tokens": 0
          }
        }
      ],
      "classification_correct": true,
      "peak_allocated_bytes": 1209867264,
      "peak_reserved_bytes": 8164212736,
      "nvidia_smi_used_mib": "8481",
      "process_max_rss_kib": 4261532
    },
    {
      "label": "cuda_fp16_image_512",
      "dtype": "float16",
      "fixture": "synthetic solid red RGB image, 512x512",
      "expected_choice": "billing",
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        14.451222494244576,
        11.71690970659256,
        11.358479037880898
      ],
      "result": {
        "answers": {
          "team": {
            "type": "choice",
            "choice": "technical",
            "confidence": 0.987129271030426,
            "probabilities": {
              "billing": 0.01287075038999319,
              "technical": 0.987129271030426
            }
          }
        },
        "usage": {
          "input_tokens": 281,
          "output_tokens": 0
        }
      },
      "classification_correct": false,
      "peak_allocated_bytes": 1222035456,
      "peak_reserved_bytes": 8164212736,
      "nvidia_smi_used_mib": "8481",
      "process_max_rss_kib": 4261532
    },
    {
      "label": "cuda_fp16_audio_1s",
      "dtype": "float16",
      "fixture": "synthetic silence, 16000 Hz mono, 1 second; API check only",
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        19.485503435134888,
        18.97764950990677,
        18.72187852859497
      ],
      "result": {
        "answers": {
          "team": {
            "type": "choice",
            "choice": "technical",
            "confidence": 0.9998421669006348,
            "probabilities": {
              "billing": 0.00015781863476149738,
              "technical": 0.9998421669006348
            }
          }
        },
        "usage": {
          "input_tokens": 56,
          "output_tokens": 0
        }
      },
      "peak_allocated_bytes": 1199254016,
      "peak_reserved_bytes": 8164212736,
      "nvidia_smi_used_mib": "8497",
      "process_max_rss_kib": 4261532
    },
    {
      "label": "cpu_fp32_text_0",
      "dtype": "float32",
      "input": "I was charged twice. Please refund the duplicate payment.",
      "cpu_threads": 8,
      "expected_choice": "billing",
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        59.924086555838585,
        59.30124409496784,
        59.049561619758606
      ],
      "result": {
        "answers": {
          "team": {
            "type": "choice",
            "choice": "billing",
            "confidence": 0.9713522791862488,
            "probabilities": {
              "billing": 0.9713522791862488,
              "technical": 0.02864774689078331
            }
          }
        },
        "usage": {
          "input_tokens": 45,
          "output_tokens": 0
        }
      },
      "classification_correct": true,
      "process_max_rss_kib": 4261532
    },
    {
      "label": "cpu_fp32_text_1",
      "dtype": "float32",
      "input": "The application crashes at startup. Please help me fix it.",
      "cpu_threads": 8,
      "expected_choice": "technical",
      "status": "passed",
      "warmup_excluded": true,
      "latency_ms": [
        58.10386687517166,
        57.91022628545761,
        59.203965589404106
      ],
      "result": {
        "answers": {
          "team": {
            "type": "choice",
            "choice": "technical",
            "confidence": 0.9957237243652344,
            "probabilities": {
              "billing": 0.004276310093700886,
              "technical": 0.9957237243652344
            }
          }
        },
        "usage": {
          "input_tokens": 46,
          "output_tokens": 0
        }
      },
      "classification_correct": true,
      "process_max_rss_kib": 4261532
    }
  ],
  "files": [
    {
      "file": "model.safetensors",
      "bytes": 2348774500,
      "sha256": "0713bb05270c2685ad106522f4092bceeeb3a93cf79b401f399a712296c911e1"
    }
  ],
  "load_peak_allocated_bytes": 1187181056,
  "load_peak_reserved_bytes": 1210056704,
  "media_exclusivity": {
    "status": "passed",
    "error": "a request carries images or audio, not both"
  },
  "status": "completed"
}