vllm-omni/tests/dfx/perf/tests/test_bagel_vllm_omni.json

[
  {
    "test_name": "test_bagel_single_device_single_stage_t2i",
    "mark": [
      {
        "hardware_marks": {
          "res": {
            "cuda": "H100"
          },
          "num_cards": 1
        }
      },
      "local_model",
      "diffusion"
    ],
    "description": "Single-stage BAGEL (TP=1, CFG=1), t2i Task",
    "server_type": "vllm-omni",
    "server_params": {
      "model": "ByteDance-Seed/BAGEL-7B-MoT",
      "serve_args": {
        "enable-diffusion-pipeline-profiler": true,
        "deploy-config": "../vllm_omni/deploy/bagel_single_stage.yaml",
        "no-async-chunk": true,
        "tensor-parallel-size": 1,
        "cfg-parallel-size": 1,
        "gpu-memory-utilization": 0.90,
        "max-model-len": 8192,
        "max-num-batched-tokens": 9216
      }
    },
    "benchmark_params": [
      {
        "name": "512x512_t2i_steps20",
        "dataset": "random",
        "task": "t2i",
        "width": 512,
        "height": 512,
        "num-inference-steps": 20,
        "num-prompts": 20,
        "max-concurrency": 1,
        "enable-negative-prompt": true,
        "baseline": {
          "H100": {
            "throughput_qps": 0.495,
            "latency_mean": 2.0238,
            "peak_memory_mb_max": 29392.0,
            "peak_memory_mb_mean": 29392.0
          }
        }
      }
    ]
  },
  {
    "test_name": "test_bagel_single_device_single_stage_i2i",
    "mark": [
      {
        "hardware_marks": {
          "res": {
            "cuda": "H100"
          },
          "num_cards": 1
        }
      },
      "local_model",
      "diffusion"
    ],
    "description": "Single-stage BAGEL (TP=1, CFG=1), i2i Task",
    "server_type": "vllm-omni",
    "server_params": {
      "model": "ByteDance-Seed/BAGEL-7B-MoT",
      "serve_args": {
        "enable-diffusion-pipeline-profiler": true,
        "deploy-config": "../vllm_omni/deploy/bagel_single_stage.yaml",
        "no-async-chunk": true,
        "tensor-parallel-size": 1,
        "cfg-parallel-size": 1,
        "gpu-memory-utilization": 0.90,
        "max-model-len": 8192,
        "max-num-batched-tokens": 9216
      }
    },
    "benchmark_params": [
      {
        "name": "512x512_i2i_steps20",
        "dataset": "random",
        "task": "i2i",
        "width": 512,
        "height": 512,
        "num-inference-steps": 20,
        "num-prompts": 20,
        "max-concurrency": 1,
        "enable-negative-prompt": true,
        "num-input-images": 1,
        "baseline": {
          "H100": {
            "throughput_qps": 0.3499,
            "latency_mean": 2.8701,
            "peak_memory_mb_max": 30466.0,
            "peak_memory_mb_mean": 30465.0
          }
        }
      }
    ]
  },
  {
    "test_name": "test_bagel_single_device_multi_stage_t2i",
    "mark": [
      {
        "hardware_marks": {
          "res": {
            "cuda": "H100"
          },
          "num_cards": 1
        }
      },
      "local_model",
      "diffusion"
    ],
    "description": "Two-stage BAGEL (bagel.yaml), TP=1, CFG=1, t2i Task",
    "server_type": "vllm-omni",
    "server_params": {
      "model": "ByteDance-Seed/BAGEL-7B-MoT",
      "serve_args": {
        "enable-diffusion-pipeline-profiler": true,
        "deploy-config": "../vllm_omni/deploy/bagel.yaml",
        "no-async-chunk": true,
        "tensor-parallel-size": 1,
        "cfg-parallel-size": 1,
        "gpu-memory-utilization": 0.45,
        "max-model-len": 8192,
        "max-num-batched-tokens": 9216
      }
    },
    "benchmark_params": [
      {
        "name": "512x512_t2i_steps20",
        "dataset": "random",
        "task": "t2i",
        "width": 512,
        "height": 512,
        "num-inference-steps": 20,
        "num-prompts": 20,
        "max-concurrency": 1,
        "enable-negative-prompt": true,
        "baseline": {
          "H100": {
            "throughput_qps": 0.5048,
            "latency_mean": 1.987,
            "peak_memory_mb_max": 29380.0,
            "peak_memory_mb_mean": 29380.0
          }
        }
      }
    ]
  },
  {
    "test_name": "test_bagel_single_device_multi_stage_i2i",
    "mark": [
      {
        "hardware_marks": {
          "res": {
            "cuda": "H100"
          },
          "num_cards": 1
        }
      },
      "local_model",
      "diffusion"
    ],
    "description": "Two-stage BAGEL (bagel.yaml), TP=1, CFG=1, i2i Task",
    "server_type": "vllm-omni",
    "server_params": {
      "model": "ByteDance-Seed/BAGEL-7B-MoT",
      "serve_args": {
        "enable-diffusion-pipeline-profiler": true,
        "deploy-config": "../vllm_omni/deploy/bagel.yaml",
        "no-async-chunk": true,
        "tensor-parallel-size": 1,
        "cfg-parallel-size": 1,
        "gpu-memory-utilization": 0.45,
        "max-model-len": 8192,
        "max-num-batched-tokens": 9216
      }
    },
    "benchmark_params": [
      {
        "name": "512x512_i2i_steps20",
        "dataset": "random",
        "task": "i2i",
        "width": 512,
        "height": 512,
        "num-inference-steps": 20,
        "num-prompts": 20,
        "max-concurrency": 1,
        "enable-negative-prompt": true,
        "num-input-images": 1,
        "baseline": {
          "H100": {
            "throughput_qps": 0.1533,
            "latency_mean": 6.5243,
            "peak_memory_mb_max": 30574.0,
            "peak_memory_mb_mean": 30574.0
          }
        }
      }
    ]
  }
]