{
  "device": "NVIDIA RTX PRO 6000 Blackwell Server Edition",
  "attention": "sdpa",
  "steps": 12,
  "seed": 440420,
  "hourly_usd": {
    "one_gpu": 2.09,
    "two_gpu": 4.18
  },
  "results": [
    {
      "resolution": [
        864,
        480
      ],
      "frames": 141,
      "video_seconds_at_24fps": 5.875,
      "one_gpu": {
        "mode": "tensor",
        "sampling_seconds": 28.500914809992537,
        "sampling_cost_usd": 0.016546364431356778
      },
      "two_gpu": {
        "mode": "ulysses",
        "sampling_seconds": 23.494563594460487,
        "sampling_cost_usd": 0.027279798840234674,
        "speedup": 1.2130855163750494,
        "scaling_efficiency": 0.6065427581875247,
        "cost_premium": 0.6486883842916646
      }
    },
    {
      "resolution": [
        1344,
        768
      ],
      "frames": 124,
      "video_seconds_at_24fps": 5.166666666666667,
      "one_gpu": {
        "mode": "tensor",
        "sampling_seconds": 97.94385590963066,
        "sampling_cost_usd": 0.05686184968086891
      },
      "two_gpu": {
        "mode": "ulysses",
        "sampling_seconds": 63.132430186495185,
        "sampling_cost_usd": 0.07330376616098608,
        "speedup": 1.5514032268408078,
        "scaling_efficiency": 0.7757016134204039,
        "cost_premium": 0.2891554983243718
      }
    },
    {
      "resolution": [
        1344,
        768
      ],
      "frames": 243,
      "video_seconds_at_24fps": 10.125,
      "one_gpu": {
        "mode": "tensor",
        "sampling_seconds": 311.01632468774915,
        "sampling_cost_usd": 0.18056225516594326
      },
      "two_gpu": {
        "mode": "ulysses",
        "sampling_seconds": 180.68109439313412,
        "sampling_cost_usd": 0.2097908262675835,
        "speedup": 1.7213551076407902,
        "scaling_efficiency": 0.8606775538203951,
        "cost_premium": 0.16187531040071534
      }
    }
  ],
  "two_gpu_mode_comparison": [
    {
      "resolution": [
        864,
        480
      ],
      "frames": 141,
      "ulysses_sampling_seconds": 23.946259677002672,
      "tensor_sampling_seconds": 28.037104761999217
    },
    {
      "resolution": [
        1344,
        768
      ],
      "frames": 124,
      "ulysses_sampling_seconds": 66.31268315999478,
      "tensor_sampling_seconds": 74.59926067800552
    },
    {
      "resolution": [
        1344,
        768
      ],
      "frames": 243,
      "ulysses_sampling_seconds": 190.96160273600253,
      "tensor_sampling_seconds": 203.40585646100226
    }
  ],
  "topology": {
    "benchmark_host": "SYS between GPUs, separate NUMA nodes, no NVLink",
    "diagnostic_host": "NODE between GPUs, same NUMA node, no NVLink",
    "p2p_read": "OK in both directions",
    "p2p_write": "OK in both directions",
    "nccl_version": "2.27.7+cuda13.0",
    "nccl_transport": "P2P/CUMEM",
    "nccl_gdr": true,
    "nccl_nvls_channels": 0,
    "nccl_log": "/runpod-volume/h3-benchmarks/rtxpro6000-server-2gpu-nccl-transport.log"
  },
  "cost_scope": "Sampling wall time only. Model/Qwen loading, text conditioning, VAE decode, media encoding, muxing, and pod startup are excluded.",
  "notes": [
    "Two-GPU Ulysses timing in the primary results uses the better NODE topology diagnostic host.",
    "The separate two-GPU mode comparison was measured on the SYS topology host.",
    "Ulysses was faster than tensor parallelism at every tested shape.",
    "Cross-mode and cross-device latent parity was not measured because latents were not retained."
  ]
}